From 38d967fc6325af38ca66cbe97eafaa5c3ce9bea4 Mon Sep 17 00:00:00 2001 From: Safi Date: Mon, 6 Apr 2026 14:40:10 +0100 Subject: [PATCH] feat: multi-platform skill files and install routing (Codex, OpenCode, OpenClaw) --- README.md | 15 +- .../2026-04-06-v3-platform-compatibility.md | 581 ++++++++ ...-04-06-v3-platform-compatibility-design.md | 92 ++ graphify/__main__.py | 87 +- graphify/skill-claw.md | 1164 ++++++++++++++++ graphify/skill-codex.md | 1221 +++++++++++++++++ graphify/skill-opencode.md | 1216 ++++++++++++++++ pyproject.toml | 2 +- tests/test_install.py | 85 ++ 9 files changed, 4436 insertions(+), 27 deletions(-) create mode 100644 docs/superpowers/plans/2026-04-06-v3-platform-compatibility.md create mode 100644 docs/superpowers/specs/2026-04-06-v3-platform-compatibility-design.md create mode 100644 graphify/skill-claw.md create mode 100644 graphify/skill-codex.md create mode 100644 graphify/skill-opencode.md create mode 100644 tests/test_install.py diff --git a/README.md b/README.md index a83a8d9a..33a34dbd 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,18 @@ pip install graphifyy && graphify install > The PyPI package is temporarily named `graphifyy` while the `graphify` name is being reclaimed. The CLI and skill command are still `graphify`. -Then open Claude Code in any directory and type: +### Platform support + +| Platform | Install command | +|----------|----------------| +| Claude Code | `graphify install` | +| Codex | `graphify install --platform codex` | +| OpenCode | `graphify install --platform opencode` | +| OpenClaw | `graphify install --platform claw` | + +Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. OpenClaw uses sequential extraction (parallel agent support is still early on that platform). + +Then open your AI coding assistant and type: ``` /graphify . @@ -131,7 +142,7 @@ Works with any mix of file types: **Hyperedges** - group relationships connecting 3+ nodes that pairwise edges can't express. All classes implementing a shared protocol, all functions in an auth flow, all concepts from a paper section forming one idea. -**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files. +**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files. The first run extracts and builds the graph (this costs tokens). Every subsequent query reads the compact graph instead of raw files — that's where the savings compound. The SHA256 cache means re-runs only re-process changed files. **Auto-sync** (`--watch`) - run in a background terminal and the graph updates itself as your codebase changes. Code file saves trigger an instant rebuild (AST only, no LLM). Doc/image changes notify you to run `--update` for the LLM re-pass. diff --git a/docs/superpowers/plans/2026-04-06-v3-platform-compatibility.md b/docs/superpowers/plans/2026-04-06-v3-platform-compatibility.md new file mode 100644 index 00000000..2dc86fd5 --- /dev/null +++ b/docs/superpowers/plans/2026-04-06-v3-platform-compatibility.md @@ -0,0 +1,581 @@ +# v3 Platform Compatibility Implementation Plan + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. + +**Goal:** Add Codex, OpenCode, and OpenClaw platform support via platform-specific skill files and a `graphify install --platform X` flag. + +**Architecture:** The only section that differs between platforms is Step B2 (semantic extraction subagent dispatch) in skill.md. Three new skill files are created — one per platform — each identical to skill.md except for that one section. The `install()` function in `__main__.py` gains a `--platform` flag that copies the right skill file to the right config directory. + +**Tech Stack:** Python 3.10+, pathlib, shutil, argparse (no new deps) + +--- + +## File Map + +| File | Action | Purpose | +|------|--------|---------| +| `graphify/skill.md` | Read-only | Source of truth — unchanged | +| `graphify/skill-codex.md` | Create | Codex variant (spawn_agent + wait) | +| `graphify/skill-opencode.md` | Create | OpenCode variant (@mention dispatch) | +| `graphify/skill-claw.md` | Create | OpenClaw variant (sequential extraction) | +| `graphify/__main__.py` | Modify | Add --platform flag to install() and main() | +| `pyproject.toml` | Modify | Add 3 new skill files to package-data | +| `tests/test_install.py` | Create | Platform routing tests | +| `README.md` | Modify | Platform table + token efficiency clarification | + +--- + +## Task 1: Create the v3 branch + +**Files:** none (git only) + +- [ ] **Step 1: Create and switch to v3 branch** + +```bash +cd /home/safi/graphify +git checkout -b v3 +``` + +Expected: `Switched to a new branch 'v3'` + +- [ ] **Step 2: Verify branch** + +```bash +git branch --show-current +``` + +Expected: `v3` + +--- + +## Task 2: Create `skill-codex.md` + +skill-codex.md is identical to skill.md with one change: Step B2 replaces `Agent` tool calls with `spawn_agent` + `wait` + `close_agent` calls. + +**Files:** +- Create: `graphify/skill-codex.md` + +- [ ] **Step 1: Copy skill.md as the base** + +```bash +cp graphify/skill.md graphify/skill-codex.md +``` + +- [ ] **Step 2: Open `graphify/skill-codex.md` and replace the Step B2 section** + +Find this block (starts at "**Step B2 - Dispatch ALL subagents in a single message**", ends before "**Step B3**"): + +Replace the entire Step B2 section with: + +```markdown +**Step B2 - Dispatch ALL subagents in a single message (Codex)** + +> **Codex platform:** This step uses `spawn_agent` + `wait` + `close_agent` instead of the Agent tool. +> Requires `multi_agent = true` in `~/.codex/config.toml`. If you get an error about multi-agent support, ask the user to add that config line and restart Codex. + +Call `spawn_agent` once per chunk — all in the same response so they run in parallel: + +``` +spawn_agent(agent_type="worker", message="Your task is to perform the following. Follow the instructions below exactly.\n\n\nYou are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment.\nOutput ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble.\n\nFiles (chunk CHUNK_NUM of TOTAL_CHUNKS):\nFILE_LIST\n\n[copy the extraction rules and JSON schema verbatim from the existing Step B2 content — it's already in the file from the cp step]\n\n\nExecute this now. Output ONLY the structured JSON response.") +``` + +Collect all handles. Then for each handle: +``` +result = wait(handle) +close_agent(handle) +``` + +Parse each result as JSON. Accumulate nodes/edges/hyperedges across all results into `.graphify_semantic_new.json`. + +If `spawn_agent` is not available, tell the user: "Codex multi-agent support is not enabled. Add `multi_agent = true` under `[features]` in `~/.codex/config.toml` and restart Codex." +``` + +- [ ] **Step 3: Verify the file looks correct** + +```bash +grep -n "spawn_agent\|Step B2\|Step B3" graphify/skill-codex.md | head -20 +``` + +Expected: lines showing spawn_agent in B2 and Step B3 after it. + +- [ ] **Step 4: Commit** + +```bash +git add graphify/skill-codex.md +git commit -m "add skill-codex.md for Codex platform (spawn_agent parallel extraction)" +``` + +--- + +## Task 3: Create `skill-opencode.md` + +**Files:** +- Create: `graphify/skill-opencode.md` + +- [ ] **Step 1: Copy skill.md as the base** + +```bash +cp graphify/skill.md graphify/skill-opencode.md +``` + +- [ ] **Step 2: Open `graphify/skill-opencode.md` and replace the Step B2 section** + +Replace the entire Step B2 section with: + +```markdown +**Step B2 - Dispatch ALL subagents in a single message (OpenCode)** + +> **OpenCode platform:** This step uses OpenCode's `@mention` dispatch instead of the Agent tool. + +Dispatch all chunks in a single response. Each `@mention` runs in parallel: + +``` +@agent Chunk CHUNK_NUM of TOTAL_CHUNKS: You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment. Output ONLY valid JSON matching the schema below. + +Files: +FILE_LIST + +[copy the extraction rules and JSON schema verbatim from the existing Step B2 content — already in the file from the cp step] +``` + +One `@mention` block per chunk. All in the same message — this is what makes them parallel. + +Wait for all agents to return. Parse each response as JSON. Accumulate nodes/edges/hyperedges across all results into `.graphify_semantic_new.json`. +``` + +- [ ] **Step 3: Verify the file looks correct** + +```bash +grep -n "@mention\|Step B2\|Step B3" graphify/skill-opencode.md | head -20 +``` + +Expected: lines showing @mention in B2 and Step B3 after it. + +- [ ] **Step 4: Commit** + +```bash +git add graphify/skill-opencode.md +git commit -m "add skill-opencode.md for OpenCode platform (@mention parallel extraction)" +``` + +--- + +## Task 4: Create `skill-claw.md` + +OpenClaw's agent support is MVP/incomplete so extraction is sequential — the orchestrating LLM reads each file and extracts directly. + +**Files:** +- Create: `graphify/skill-claw.md` + +- [ ] **Step 1: Copy skill.md as the base** + +```bash +cp graphify/skill.md graphify/skill-claw.md +``` + +- [ ] **Step 2: Open `graphify/skill-claw.md` and replace the Step B2 section** + +Replace the entire Step B2 section with: + +```markdown +**Step B2 - Sequential extraction (OpenClaw)** + +> **OpenClaw platform:** OpenClaw's multi-agent support is still early. Extraction runs sequentially — you read each file yourself and extract directly. This is slower than parallel platforms but reliable. + +Load files from `.graphify_uncached.txt`. For each file, one at a time: + +1. Read the file contents +2. Extract nodes, edges, and hyperedges following the same rules and schema as the parallel variant (see schema below) +3. Accumulate results into a running JSON object + +Apply all the same extraction rules: +- EXTRACTED / INFERRED / AMBIGUOUS confidence with confidence_score on every edge +- rationale_for nodes for design decisions and WHY comments +- semantically_similar_to edges for cross-file conceptual links (non-obvious only) +- hyperedges for groups of 3+ nodes (max 3 per file) +- DEEP_MODE: more aggressive INFERRED edges if --mode deep was given + +Schema (same as parallel variant): +{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"relative/path","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"relative/path"}],"input_tokens":0,"output_tokens":0} + +After processing all files, write the accumulated result to `.graphify_semantic_new.json`. +``` + +- [ ] **Step 3: Also remove the timing estimate block from Step B** + +In skill-claw.md, find and remove this paragraph (it only applies to parallel dispatch): + +``` +Before dispatching subagents, print a timing estimate: +- Load `total_words` and file counts from `.graphify_detect.json` +- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25) +- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit)) +- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys" +``` + +Replace with: + +``` +Print: "Semantic extraction: N files (sequential — OpenClaw platform)" +``` + +- [ ] **Step 4: Verify** + +```bash +grep -n "sequential\|Step B2\|Step B3\|spawn_agent\|@mention" graphify/skill-claw.md | head -20 +``` + +Expected: "sequential" appears in B2, no spawn_agent or @mention. + +- [ ] **Step 5: Commit** + +```bash +git add graphify/skill-claw.md +git commit -m "add skill-claw.md for OpenClaw platform (sequential extraction)" +``` + +--- + +## Task 5: Update `pyproject.toml` package-data + +**Files:** +- Modify: `pyproject.toml` + +- [ ] **Step 1: Update package-data to include the three new skill files** + +In `pyproject.toml`, find: + +```toml +[tool.setuptools.package-data] +graphify = ["skill.md"] +``` + +Replace with: + +```toml +[tool.setuptools.package-data] +graphify = ["skill.md", "skill-codex.md", "skill-opencode.md", "skill-claw.md"] +``` + +- [ ] **Step 2: Verify** + +```bash +grep -A2 "package-data" pyproject.toml +``` + +Expected: all four skill files listed. + +- [ ] **Step 3: Commit** + +```bash +git add pyproject.toml +git commit -m "include platform skill files in package-data" +``` + +--- + +## Task 6: Add `--platform` flag to install command + +**Files:** +- Modify: `graphify/__main__.py` + +- [ ] **Step 1: Write the failing test first** + +Create `tests/test_install.py`: + +```python +"""Tests for graphify install --platform routing.""" +import shutil +from pathlib import Path +import pytest +from unittest.mock import patch + + +PLATFORMS = { + "claude": ("skill.md", ".claude/skills/graphify/SKILL.md"), + "codex": ("skill-codex.md", ".agents/skills/graphify/SKILL.md"), + "opencode": ("skill-opencode.md", ".config/opencode/skills/graphify/SKILL.md"), + "claw": ("skill-claw.md", ".claw/skills/graphify/SKILL.md"), +} + + +def test_install_default_uses_claude_skill(tmp_path): + """install() with no platform copies skill.md to ~/.claude/skills/graphify/SKILL.md""" + from graphify.__main__ import install + with patch("graphify.__main__.Path.home", return_value=tmp_path): + install(platform="claude") + dst = tmp_path / ".claude" / "skills" / "graphify" / "SKILL.md" + assert dst.exists() + + +def test_install_codex_copies_correct_file(tmp_path): + from graphify.__main__ import install + with patch("graphify.__main__.Path.home", return_value=tmp_path): + install(platform="codex") + dst = tmp_path / ".agents" / "skills" / "graphify" / "SKILL.md" + assert dst.exists() + + +def test_install_opencode_copies_correct_file(tmp_path): + from graphify.__main__ import install + with patch("graphify.__main__.Path.home", return_value=tmp_path): + install(platform="opencode") + dst = tmp_path / ".config" / "opencode" / "skills" / "graphify" / "SKILL.md" + assert dst.exists() + + +def test_install_claw_copies_correct_file(tmp_path): + from graphify.__main__ import install + with patch("graphify.__main__.Path.home", return_value=tmp_path): + install(platform="claw") + dst = tmp_path / ".claw" / "skills" / "graphify" / "SKILL.md" + assert dst.exists() + + +def test_install_unknown_platform_exits(tmp_path): + from graphify.__main__ import install + with patch("graphify.__main__.Path.home", return_value=tmp_path): + with pytest.raises(SystemExit): + install(platform="unknown") + + +def test_all_skill_files_exist_in_package(): + """Verify all platform skill files are present in the installed package.""" + import graphify + pkg_dir = Path(graphify.__file__).parent + for src_name, _ in PLATFORMS.values(): + skill_path = pkg_dir / src_name + assert skill_path.exists(), f"Missing skill file: {src_name}" +``` + +- [ ] **Step 2: Run the test to verify it fails** + +```bash +python -m pytest tests/test_install.py -v --tb=short 2>&1 | head -40 +``` + +Expected: FAIL — `install()` doesn't accept a `platform` argument yet. + +- [ ] **Step 3: Update `install()` in `graphify/__main__.py`** + +Replace the current `install()` function and add `_PLATFORM_CONFIG`: + +```python +_PLATFORM_CONFIG = { + "claude": { + "skill_file": "skill.md", + "skill_dst": Path(".claude") / "skills" / "graphify" / "SKILL.md", + "claude_md": True, # only Claude Code gets CLAUDE.md registration + }, + "codex": { + "skill_file": "skill-codex.md", + "skill_dst": Path(".agents") / "skills" / "graphify" / "SKILL.md", + "claude_md": False, + }, + "opencode": { + "skill_file": "skill-opencode.md", + "skill_dst": Path(".config") / "opencode" / "skills" / "graphify" / "SKILL.md", + "claude_md": False, + }, + "claw": { + "skill_file": "skill-claw.md", + "skill_dst": Path(".claw") / "skills" / "graphify" / "SKILL.md", + "claude_md": False, + }, +} + + +def install(platform: str = "claude") -> None: + if platform not in _PLATFORM_CONFIG: + print(f"error: unknown platform '{platform}'. Choose from: {', '.join(_PLATFORM_CONFIG)}", file=sys.stderr) + sys.exit(1) + + cfg = _PLATFORM_CONFIG[platform] + skill_src = Path(__file__).parent / cfg["skill_file"] + if not skill_src.exists(): + print(f"error: {cfg['skill_file']} not found in package - reinstall graphify", file=sys.stderr) + sys.exit(1) + + skill_dst = Path.home() / cfg["skill_dst"] + skill_dst.parent.mkdir(parents=True, exist_ok=True) + shutil.copy(skill_src, skill_dst) + print(f" skill installed → {skill_dst}") + + if cfg["claude_md"]: + # Register in ~/.claude/CLAUDE.md (Claude Code only) + claude_md = Path.home() / ".claude" / "CLAUDE.md" + if claude_md.exists(): + content = claude_md.read_text() + if "graphify" in content: + print(f" CLAUDE.md → already registered (no change)") + else: + claude_md.write_text(content.rstrip() + _SKILL_REGISTRATION) + print(f" CLAUDE.md → skill registered in {claude_md}") + else: + claude_md.parent.mkdir(parents=True, exist_ok=True) + claude_md.write_text(_SKILL_REGISTRATION.lstrip()) + print(f" CLAUDE.md → created at {claude_md}") + + print() + print("Done. Open your AI coding assistant and type:") + print() + print(" /graphify .") + print() +``` + +- [ ] **Step 4: Update `main()` to pass `--platform` to `install()`** + +In `main()`, find the `if cmd == "install":` block: + +```python + if cmd == "install": + install() +``` + +Replace with: + +```python + if cmd == "install": + platform = "claude" + args = sys.argv[2:] + i = 0 + while i < len(args): + if args[i].startswith("--platform="): + platform = args[i].split("=", 1)[1] + i += 1 + elif args[i] == "--platform" and i + 1 < len(args): + platform = args[i + 1] + i += 2 + else: + i += 1 + install(platform=platform) +``` + +- [ ] **Step 5: Update the help text in `main()`** + +Find: +```python + print(" install copy skill to ~/.claude/skills/ and register in CLAUDE.md") +``` + +Replace with: +```python + print(" install [--platform P] copy skill to platform config dir (claude|codex|opencode|claw)") +``` + +- [ ] **Step 6: Run tests to verify they pass** + +```bash +python -m pytest tests/test_install.py -v --tb=short +``` + +Expected: all 6 tests PASS. + +- [ ] **Step 7: Run the full test suite to check for regressions** + +```bash +python -m pytest tests/ -q --tb=short 2>&1 | tail -20 +``` + +Expected: existing tests still pass. + +- [ ] **Step 8: Commit** + +```bash +git add graphify/__main__.py tests/test_install.py +git commit -m "add --platform flag to graphify install (codex, opencode, claw)" +``` + +--- + +## Task 7: Update README + +**Files:** +- Modify: `README.md` + +- [ ] **Step 1: Add platform support table under the Install section** + +After the `pip install graphifyy && graphify install` code block, add: + +```markdown +### Platform support + +| Platform | Install command | +|----------|----------------| +| Claude Code | `graphify install` | +| Codex | `graphify install --platform codex` | +| OpenCode | `graphify install --platform opencode` | +| OpenClaw | `graphify install --platform claw` | + +Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. OpenClaw uses sequential extraction (parallel agent support is still early on that platform). +``` + +- [ ] **Step 2: Clarify token efficiency — find the benchmark section** + +Find the line: +``` +**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files. +``` + +Replace with: +``` +**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files. The first run extracts and builds the graph (this costs tokens). Every subsequent query reads the compact graph instead of raw files — that's where the savings compound. The SHA256 cache means re-runs only re-process changed files. +``` + +- [ ] **Step 3: Verify README renders correctly** + +```bash +grep -n "Platform support\|multi_agent\|first run extracts" README.md +``` + +Expected: all three lines found. + +- [ ] **Step 4: Commit** + +```bash +git add README.md +git commit -m "add platform support table and clarify token efficiency in README" +``` + +--- + +## Task 8: Final verification + +- [ ] **Step 1: Run the full test suite** + +```bash +python -m pytest tests/ -q --tb=short 2>&1 | tail -20 +``` + +Expected: all tests pass, no regressions. + +- [ ] **Step 2: Verify all four skill files are present in the package** + +```bash +ls graphify/skill*.md +``` + +Expected: +``` +graphify/skill.md +graphify/skill-codex.md +graphify/skill-opencode.md +graphify/skill-claw.md +``` + +- [ ] **Step 3: Smoke test each install path** + +```bash +python -m graphify.__main__ install --platform codex 2>&1 | head -5 +python -m graphify.__main__ install --platform opencode 2>&1 | head -5 +python -m graphify.__main__ install --platform claw 2>&1 | head -5 +python -m graphify.__main__ install --platform unknown 2>&1 +``` + +Expected: first three print "skill installed →", last prints "error: unknown platform". + +- [ ] **Step 4: Push v3 branch** + +```bash +git push -u origin v3 +``` diff --git a/docs/superpowers/specs/2026-04-06-v3-platform-compatibility-design.md b/docs/superpowers/specs/2026-04-06-v3-platform-compatibility-design.md new file mode 100644 index 00000000..d04b86bb --- /dev/null +++ b/docs/superpowers/specs/2026-04-06-v3-platform-compatibility-design.md @@ -0,0 +1,92 @@ +# v3 Platform Compatibility Design + +**Date:** 2026-04-06 +**Status:** Approved + +## Problem + +graphify's `skill.md` uses the Claude Code `Agent` tool for parallel semantic extraction. Users on Codex, OpenCode, and OpenClaw cannot use the skill. v3 adds platform-specific skill files so graphify works natively on all four platforms. + +## Scope + +- Four platform-specific skill files (one already exists) +- `graphify install --platform X` routing +- README clarifications (token efficiency, platform table) +- No always-on project hooks for non-Claude-Code platforms in v3 (deferred to v3.1) + +## What Changes Per Platform + +The semantic extraction step (Step 3B) is the **only** section that differs. AST extraction, merging, clustering, labelling, export, and benchmarking are identical across all platforms and live in the shared Python CLI. + +| Platform | Extraction approach | Rationale | +|----------|-------------------|-----------| +| Claude Code | Parallel `Agent` tool calls | Current behavior, unchanged | +| Codex | Parallel `spawn_agent` + `wait` + `close_agent` | Codex multi-agent API (`multi_agent = true` required) | +| OpenCode | Parallel `@mention` dispatches | OpenCode's native subagent system | +| OpenClaw | Sequential loop — orchestrator extracts each file itself | OpenClaw agent support is MVP/incomplete; sequential is reliable | + +## File Structure + +``` +graphify/ +├── skill.md # Claude Code (unchanged) +├── skill-codex.md # Codex — parallel via spawn_agent +├── skill-opencode.md # OpenCode — parallel via @mention +├── skill-claw.md # OpenClaw — sequential extraction +``` + +All four files ship in the PyPI package via `pyproject.toml` `package-data`. + +## Install Command + +`graphify install` gains a `--platform` flag: + +``` +graphify install # Claude Code → ~/.claude/skills/graphify/SKILL.md +graphify install --platform codex # Codex → ~/.agents/skills/graphify/SKILL.md +graphify install --platform opencode # OpenCode → ~/.config/opencode/skills/graphify/SKILL.md +graphify install --platform claw # OpenClaw → ~/.claw/skills/graphify/SKILL.md +``` + +Behaviour: +- Creates target directory if it doesn't exist (same as current Claude Code install) +- If the platform's root config directory doesn't exist, prints a warning and exits cleanly: `"Codex config directory not found — is Codex installed?"` +- `--platform` is optional; default is `claude` (current behaviour preserved) + +## Skill File Content + +Each file follows the same structure as `skill.md`. The extraction step (Step 3B) is rewritten for the platform: + +**Codex (`skill-codex.md`):** +- For each uncached file, call `spawn_agent(agent_type="worker", message=)` +- Collect all agent handles, call `wait()` on each, then `close_agent()` +- Requires user to have `multi_agent = true` in `~/.codex/config.toml`; skill notes this requirement + +**OpenCode (`skill-opencode.md`):** +- For each uncached file, dispatch via `@mention` with the extraction prompt +- Collect results as agents complete + +**OpenClaw (`skill-claw.md`):** +- Loop over uncached files sequentially +- Orchestrating LLM reads each file and extracts concepts/relationships/edges directly +- Slower than parallel platforms but reliable given OpenClaw's MVP agent status +- A note in the skill explains why: "OpenClaw's multi-agent support is still early; sequential extraction ensures reliability" + +## README Changes + +1. Add "Platform support" table under the Install section +2. Clarify token efficiency: *"First run extracts and builds the graph — subsequent queries read the compact graph instead of raw files. The 71.5x reduction applies per query, and the cache means re-runs only re-process changed files."* +3. Note sequential extraction on OpenClaw with brief explanation + +## Not In Scope (v3) + +- `graphify codex install` / `graphify opencode install` (always-on project hooks for non-CC platforms) — deferred to v3.1 +- Gemini CLI support — not enough information yet +- Copilot CLI support — not enough information yet + +## Testing + +- Unit tests in `tests/test_install.py`: verify `--platform X` routes to correct source file and target path +- Package data test: assert all four skill files are present in the installed package +- No execution tests for platform-specific extraction (requires live platform) +- Evals before release: run each platform skill on a real corpus, verify graph output is equivalent diff --git a/graphify/__main__.py b/graphify/__main__.py index fbd4ec93..cb81d39b 100644 --- a/graphify/__main__.py +++ b/graphify/__main__.py @@ -29,39 +29,66 @@ _SKILL_REGISTRATION = ( ) -def _bundled_skill() -> Path: - """Path to the skill.md bundled with this package.""" - return Path(__file__).parent / "skill.md" +_PLATFORM_CONFIG: dict[str, dict] = { + "claude": { + "skill_file": "skill.md", + "skill_dst": Path(".claude") / "skills" / "graphify" / "SKILL.md", + "claude_md": True, + }, + "codex": { + "skill_file": "skill-codex.md", + "skill_dst": Path(".agents") / "skills" / "graphify" / "SKILL.md", + "claude_md": False, + }, + "opencode": { + "skill_file": "skill-opencode.md", + "skill_dst": Path(".config") / "opencode" / "skills" / "graphify" / "SKILL.md", + "claude_md": False, + }, + "claw": { + "skill_file": "skill-claw.md", + "skill_dst": Path(".claw") / "skills" / "graphify" / "SKILL.md", + "claude_md": False, + }, +} -def install() -> None: - skill_src = _bundled_skill() - if not skill_src.exists(): - print("error: skill.md not found in package - reinstall graphify", file=sys.stderr) +def install(platform: str = "claude") -> None: + if platform not in _PLATFORM_CONFIG: + print( + f"error: unknown platform '{platform}'. Choose from: {', '.join(_PLATFORM_CONFIG)}", + file=sys.stderr, + ) sys.exit(1) - # Copy skill to ~/.claude/skills/graphify/SKILL.md - skill_dst = Path.home() / ".claude" / "skills" / "graphify" / "SKILL.md" + cfg = _PLATFORM_CONFIG[platform] + skill_src = Path(__file__).parent / cfg["skill_file"] + if not skill_src.exists(): + print(f"error: {cfg['skill_file']} not found in package - reinstall graphify", file=sys.stderr) + sys.exit(1) + + skill_dst = Path.home() / cfg["skill_dst"] skill_dst.parent.mkdir(parents=True, exist_ok=True) shutil.copy(skill_src, skill_dst) print(f" skill installed → {skill_dst}") - # Register in ~/.claude/CLAUDE.md - claude_md = Path.home() / ".claude" / "CLAUDE.md" - if claude_md.exists(): - content = claude_md.read_text() - if "graphify" in content: - print(f" CLAUDE.md → already registered (no change)") + if cfg["claude_md"]: + # Register in ~/.claude/CLAUDE.md (Claude Code only) + claude_md = Path.home() / ".claude" / "CLAUDE.md" + if claude_md.exists(): + content = claude_md.read_text() + if "graphify" in content: + print(f" CLAUDE.md → already registered (no change)") + else: + claude_md.write_text(content.rstrip() + _SKILL_REGISTRATION) + print(f" CLAUDE.md → skill registered in {claude_md}") else: - claude_md.write_text(content.rstrip() + _SKILL_REGISTRATION) - print(f" CLAUDE.md → skill registered in {claude_md}") - else: - claude_md.parent.mkdir(parents=True, exist_ok=True) - claude_md.write_text(_SKILL_REGISTRATION.lstrip()) - print(f" CLAUDE.md → created at {claude_md}") + claude_md.parent.mkdir(parents=True, exist_ok=True) + claude_md.write_text(_SKILL_REGISTRATION.lstrip()) + print(f" CLAUDE.md → created at {claude_md}") print() - print("Done. Open Claude Code in any directory and type:") + print("Done. Open your AI coding assistant and type:") print() print(" /graphify .") print() @@ -184,7 +211,7 @@ def main() -> None: print("Usage: graphify ") print() print("Commands:") - print(" install copy skill to ~/.claude/skills/ and register in CLAUDE.md") + print(" install [--platform P] copy skill to platform config dir (claude|codex|opencode|claw)") print(" benchmark [graph.json] measure token reduction vs naive full-corpus approach") print(" hook install install post-commit git hook (auto-rebuilds graph on commit)") print(" hook uninstall remove post-commit git hook") @@ -196,7 +223,19 @@ def main() -> None: cmd = sys.argv[1] if cmd == "install": - install() + platform = "claude" + args = sys.argv[2:] + i = 0 + while i < len(args): + if args[i].startswith("--platform="): + platform = args[i].split("=", 1)[1] + i += 1 + elif args[i] == "--platform" and i + 1 < len(args): + platform = args[i + 1] + i += 2 + else: + i += 1 + install(platform=platform) elif cmd == "claude": subcmd = sys.argv[2] if len(sys.argv) > 2 else "" if subcmd == "install": diff --git a/graphify/skill-claw.md b/graphify/skill-claw.md new file mode 100644 index 00000000..4e967ee2 --- /dev/null +++ b/graphify/skill-claw.md @@ -0,0 +1,1164 @@ +--- +name: graphify +description: any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report +trigger: /graphify +--- + +# /graphify + +Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md. + +## Usage + +``` +/graphify # full pipeline on current directory → Obsidian vault +/graphify # full pipeline on specific path +/graphify --mode deep # thorough extraction, richer INFERRED edges +/graphify --update # incremental - re-extract only new/changed files +/graphify --cluster-only # rerun clustering on existing graph +/graphify --no-viz # skip visualization, just report + JSON +/graphify --html # (HTML is generated by default - this flag is a no-op) +/graphify --svg # also export graph.svg (embeds in Notion, GitHub) +/graphify --graphml # export graph.graphml (Gephi, yEd) +/graphify --neo4j # generate graphify-out/cypher.txt for Neo4j +/graphify --neo4j-push bolt://localhost:7687 # push directly to Neo4j +/graphify --mcp # start MCP stdio server for agent access +/graphify --watch # watch folder, auto-rebuild on code changes (no LLM needed) +/graphify add # fetch URL, save to ./raw, update graph +/graphify add --author "Name" # tag who wrote it +/graphify add --contributor "Name" # tag who added it to the corpus +/graphify query "" # BFS traversal - broad context +/graphify query "" --dfs # DFS - trace a specific path +/graphify query "" --budget 1500 # cap answer at N tokens +/graphify path "AuthModule" "Database" # shortest path between two concepts +/graphify explain "SwinTransformer" # plain-language explanation of a node +``` + +## What graphify is for + +graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. + +Three things it does that Claude alone cannot: +1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. +2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. +3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. + +Use it for: +- A codebase you're new to (understand architecture before touching anything) +- A reading list (papers + tweets + notes → one navigable graph) +- A research corpus (citation graph + concept graph in one) +- Your personal /raw folder (drop everything in, let it grow, query it) + +## What You Must Do When Invoked + +If no path was given, use `.` (current directory). Do not ask the user for a path. + +Follow these steps in order. Do not skip steps. + +### Step 1 - Ensure graphify is installed + +```bash +# Detect the correct Python interpreter (handles pipx, venv, system installs) +GRAPHIFY_BIN=$(which graphify 2>/dev/null) +if [ -n "$GRAPHIFY_BIN" ]; then + PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!') +else + PYTHON="python3" +fi +$PYTHON -c "import graphify" 2>/dev/null || pip install graphifyy -q --break-system-packages 2>&1 | tail -3 +# Write interpreter path for all subsequent steps +$PYTHON -c "import sys; open('.graphify_python', 'w').write(sys.executable)" +``` + +If the import succeeds, print nothing and move straight to Step 2. + +**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.** + +### Step 2 - Detect files + +```bash +$(cat .graphify_python) -c " +import json +from graphify.detect import detect +from pathlib import Path +result = detect(Path('INPUT_PATH')) +print(json.dumps(result)) +" > .graphify_detect.json +``` + +Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead: + +``` +Corpus: X files · ~Y words + code: N files (.py .ts .go ...) + docs: N files (.md .txt ...) + papers: N files (.pdf ...) + images: N files +``` + +Then act on it: +- If `total_files` is 0: stop with "No supported files found in [path]." +- If `skipped_sensitive` is non-empty: mention file count skipped, not the file names. +- If `total_words` > 2,000,000 OR `total_files` > 200: show the warning and the top 5 subdirectories by file count, then ask which subfolder to run on. Wait for the user's answer before proceeding. +- Otherwise: proceed directly to Step 3 - no need to ask anything. + +### Step 3 - Extract entities and relationships + +**Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. + +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). + +**Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** + +Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers. + +#### Part A - Structural extraction for code files + +For any code files detected, run AST extraction in parallel with Part B subagents: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.extract import collect_files, extract +from pathlib import Path +import json + +code_files = [] +detect = json.loads(Path('.graphify_detect.json').read_text()) +for f in detect.get('files', {}).get('code', []): + code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)]) + +if code_files: + result = extract(code_files) + Path('.graphify_ast.json').write_text(json.dumps(result, indent=2)) + print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges') +else: + Path('.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0})) + print('No code files - skipping AST extraction') +" +``` + +#### Part B - Semantic extraction (parallel subagents) + +**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do. + +> **OpenClaw platform:** Multi-agent support is still early on OpenClaw. Extraction runs sequentially — you read and extract each file yourself. This is slower than parallel platforms but fully reliable. + +Print: `"Semantic extraction: N files (sequential — OpenClaw)"` + +**Step B0 - Check extraction cache first** + +Before dispatching any subagents, check which files already have cached extraction results: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.cache import check_semantic_cache +from pathlib import Path + +detect = json.loads(Path('.graphify_detect.json').read_text()) +all_files = [f for files in detect['files'].values() for f in files] + +cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files) + +if cached_nodes or cached_edges or cached_hyperedges: + Path('.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges})) +Path('.graphify_uncached.txt').write_text('\n'.join(uncached)) +print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction') +" +``` + +Only dispatch subagents for files listed in `.graphify_uncached.txt`. If all files are cached, skip to Part C directly. + +**Step B1 - Split into chunks** + +Load files from `.graphify_uncached.txt`. + +**Step B2 - Sequential extraction (OpenClaw)** + +Process each file one at a time. For each file: + +1. Read the file contents +2. Extract nodes, edges, and hyperedges applying the same rules: + - EXTRACTED: relationship explicit in source (import, call, citation) + - INFERRED: reasonable inference (shared structure, implied dependency) + - AMBIGUOUS: uncertain — flag it, do not omit + - Code files: semantic edges AST cannot find. Do not re-extract imports. + - Doc/paper files: named concepts, entities, citations, and rationale nodes (WHY decisions were made → `rationale_for` edges) + - Image files: use vision — understand what the image IS, not just OCR + - DEEP_MODE (if --mode deep): be aggressive with INFERRED edges + - Semantic similarity: if two concepts solve the same problem without a structural link, add `semantically_similar_to` INFERRED edge (confidence 0.6-0.95). Non-obvious cross-file links only. + - Hyperedges: if 3+ nodes share a concept/flow not captured by pairwise edges, add a hyperedge. Max 3 per file. + - confidence_score REQUIRED on every edge: EXTRACTED=1.0, INFERRED=0.6-0.9 (reason individually), AMBIGUOUS=0.1-0.3 +3. Accumulate results across all files + +Schema for each file's output: +{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"relative/path","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"relative/path"}],"input_tokens":0,"output_tokens":0} + +After processing all files, write the accumulated result to `.graphify_semantic_new.json`. + +**Step B3 - Cache and merge** + +For the accumulated result: + +If more than half the chunks failed, stop and tell the user. + +Save new results to cache: +```bash +$(cat .graphify_python) -c " +import json +from graphify.cache import save_semantic_cache +from pathlib import Path + +new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', [])) +print(f'Cached {saved} files') +" +``` + +Merge cached + new results into `.graphify_semantic.json`: +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path + +cached = json.loads(Path('.graphify_cached.json').read_text()) if Path('.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} + +all_nodes = cached['nodes'] + new.get('nodes', []) +all_edges = cached['edges'] + new.get('edges', []) +all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', []) +seen = set() +deduped = [] +for n in all_nodes: + if n['id'] not in seen: + seen.add(n['id']) + deduped.append(n) + +merged = { + 'nodes': deduped, + 'edges': all_edges, + 'hyperedges': all_hyperedges, + 'input_tokens': new.get('input_tokens', 0), + 'output_tokens': new.get('output_tokens', 0), +} +Path('.graphify_semantic.json').write_text(json.dumps(merged, indent=2)) +print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)') +" +``` +Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphify_semantic_new.json` + +#### Part C - Merge AST + semantic into final extraction + +```bash +$(cat .graphify_python) -c " +import sys, json +from pathlib import Path + +ast = json.loads(Path('.graphify_ast.json').read_text()) +sem = json.loads(Path('.graphify_semantic.json').read_text()) + +# Merge: AST nodes first, semantic nodes deduplicated by id +seen = {n['id'] for n in ast['nodes']} +merged_nodes = list(ast['nodes']) +for n in sem['nodes']: + if n['id'] not in seen: + merged_nodes.append(n) + seen.add(n['id']) + +merged_edges = ast['edges'] + sem['edges'] +merged_hyperedges = sem.get('hyperedges', []) +merged = { + 'nodes': merged_nodes, + 'edges': merged_edges, + 'hyperedges': merged_hyperedges, + 'input_tokens': sem.get('input_tokens', 0), + 'output_tokens': sem.get('output_tokens', 0), +} +Path('.graphify_extract.json').write_text(json.dumps(merged, indent=2)) +total = len(merged_nodes) +edges = len(merged_edges) +print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)') +" +``` + +### Step 4 - Build graph, cluster, analyze, generate outputs + +```bash +mkdir -p graphify-out +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from graphify.export import to_json +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +detection = json.loads(Path('.graphify_detect.json').read_text()) + +G = build_from_json(extraction) +communities = cluster(G) +cohesion = score_all(G, communities) +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} +# Placeholder questions - regenerated with real labels in Step 5 +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +to_json(G, communities, 'graphify-out/graph.json') + +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, + 'questions': questions, +} +Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2)) +if G.number_of_nodes() == 0: + print('ERROR: Graph is empty - extraction produced no nodes.') + print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.') + raise SystemExit(1) +print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities') +" +``` + +If this step prints `ERROR: Graph is empty`, stop and tell the user what happened - do not proceed to labeling or visualization. + +Replace INPUT_PATH with the actual path. + +### Step 5 - Label communities + +Read `.graphify_analysis.json`. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading"). + +Then regenerate the report and save the labels for the visualizer: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +detection = json.loads(Path('.graphify_detect.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} + +# LABELS - replace these with the names you chose above +labels = LABELS_DICT + +# Regenerate questions with real community labels (labels affect question phrasing) +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +Path('.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()})) +print('Report updated with community labels') +" +``` + +Replace `LABELS_DICT` with the actual dict you constructed (e.g. `{0: "Attention Mechanism", 1: "Training Pipeline"}`). +Replace INPUT_PATH with the actual path. + +### Step 6 - Generate Obsidian vault (opt-in) + HTML + +**Generate HTML always** (unless `--no-viz`). **Obsidian vault only if `--obsidian` was explicitly given** — skip it otherwise, it generates one file per node. + +If `--obsidian` was given: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_obsidian, to_canvas +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +n = to_obsidian(G, communities, 'graphify-out/obsidian', community_labels=labels or None, cohesion=cohesion) +print(f'Obsidian vault: {n} notes in graphify-out/obsidian/') + +to_canvas(G, communities, 'graphify-out/obsidian/graph.canvas', community_labels=labels or None) +print('Canvas: graphify-out/obsidian/graph.canvas - open in Obsidian for structured community layout') +print() +print('Open graphify-out/obsidian/ as a vault in Obsidian.') +print(' Graph view - nodes colored by community (set automatically)') +print(' graph.canvas - structured layout with communities as groups') +print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries') +" +``` + +Generate the HTML graph (always, unless `--no-viz`): + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_html +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +if G.number_of_nodes() > 5000: + print(f'Graph has {G.number_of_nodes()} nodes - too large for HTML viz. Use Obsidian vault instead.') +else: + to_html(G, communities, 'graphify-out/graph.html', community_labels=labels or None) + print('graph.html written - open in any browser, no server needed') +" +``` + +### Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag) + +**If `--neo4j`** - generate a Cypher file for manual import: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_cypher +from pathlib import Path + +G = build_from_json(json.loads(Path('.graphify_extract.json').read_text())) +to_cypher(G, 'graphify-out/cypher.txt') +print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt') +" +``` + +**If `--neo4j-push `** - push directly to a running Neo4j instance. Ask the user for credentials if not provided: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster +from graphify.export import push_to_neo4j +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} + +result = push_to_neo4j(G, uri='NEO4J_URI', user='NEO4J_USER', password='NEO4J_PASSWORD', communities=communities) +print(f'Pushed to Neo4j: {result[\"nodes\"]} nodes, {result[\"edges\"]} edges') +" +``` + +Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default URI is `bolt://localhost:7687`, default user is `neo4j`. Uses MERGE - safe to re-run without creating duplicates. + +### Step 7b - SVG export (only if --svg flag) + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_svg +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +to_svg(G, communities, 'graphify-out/graph.svg', community_labels=labels or None) +print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs') +" +``` + +### Step 7c - GraphML export (only if --graphml flag) + +```bash +$(cat .graphify_python) -c " +import json +from graphify.build import build_from_json +from graphify.export import to_graphml +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} + +to_graphml(G, communities, 'graphify-out/graph.graphml') +print('graph.graphml written - open in Gephi, yEd, or any GraphML tool') +" +``` + +### Step 7d - MCP server (only if --mcp flag) + +```bash +python3 -m graphify.serve graphify-out/graph.json +``` + +This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `get_neighbors`, `get_community`, `god_nodes`, `graph_stats`, `shortest_path`. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live. + +To configure in Claude Desktop, add to `claude_desktop_config.json`: +```json +{ + "mcpServers": { + "graphify": { + "command": "python3", + "args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"] + } + } +} +``` + +### Step 8 - Token reduction benchmark (only if total_words > 5000) + +If `total_words` from `.graphify_detect.json` is greater than 5,000, run: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.benchmark import run_benchmark, print_benchmark +from pathlib import Path + +detection = json.loads(Path('.graphify_detect.json').read_text()) +result = run_benchmark('graphify-out/graph.json', corpus_words=detection['total_words']) +print_benchmark(result) +" +``` + +Print the output directly in chat. If `total_words <= 5000`, skip silently - the graph value is structural clarity, not token compression, for small corpora. + +--- + +### Step 9 - Save manifest, update cost tracker, clean up, and report + +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path +from datetime import datetime, timezone +from graphify.detect import save_manifest + +# Save manifest for --update +detect = json.loads(Path('.graphify_detect.json').read_text()) +save_manifest(detect['files']) + +# Update cumulative cost tracker +extract = json.loads(Path('.graphify_extract.json').read_text()) +input_tok = extract.get('input_tokens', 0) +output_tok = extract.get('output_tokens', 0) + +cost_path = Path('graphify-out/cost.json') +if cost_path.exists(): + cost = json.loads(cost_path.read_text()) +else: + cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0} + +cost['runs'].append({ + 'date': datetime.now(timezone.utc).isoformat(), + 'input_tokens': input_tok, + 'output_tokens': output_tok, + 'files': detect.get('total_files', 0), +}) +cost['total_input_tokens'] += input_tok +cost['total_output_tokens'] += output_tok +cost_path.write_text(json.dumps(cost, indent=2)) + +print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens') +print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)') +" +rm -f .graphify_detect.json .graphify_extract.json .graphify_ast.json .graphify_semantic.json .graphify_analysis.json .graphify_labels.json .graphify_python +rm -f graphify-out/.needs_update 2>/dev/null || true +``` + +Tell the user (omit the obsidian line unless --obsidian was given): +``` +Graph complete. Outputs in PATH_TO_DIR/graphify-out/ + + graph.html - interactive graph, open in browser + GRAPH_REPORT.md - audit report + graph.json - raw graph data + obsidian/ - Obsidian vault (only if --obsidian was given) +``` + +Replace PATH_TO_DIR with the actual absolute path of the directory that was processed. + +Then paste these sections from GRAPH_REPORT.md directly into the chat: +- God Nodes +- Surprising Connections +- Suggested Questions + +Do NOT paste the full report - just those three sections. Keep it concise. + +Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask: + +> "The most interesting question this graph can answer: **[question]**. Want me to trace it?" + +If the user says yes, run `/graphify query "[question]"` on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report. + +The graph is the map. Your job after the pipeline is to be the guide. + +--- + +## For --update (incremental re-extraction) + +Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time. + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.detect import detect_incremental, save_manifest +from pathlib import Path + +result = detect_incremental(Path('INPUT_PATH')) +new_total = result.get('new_total', 0) +print(json.dumps(result, indent=2)) +Path('.graphify_incremental.json').write_text(json.dumps(result)) +if new_total == 0: + print('No files changed since last run. Nothing to update.') + raise SystemExit(0) +print(f'{new_total} new/changed file(s) to re-extract.') +" +``` + +If new files exist, first check whether all changed files are code files: + +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path + +result = json.loads(open('.graphify_incremental.json').read()) if Path('.graphify_incremental.json').exists() else {} +code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts'} +new_files = result.get('new_files', {}) +all_changed = [f for files in new_files.values() for f in files] +code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed) +print('code_only:', code_only) +" +``` + +If `code_only` is True: print `[graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed)`, run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8. + +If `code_only` is False (any changed file is a doc/paper/image): run the full Steps 3A–3C pipeline as normal. + +Then: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load existing graph +existing_data = json.loads(Path('graphify-out/graph.json').read_text()) +G_existing = json_graph.node_link_graph(existing_data, edges='links') + +# Load new extraction +new_extraction = json.loads(Path('.graphify_extract.json').read_text()) +G_new = build_from_json(new_extraction) + +# Merge: new nodes/edges into existing graph +G_existing.update(G_new) +print(f'Merged: {G_existing.number_of_nodes()} nodes, {G_existing.number_of_edges()} edges') +" +``` + +Then run Steps 4–8 on the merged graph as normal. + +After Step 4, show the graph diff: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.analyze import graph_diff +from graphify.build import build_from_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load old graph (before update) from backup written before merge +old_data = json.loads(Path('.graphify_old.json').read_text()) if Path('.graphify_old.json').exists() else None +new_extract = json.loads(Path('.graphify_extract.json').read_text()) +G_new = build_from_json(new_extract) + +if old_data: + G_old = json_graph.node_link_graph(old_data, edges='links') + diff = graph_diff(G_old, G_new) + print(diff['summary']) + if diff['new_nodes']: + print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5])) + if diff['new_edges']: + print('New edges:', len(diff['new_edges'])) +" +``` + +Before the merge step, save the old graph: `cp graphify-out/graph.json .graphify_old.json` +Clean up after: `rm -f .graphify_old.json` + +--- + +## For --cluster-only + +Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections +from graphify.report import generate +from graphify.export import to_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +detection = {'total_files': 0, 'total_words': 99999, 'needs_graph': True, 'warning': None, + 'files': {'code': [], 'document': [], 'paper': []}} +tokens = {'input': 0, 'output': 0} + +communities = cluster(G) +cohesion = score_all(G, communities) +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} + +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, '.') +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +to_json(G, communities, 'graphify-out/graph.json') + +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, +} +Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2)) +print(f'Re-clustered: {len(communities)} communities') +" +``` + +Then run Steps 5–9 as normal (label communities, generate viz, benchmark, clean up, report). + +--- + +## For /graphify query + +Two traversal modes - choose based on the question: + +| Mode | Flag | Best for | +|------|------|----------| +| BFS (default) | _(none)_ | "What is X connected to?" - broad context, nearest neighbors first | +| DFS | `--dfs` | "How does X reach Y?" - trace a specific chain or dependency path | + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +Load `graphify-out/graph.json`, then: + +1. Find the 1-3 nodes whose label best matches key terms in the question. +2. Run the appropriate traversal from each starting node. +3. Read the subgraph - node labels, edge relations, confidence tags, source locations. +4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact. +5. If the graph lacks enough information, say so - do not hallucinate edges. + +```bash +$(cat .graphify_python) -c " +import sys, json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +question = 'QUESTION' +mode = 'MODE' # 'bfs' or 'dfs' +terms = [t.lower() for t in question.split() if len(t) > 3] + +# Find best-matching start nodes +scored = [] +for nid, ndata in G.nodes(data=True): + label = ndata.get('label', '').lower() + score = sum(1 for t in terms if t in label) + if score > 0: + scored.append((score, nid)) +scored.sort(reverse=True) +start_nodes = [nid for _, nid in scored[:3]] + +if not start_nodes: + print('No matching nodes found for query terms:', terms) + sys.exit(0) + +subgraph_nodes = set() +subgraph_edges = [] + +if mode == 'dfs': + # DFS: follow one path as deep as possible before backtracking. + # Depth-limited to 6 to avoid traversing the whole graph. + visited = set() + stack = [(n, 0) for n in reversed(start_nodes)] + while stack: + node, depth = stack.pop() + if node in visited or depth > 6: + continue + visited.add(node) + subgraph_nodes.add(node) + for neighbor in G.neighbors(node): + if neighbor not in visited: + stack.append((neighbor, depth + 1)) + subgraph_edges.append((node, neighbor)) +else: + # BFS: explore all neighbors layer by layer up to depth 3. + frontier = set(start_nodes) + subgraph_nodes = set(start_nodes) + for _ in range(3): + next_frontier = set() + for n in frontier: + for neighbor in G.neighbors(n): + if neighbor not in subgraph_nodes: + next_frontier.add(neighbor) + subgraph_edges.append((n, neighbor)) + subgraph_nodes.update(next_frontier) + frontier = next_frontier + +# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token) +token_budget = BUDGET # default 2000 +char_budget = token_budget * 4 + +# Score each node by term overlap for ranked output +def relevance(nid): + label = G.nodes[nid].get('label', '').lower() + return sum(1 for t in terms if t in label) + +ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True) + +lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes'] +for nid in ranked_nodes: + d = G.nodes[nid] + lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]') +for u, v in subgraph_edges: + if u in subgraph_nodes and v in subgraph_nodes: + d = G.edges[u, v] + lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}') + +output = '\n'.join(lines) +if len(output) > char_budget: + output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)' +print(output) +" +``` + +Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`, and `BUDGET` with the token budget (default `2000`, or whatever `--budget N` specifies). Then answer based on the subgraph output above. + +After writing the answer, save it back into the graph so it improves future queries: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='QUESTION', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='query', + source_nodes=SOURCE_NODES, # list of node labels cited, or [] +) +print('Query result saved to graphify-out/memory/') +" +``` + +Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph. + +--- + +## For /graphify path + +Find the shortest path between two named concepts in the graph. + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +```bash +$(cat .graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +a_term = 'NODE_A' +b_term = 'NODE_B' + +def find_node(term): + term = term.lower() + scored = sorted( + [(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True + ) + return scored[0][1] if scored and scored[0][0] > 0 else None + +src = find_node(a_term) +tgt = find_node(b_term) + +if not src or not tgt: + print(f'Could not find nodes matching: {a_term!r} or {b_term!r}') + sys.exit(0) + +try: + path = nx.shortest_path(G, src, tgt) + print(f'Shortest path ({len(path)-1} hops):') + for i, nid in enumerate(path): + label = G.nodes[nid].get('label', nid) + if i < len(path) - 1: + edge = G.edges[nid, path[i+1]] + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + print(f' {label} --{rel}--> [{conf}]') + else: + print(f' {label}') +except nx.NetworkXNoPath: + print(f'No path found between {a_term!r} and {b_term!r}') +except nx.NodeNotFound as e: + print(f'Node not found: {e}') +" +``` + +Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant. + +After writing the explanation, save it back: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='Path from NODE_A to NODE_B', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='path_query', + source_nodes=PATH_NODES, # list of node labels on the path +) +print('Path result saved to graphify-out/memory/') +" +``` + +--- + +## For /graphify explain + +Give a plain-language explanation of a single node - everything connected to it. + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +```bash +$(cat .graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +term = 'NODE_NAME' +term_lower = term.lower() + +# Find best matching node +scored = sorted( + [(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True +) +if not scored or scored[0][0] == 0: + print(f'No node matching {term!r}') + sys.exit(0) + +nid = scored[0][1] +data_n = G.nodes[nid] +print(f'NODE: {data_n.get(\"label\", nid)}') +print(f' source: {data_n.get(\"source_file\",\"unknown\")}') +print(f' type: {data_n.get(\"file_type\",\"unknown\")}') +print(f' degree: {G.degree(nid)}') +print() +print('CONNECTIONS:') +for neighbor in G.neighbors(nid): + edge = G.edges[nid, neighbor] + nlabel = G.nodes[neighbor].get('label', neighbor) + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + src_file = G.nodes[neighbor].get('source_file', '') + print(f' --{rel}--> {nlabel} [{conf}] ({src_file})') +" +``` + +Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations. + +After writing the explanation, save it back: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='Explain NODE_NAME', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='explain', + source_nodes=['NODE_NAME'], +) +print('Explanation saved to graphify-out/memory/') +" +``` + +--- + +## For /graphify add + +Fetch a URL and add it to the corpus, then update the graph. + +```bash +$(cat .graphify_python) -c " +import sys +from graphify.ingest import ingest +from pathlib import Path + +try: + out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR') + print(f'Saved to {out}') +except ValueError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +except RuntimeError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +" +``` + +Replace `URL` with the actual URL, `AUTHOR` with the user's name if provided, `CONTRIBUTOR` likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the `--update` pipeline on `./raw` to merge the new file into the existing graph. + +Supported URL types (auto-detected): +- Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author +- arXiv → abstract + metadata saved as `.md` +- PDF → downloaded as `.pdf` +- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Any webpage → converted to markdown via html2text + +--- + +## For --watch + +Start a background watcher that monitors a folder and auto-updates the graph when files change. + +```bash +python3 -m graphify.watch INPUT_PATH --debounce 3 +``` + +Replace INPUT_PATH with the folder to watch. Behavior depends on what changed: + +- **Code files only (.py, .ts, .go, etc.):** re-runs AST extraction + rebuild + cluster immediately, no LLM needed. `graph.json` and `GRAPH_REPORT.md` are updated automatically. +- **Docs, papers, or images:** writes a `graphify-out/needs_update` flag and prints a notification to run `/graphify --update` (LLM semantic re-extraction required). + +Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file. + +Press Ctrl+C to stop. + +For agentic workflows: run `--watch` in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual `/graphify --update` after those waves. + +--- + +## For git commit hook + +Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor. + +```bash +graphify hook install # install +graphify hook uninstall # remove +graphify hook status # check +``` + +After every `git commit`, the hook detects which code files changed (via `git diff HEAD~1`), re-runs AST extraction on those files, and rebuilds `graph.json` and `GRAPH_REPORT.md`. Doc/image changes are ignored by the hook - run `/graphify --update` manually for those. + +If a post-commit hook already exists, graphify appends to it rather than replacing it. + +--- + +## For native CLAUDE.md integration + +Run once per project to make graphify always-on in Claude Code sessions: + +```bash +graphify claude install +``` + +This writes a `## graphify` section to the local `CLAUDE.md` that instructs Claude to check the graph before answering codebase questions and rebuild it after code changes. No manual `/graphify` needed in future sessions. + +```bash +graphify claude uninstall # remove the section +``` + +--- + +## Honesty Rules + +- Never invent an edge. If unsure, use AMBIGUOUS. +- Never skip the corpus check warning. +- Always show token cost in the report. +- Never hide cohesion scores behind symbols - show the raw number. +- Never run HTML viz on a graph with more than 5,000 nodes without warning the user. diff --git a/graphify/skill-codex.md b/graphify/skill-codex.md new file mode 100644 index 00000000..cfd1e921 --- /dev/null +++ b/graphify/skill-codex.md @@ -0,0 +1,1221 @@ +--- +name: graphify +description: any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report +trigger: /graphify +--- + +# /graphify + +Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md. + +## Usage + +``` +/graphify # full pipeline on current directory → Obsidian vault +/graphify # full pipeline on specific path +/graphify --mode deep # thorough extraction, richer INFERRED edges +/graphify --update # incremental - re-extract only new/changed files +/graphify --cluster-only # rerun clustering on existing graph +/graphify --no-viz # skip visualization, just report + JSON +/graphify --html # (HTML is generated by default - this flag is a no-op) +/graphify --svg # also export graph.svg (embeds in Notion, GitHub) +/graphify --graphml # export graph.graphml (Gephi, yEd) +/graphify --neo4j # generate graphify-out/cypher.txt for Neo4j +/graphify --neo4j-push bolt://localhost:7687 # push directly to Neo4j +/graphify --mcp # start MCP stdio server for agent access +/graphify --watch # watch folder, auto-rebuild on code changes (no LLM needed) +/graphify add # fetch URL, save to ./raw, update graph +/graphify add --author "Name" # tag who wrote it +/graphify add --contributor "Name" # tag who added it to the corpus +/graphify query "" # BFS traversal - broad context +/graphify query "" --dfs # DFS - trace a specific path +/graphify query "" --budget 1500 # cap answer at N tokens +/graphify path "AuthModule" "Database" # shortest path between two concepts +/graphify explain "SwinTransformer" # plain-language explanation of a node +``` + +## What graphify is for + +graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. + +Three things it does that Claude alone cannot: +1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. +2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. +3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. + +Use it for: +- A codebase you're new to (understand architecture before touching anything) +- A reading list (papers + tweets + notes → one navigable graph) +- A research corpus (citation graph + concept graph in one) +- Your personal /raw folder (drop everything in, let it grow, query it) + +## What You Must Do When Invoked + +If no path was given, use `.` (current directory). Do not ask the user for a path. + +Follow these steps in order. Do not skip steps. + +### Step 1 - Ensure graphify is installed + +```bash +# Detect the correct Python interpreter (handles pipx, venv, system installs) +GRAPHIFY_BIN=$(which graphify 2>/dev/null) +if [ -n "$GRAPHIFY_BIN" ]; then + PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!') +else + PYTHON="python3" +fi +$PYTHON -c "import graphify" 2>/dev/null || pip install graphifyy -q --break-system-packages 2>&1 | tail -3 +# Write interpreter path for all subsequent steps +$PYTHON -c "import sys; open('.graphify_python', 'w').write(sys.executable)" +``` + +If the import succeeds, print nothing and move straight to Step 2. + +**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.** + +### Step 2 - Detect files + +```bash +$(cat .graphify_python) -c " +import json +from graphify.detect import detect +from pathlib import Path +result = detect(Path('INPUT_PATH')) +print(json.dumps(result)) +" > .graphify_detect.json +``` + +Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead: + +``` +Corpus: X files · ~Y words + code: N files (.py .ts .go ...) + docs: N files (.md .txt ...) + papers: N files (.pdf ...) + images: N files +``` + +Then act on it: +- If `total_files` is 0: stop with "No supported files found in [path]." +- If `skipped_sensitive` is non-empty: mention file count skipped, not the file names. +- If `total_words` > 2,000,000 OR `total_files` > 200: show the warning and the top 5 subdirectories by file count, then ask which subfolder to run on. Wait for the user's answer before proceeding. +- Otherwise: proceed directly to Step 3 - no need to ask anything. + +### Step 3 - Extract entities and relationships + +**Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. + +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). + +**Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** + +Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers. + +#### Part A - Structural extraction for code files + +For any code files detected, run AST extraction in parallel with Part B subagents: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.extract import collect_files, extract +from pathlib import Path +import json + +code_files = [] +detect = json.loads(Path('.graphify_detect.json').read_text()) +for f in detect.get('files', {}).get('code', []): + code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)]) + +if code_files: + result = extract(code_files) + Path('.graphify_ast.json').write_text(json.dumps(result, indent=2)) + print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges') +else: + Path('.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0})) + print('No code files - skipping AST extraction') +" +``` + +#### Part B - Semantic extraction (parallel subagents) + +**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do. + +**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.** + +Before dispatching subagents, print a timing estimate: +- Load `total_words` and file counts from `.graphify_detect.json` +- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25) +- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit)) +- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys" + +**Step B0 - Check extraction cache first** + +Before dispatching any subagents, check which files already have cached extraction results: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.cache import check_semantic_cache +from pathlib import Path + +detect = json.loads(Path('.graphify_detect.json').read_text()) +all_files = [f for files in detect['files'].values() for f in files] + +cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files) + +if cached_nodes or cached_edges or cached_hyperedges: + Path('.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges})) +Path('.graphify_uncached.txt').write_text('\n'.join(uncached)) +print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction') +" +``` + +Only dispatch subagents for files listed in `.graphify_uncached.txt`. If all files are cached, skip to Part C directly. + +**Step B1 - Split into chunks** + +Load files from `.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context). + +**Step B2 - Dispatch ALL subagents in a single message (Codex)** + +> **Codex platform:** Uses `spawn_agent` + `wait` + `close_agent` instead of the Agent tool. +> Requires `multi_agent = true` under `[features]` in `~/.codex/config.toml`. +> If `spawn_agent` is unavailable, tell the user to add that config and restart Codex. + +Call `spawn_agent` once per chunk — ALL in the same response so they run in parallel. Build the message by wrapping the extraction prompt below in task-delegation framing: + +``` +spawn_agent(agent_type="worker", message="Your task is to perform the following. Follow the instructions below exactly.\n\n\n[extraction prompt below, with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE substituted]\n\n\nExecute this now. Output ONLY the structured JSON response.") +``` + +After all agents are dispatched, collect results sequentially: +``` +result = wait(handle); close_agent(handle) # repeat per handle +``` + +Parse each result as JSON. Accumulate nodes/edges/hyperedges across all results and write to `.graphify_semantic_new.json`. + +The extraction prompt each subagent receives (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE): + +``` +You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment. +Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble. + +Files (chunk CHUNK_NUM of TOTAL_CHUNKS): +FILE_LIST + +Rules: +- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2") +- INFERRED: reasonable inference (shared data structure, implied dependency) +- AMBIGUOUS: uncertain - flag for review, do not omit + +Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns). + Do not re-extract imports - AST already has those. +Doc/paper files: extract named concepts, entities, citations. Also extract rationale — sections that explain WHY a decision was made, trade-offs chosen, or design intent. These become nodes with `rationale_for` edges pointing to the concept they explain. +Image files: use vision to understand what the image IS - do not just OCR. + UI screenshot: layout patterns, design decisions, key elements, purpose. + Chart: metric, trend/insight, data source. + Tweet/post: claim as node, author, concepts mentioned. + Diagram: components and connections. + Research figure: what it demonstrates, method, result. + Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS. + +DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps, + shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting. + +Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples: +- Two functions that both validate user input but never call each other +- A class in code and a concept in a paper that describe the same algorithm +- Two error types that handle the same failure mode differently +Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things. + +Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples: +- All classes that implement a common protocol or interface +- All functions in an authentication flow (even if they don't all call each other) +- All concepts from a paper section that form one coherent idea +Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk. + +If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author, + contributor onto every node from that file. + +confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default: +- EXTRACTED edges: confidence_score = 1.0 always +- INFERRED edges: reason about each edge individually. + Direct structural evidence (shared data structure, clear dependency): 0.8-0.9. + Reasonable inference with some uncertainty: 0.6-0.7. + Weak or speculative: 0.4-0.5. Most edges should be 0.6-0.9, not 0.5. +- AMBIGUOUS edges: 0.1-0.3 + +Output exactly this JSON (no other text): +{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"relative/path","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"relative/path"}],"input_tokens":0,"output_tokens":0} +``` + +**Step B3 - Collect, cache, and merge** + +Wait for all subagents. For each result: +- If a subagent returned valid JSON with `nodes` and `edges`, include it and save each file's nodes/edges to the cache +- If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort + +If more than half the chunks failed, stop and tell the user. + +Save new results to cache: +```bash +$(cat .graphify_python) -c " +import json +from graphify.cache import save_semantic_cache +from pathlib import Path + +new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', [])) +print(f'Cached {saved} files') +" +``` + +Merge cached + new results into `.graphify_semantic.json`: +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path + +cached = json.loads(Path('.graphify_cached.json').read_text()) if Path('.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} + +all_nodes = cached['nodes'] + new.get('nodes', []) +all_edges = cached['edges'] + new.get('edges', []) +all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', []) +seen = set() +deduped = [] +for n in all_nodes: + if n['id'] not in seen: + seen.add(n['id']) + deduped.append(n) + +merged = { + 'nodes': deduped, + 'edges': all_edges, + 'hyperedges': all_hyperedges, + 'input_tokens': new.get('input_tokens', 0), + 'output_tokens': new.get('output_tokens', 0), +} +Path('.graphify_semantic.json').write_text(json.dumps(merged, indent=2)) +print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)') +" +``` +Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphify_semantic_new.json` + +#### Part C - Merge AST + semantic into final extraction + +```bash +$(cat .graphify_python) -c " +import sys, json +from pathlib import Path + +ast = json.loads(Path('.graphify_ast.json').read_text()) +sem = json.loads(Path('.graphify_semantic.json').read_text()) + +# Merge: AST nodes first, semantic nodes deduplicated by id +seen = {n['id'] for n in ast['nodes']} +merged_nodes = list(ast['nodes']) +for n in sem['nodes']: + if n['id'] not in seen: + merged_nodes.append(n) + seen.add(n['id']) + +merged_edges = ast['edges'] + sem['edges'] +merged_hyperedges = sem.get('hyperedges', []) +merged = { + 'nodes': merged_nodes, + 'edges': merged_edges, + 'hyperedges': merged_hyperedges, + 'input_tokens': sem.get('input_tokens', 0), + 'output_tokens': sem.get('output_tokens', 0), +} +Path('.graphify_extract.json').write_text(json.dumps(merged, indent=2)) +total = len(merged_nodes) +edges = len(merged_edges) +print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)') +" +``` + +### Step 4 - Build graph, cluster, analyze, generate outputs + +```bash +mkdir -p graphify-out +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from graphify.export import to_json +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +detection = json.loads(Path('.graphify_detect.json').read_text()) + +G = build_from_json(extraction) +communities = cluster(G) +cohesion = score_all(G, communities) +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} +# Placeholder questions - regenerated with real labels in Step 5 +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +to_json(G, communities, 'graphify-out/graph.json') + +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, + 'questions': questions, +} +Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2)) +if G.number_of_nodes() == 0: + print('ERROR: Graph is empty - extraction produced no nodes.') + print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.') + raise SystemExit(1) +print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities') +" +``` + +If this step prints `ERROR: Graph is empty`, stop and tell the user what happened - do not proceed to labeling or visualization. + +Replace INPUT_PATH with the actual path. + +### Step 5 - Label communities + +Read `.graphify_analysis.json`. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading"). + +Then regenerate the report and save the labels for the visualizer: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +detection = json.loads(Path('.graphify_detect.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} + +# LABELS - replace these with the names you chose above +labels = LABELS_DICT + +# Regenerate questions with real community labels (labels affect question phrasing) +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +Path('.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()})) +print('Report updated with community labels') +" +``` + +Replace `LABELS_DICT` with the actual dict you constructed (e.g. `{0: "Attention Mechanism", 1: "Training Pipeline"}`). +Replace INPUT_PATH with the actual path. + +### Step 6 - Generate Obsidian vault (opt-in) + HTML + +**Generate HTML always** (unless `--no-viz`). **Obsidian vault only if `--obsidian` was explicitly given** — skip it otherwise, it generates one file per node. + +If `--obsidian` was given: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_obsidian, to_canvas +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +n = to_obsidian(G, communities, 'graphify-out/obsidian', community_labels=labels or None, cohesion=cohesion) +print(f'Obsidian vault: {n} notes in graphify-out/obsidian/') + +to_canvas(G, communities, 'graphify-out/obsidian/graph.canvas', community_labels=labels or None) +print('Canvas: graphify-out/obsidian/graph.canvas - open in Obsidian for structured community layout') +print() +print('Open graphify-out/obsidian/ as a vault in Obsidian.') +print(' Graph view - nodes colored by community (set automatically)') +print(' graph.canvas - structured layout with communities as groups') +print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries') +" +``` + +Generate the HTML graph (always, unless `--no-viz`): + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_html +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +if G.number_of_nodes() > 5000: + print(f'Graph has {G.number_of_nodes()} nodes - too large for HTML viz. Use Obsidian vault instead.') +else: + to_html(G, communities, 'graphify-out/graph.html', community_labels=labels or None) + print('graph.html written - open in any browser, no server needed') +" +``` + +### Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag) + +**If `--neo4j`** - generate a Cypher file for manual import: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_cypher +from pathlib import Path + +G = build_from_json(json.loads(Path('.graphify_extract.json').read_text())) +to_cypher(G, 'graphify-out/cypher.txt') +print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt') +" +``` + +**If `--neo4j-push `** - push directly to a running Neo4j instance. Ask the user for credentials if not provided: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster +from graphify.export import push_to_neo4j +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} + +result = push_to_neo4j(G, uri='NEO4J_URI', user='NEO4J_USER', password='NEO4J_PASSWORD', communities=communities) +print(f'Pushed to Neo4j: {result[\"nodes\"]} nodes, {result[\"edges\"]} edges') +" +``` + +Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default URI is `bolt://localhost:7687`, default user is `neo4j`. Uses MERGE - safe to re-run without creating duplicates. + +### Step 7b - SVG export (only if --svg flag) + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_svg +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +to_svg(G, communities, 'graphify-out/graph.svg', community_labels=labels or None) +print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs') +" +``` + +### Step 7c - GraphML export (only if --graphml flag) + +```bash +$(cat .graphify_python) -c " +import json +from graphify.build import build_from_json +from graphify.export import to_graphml +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} + +to_graphml(G, communities, 'graphify-out/graph.graphml') +print('graph.graphml written - open in Gephi, yEd, or any GraphML tool') +" +``` + +### Step 7d - MCP server (only if --mcp flag) + +```bash +python3 -m graphify.serve graphify-out/graph.json +``` + +This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `get_neighbors`, `get_community`, `god_nodes`, `graph_stats`, `shortest_path`. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live. + +To configure in Claude Desktop, add to `claude_desktop_config.json`: +```json +{ + "mcpServers": { + "graphify": { + "command": "python3", + "args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"] + } + } +} +``` + +### Step 8 - Token reduction benchmark (only if total_words > 5000) + +If `total_words` from `.graphify_detect.json` is greater than 5,000, run: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.benchmark import run_benchmark, print_benchmark +from pathlib import Path + +detection = json.loads(Path('.graphify_detect.json').read_text()) +result = run_benchmark('graphify-out/graph.json', corpus_words=detection['total_words']) +print_benchmark(result) +" +``` + +Print the output directly in chat. If `total_words <= 5000`, skip silently - the graph value is structural clarity, not token compression, for small corpora. + +--- + +### Step 9 - Save manifest, update cost tracker, clean up, and report + +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path +from datetime import datetime, timezone +from graphify.detect import save_manifest + +# Save manifest for --update +detect = json.loads(Path('.graphify_detect.json').read_text()) +save_manifest(detect['files']) + +# Update cumulative cost tracker +extract = json.loads(Path('.graphify_extract.json').read_text()) +input_tok = extract.get('input_tokens', 0) +output_tok = extract.get('output_tokens', 0) + +cost_path = Path('graphify-out/cost.json') +if cost_path.exists(): + cost = json.loads(cost_path.read_text()) +else: + cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0} + +cost['runs'].append({ + 'date': datetime.now(timezone.utc).isoformat(), + 'input_tokens': input_tok, + 'output_tokens': output_tok, + 'files': detect.get('total_files', 0), +}) +cost['total_input_tokens'] += input_tok +cost['total_output_tokens'] += output_tok +cost_path.write_text(json.dumps(cost, indent=2)) + +print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens') +print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)') +" +rm -f .graphify_detect.json .graphify_extract.json .graphify_ast.json .graphify_semantic.json .graphify_analysis.json .graphify_labels.json .graphify_python +rm -f graphify-out/.needs_update 2>/dev/null || true +``` + +Tell the user (omit the obsidian line unless --obsidian was given): +``` +Graph complete. Outputs in PATH_TO_DIR/graphify-out/ + + graph.html - interactive graph, open in browser + GRAPH_REPORT.md - audit report + graph.json - raw graph data + obsidian/ - Obsidian vault (only if --obsidian was given) +``` + +Replace PATH_TO_DIR with the actual absolute path of the directory that was processed. + +Then paste these sections from GRAPH_REPORT.md directly into the chat: +- God Nodes +- Surprising Connections +- Suggested Questions + +Do NOT paste the full report - just those three sections. Keep it concise. + +Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask: + +> "The most interesting question this graph can answer: **[question]**. Want me to trace it?" + +If the user says yes, run `/graphify query "[question]"` on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report. + +The graph is the map. Your job after the pipeline is to be the guide. + +--- + +## For --update (incremental re-extraction) + +Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time. + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.detect import detect_incremental, save_manifest +from pathlib import Path + +result = detect_incremental(Path('INPUT_PATH')) +new_total = result.get('new_total', 0) +print(json.dumps(result, indent=2)) +Path('.graphify_incremental.json').write_text(json.dumps(result)) +if new_total == 0: + print('No files changed since last run. Nothing to update.') + raise SystemExit(0) +print(f'{new_total} new/changed file(s) to re-extract.') +" +``` + +If new files exist, first check whether all changed files are code files: + +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path + +result = json.loads(open('.graphify_incremental.json').read()) if Path('.graphify_incremental.json').exists() else {} +code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts'} +new_files = result.get('new_files', {}) +all_changed = [f for files in new_files.values() for f in files] +code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed) +print('code_only:', code_only) +" +``` + +If `code_only` is True: print `[graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed)`, run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8. + +If `code_only` is False (any changed file is a doc/paper/image): run the full Steps 3A–3C pipeline as normal. + +Then: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load existing graph +existing_data = json.loads(Path('graphify-out/graph.json').read_text()) +G_existing = json_graph.node_link_graph(existing_data, edges='links') + +# Load new extraction +new_extraction = json.loads(Path('.graphify_extract.json').read_text()) +G_new = build_from_json(new_extraction) + +# Merge: new nodes/edges into existing graph +G_existing.update(G_new) +print(f'Merged: {G_existing.number_of_nodes()} nodes, {G_existing.number_of_edges()} edges') +" +``` + +Then run Steps 4–8 on the merged graph as normal. + +After Step 4, show the graph diff: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.analyze import graph_diff +from graphify.build import build_from_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load old graph (before update) from backup written before merge +old_data = json.loads(Path('.graphify_old.json').read_text()) if Path('.graphify_old.json').exists() else None +new_extract = json.loads(Path('.graphify_extract.json').read_text()) +G_new = build_from_json(new_extract) + +if old_data: + G_old = json_graph.node_link_graph(old_data, edges='links') + diff = graph_diff(G_old, G_new) + print(diff['summary']) + if diff['new_nodes']: + print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5])) + if diff['new_edges']: + print('New edges:', len(diff['new_edges'])) +" +``` + +Before the merge step, save the old graph: `cp graphify-out/graph.json .graphify_old.json` +Clean up after: `rm -f .graphify_old.json` + +--- + +## For --cluster-only + +Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections +from graphify.report import generate +from graphify.export import to_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +detection = {'total_files': 0, 'total_words': 99999, 'needs_graph': True, 'warning': None, + 'files': {'code': [], 'document': [], 'paper': []}} +tokens = {'input': 0, 'output': 0} + +communities = cluster(G) +cohesion = score_all(G, communities) +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} + +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, '.') +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +to_json(G, communities, 'graphify-out/graph.json') + +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, +} +Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2)) +print(f'Re-clustered: {len(communities)} communities') +" +``` + +Then run Steps 5–9 as normal (label communities, generate viz, benchmark, clean up, report). + +--- + +## For /graphify query + +Two traversal modes - choose based on the question: + +| Mode | Flag | Best for | +|------|------|----------| +| BFS (default) | _(none)_ | "What is X connected to?" - broad context, nearest neighbors first | +| DFS | `--dfs` | "How does X reach Y?" - trace a specific chain or dependency path | + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +Load `graphify-out/graph.json`, then: + +1. Find the 1-3 nodes whose label best matches key terms in the question. +2. Run the appropriate traversal from each starting node. +3. Read the subgraph - node labels, edge relations, confidence tags, source locations. +4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact. +5. If the graph lacks enough information, say so - do not hallucinate edges. + +```bash +$(cat .graphify_python) -c " +import sys, json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +question = 'QUESTION' +mode = 'MODE' # 'bfs' or 'dfs' +terms = [t.lower() for t in question.split() if len(t) > 3] + +# Find best-matching start nodes +scored = [] +for nid, ndata in G.nodes(data=True): + label = ndata.get('label', '').lower() + score = sum(1 for t in terms if t in label) + if score > 0: + scored.append((score, nid)) +scored.sort(reverse=True) +start_nodes = [nid for _, nid in scored[:3]] + +if not start_nodes: + print('No matching nodes found for query terms:', terms) + sys.exit(0) + +subgraph_nodes = set() +subgraph_edges = [] + +if mode == 'dfs': + # DFS: follow one path as deep as possible before backtracking. + # Depth-limited to 6 to avoid traversing the whole graph. + visited = set() + stack = [(n, 0) for n in reversed(start_nodes)] + while stack: + node, depth = stack.pop() + if node in visited or depth > 6: + continue + visited.add(node) + subgraph_nodes.add(node) + for neighbor in G.neighbors(node): + if neighbor not in visited: + stack.append((neighbor, depth + 1)) + subgraph_edges.append((node, neighbor)) +else: + # BFS: explore all neighbors layer by layer up to depth 3. + frontier = set(start_nodes) + subgraph_nodes = set(start_nodes) + for _ in range(3): + next_frontier = set() + for n in frontier: + for neighbor in G.neighbors(n): + if neighbor not in subgraph_nodes: + next_frontier.add(neighbor) + subgraph_edges.append((n, neighbor)) + subgraph_nodes.update(next_frontier) + frontier = next_frontier + +# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token) +token_budget = BUDGET # default 2000 +char_budget = token_budget * 4 + +# Score each node by term overlap for ranked output +def relevance(nid): + label = G.nodes[nid].get('label', '').lower() + return sum(1 for t in terms if t in label) + +ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True) + +lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes'] +for nid in ranked_nodes: + d = G.nodes[nid] + lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]') +for u, v in subgraph_edges: + if u in subgraph_nodes and v in subgraph_nodes: + d = G.edges[u, v] + lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}') + +output = '\n'.join(lines) +if len(output) > char_budget: + output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)' +print(output) +" +``` + +Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`, and `BUDGET` with the token budget (default `2000`, or whatever `--budget N` specifies). Then answer based on the subgraph output above. + +After writing the answer, save it back into the graph so it improves future queries: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='QUESTION', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='query', + source_nodes=SOURCE_NODES, # list of node labels cited, or [] +) +print('Query result saved to graphify-out/memory/') +" +``` + +Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph. + +--- + +## For /graphify path + +Find the shortest path between two named concepts in the graph. + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +```bash +$(cat .graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +a_term = 'NODE_A' +b_term = 'NODE_B' + +def find_node(term): + term = term.lower() + scored = sorted( + [(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True + ) + return scored[0][1] if scored and scored[0][0] > 0 else None + +src = find_node(a_term) +tgt = find_node(b_term) + +if not src or not tgt: + print(f'Could not find nodes matching: {a_term!r} or {b_term!r}') + sys.exit(0) + +try: + path = nx.shortest_path(G, src, tgt) + print(f'Shortest path ({len(path)-1} hops):') + for i, nid in enumerate(path): + label = G.nodes[nid].get('label', nid) + if i < len(path) - 1: + edge = G.edges[nid, path[i+1]] + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + print(f' {label} --{rel}--> [{conf}]') + else: + print(f' {label}') +except nx.NetworkXNoPath: + print(f'No path found between {a_term!r} and {b_term!r}') +except nx.NodeNotFound as e: + print(f'Node not found: {e}') +" +``` + +Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant. + +After writing the explanation, save it back: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='Path from NODE_A to NODE_B', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='path_query', + source_nodes=PATH_NODES, # list of node labels on the path +) +print('Path result saved to graphify-out/memory/') +" +``` + +--- + +## For /graphify explain + +Give a plain-language explanation of a single node - everything connected to it. + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +```bash +$(cat .graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +term = 'NODE_NAME' +term_lower = term.lower() + +# Find best matching node +scored = sorted( + [(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True +) +if not scored or scored[0][0] == 0: + print(f'No node matching {term!r}') + sys.exit(0) + +nid = scored[0][1] +data_n = G.nodes[nid] +print(f'NODE: {data_n.get(\"label\", nid)}') +print(f' source: {data_n.get(\"source_file\",\"unknown\")}') +print(f' type: {data_n.get(\"file_type\",\"unknown\")}') +print(f' degree: {G.degree(nid)}') +print() +print('CONNECTIONS:') +for neighbor in G.neighbors(nid): + edge = G.edges[nid, neighbor] + nlabel = G.nodes[neighbor].get('label', neighbor) + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + src_file = G.nodes[neighbor].get('source_file', '') + print(f' --{rel}--> {nlabel} [{conf}] ({src_file})') +" +``` + +Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations. + +After writing the explanation, save it back: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='Explain NODE_NAME', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='explain', + source_nodes=['NODE_NAME'], +) +print('Explanation saved to graphify-out/memory/') +" +``` + +--- + +## For /graphify add + +Fetch a URL and add it to the corpus, then update the graph. + +```bash +$(cat .graphify_python) -c " +import sys +from graphify.ingest import ingest +from pathlib import Path + +try: + out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR') + print(f'Saved to {out}') +except ValueError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +except RuntimeError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +" +``` + +Replace `URL` with the actual URL, `AUTHOR` with the user's name if provided, `CONTRIBUTOR` likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the `--update` pipeline on `./raw` to merge the new file into the existing graph. + +Supported URL types (auto-detected): +- Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author +- arXiv → abstract + metadata saved as `.md` +- PDF → downloaded as `.pdf` +- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Any webpage → converted to markdown via html2text + +--- + +## For --watch + +Start a background watcher that monitors a folder and auto-updates the graph when files change. + +```bash +python3 -m graphify.watch INPUT_PATH --debounce 3 +``` + +Replace INPUT_PATH with the folder to watch. Behavior depends on what changed: + +- **Code files only (.py, .ts, .go, etc.):** re-runs AST extraction + rebuild + cluster immediately, no LLM needed. `graph.json` and `GRAPH_REPORT.md` are updated automatically. +- **Docs, papers, or images:** writes a `graphify-out/needs_update` flag and prints a notification to run `/graphify --update` (LLM semantic re-extraction required). + +Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file. + +Press Ctrl+C to stop. + +For agentic workflows: run `--watch` in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual `/graphify --update` after those waves. + +--- + +## For git commit hook + +Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor. + +```bash +graphify hook install # install +graphify hook uninstall # remove +graphify hook status # check +``` + +After every `git commit`, the hook detects which code files changed (via `git diff HEAD~1`), re-runs AST extraction on those files, and rebuilds `graph.json` and `GRAPH_REPORT.md`. Doc/image changes are ignored by the hook - run `/graphify --update` manually for those. + +If a post-commit hook already exists, graphify appends to it rather than replacing it. + +--- + +## For native CLAUDE.md integration + +Run once per project to make graphify always-on in Claude Code sessions: + +```bash +graphify claude install +``` + +This writes a `## graphify` section to the local `CLAUDE.md` that instructs Claude to check the graph before answering codebase questions and rebuild it after code changes. No manual `/graphify` needed in future sessions. + +```bash +graphify claude uninstall # remove the section +``` + +--- + +## Honesty Rules + +- Never invent an edge. If unsure, use AMBIGUOUS. +- Never skip the corpus check warning. +- Always show token cost in the report. +- Never hide cohesion scores behind symbols - show the raw number. +- Never run HTML viz on a graph with more than 5,000 nodes without warning the user. diff --git a/graphify/skill-opencode.md b/graphify/skill-opencode.md new file mode 100644 index 00000000..62941389 --- /dev/null +++ b/graphify/skill-opencode.md @@ -0,0 +1,1216 @@ +--- +name: graphify +description: any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report +trigger: /graphify +--- + +# /graphify + +Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md. + +## Usage + +``` +/graphify # full pipeline on current directory → Obsidian vault +/graphify # full pipeline on specific path +/graphify --mode deep # thorough extraction, richer INFERRED edges +/graphify --update # incremental - re-extract only new/changed files +/graphify --cluster-only # rerun clustering on existing graph +/graphify --no-viz # skip visualization, just report + JSON +/graphify --html # (HTML is generated by default - this flag is a no-op) +/graphify --svg # also export graph.svg (embeds in Notion, GitHub) +/graphify --graphml # export graph.graphml (Gephi, yEd) +/graphify --neo4j # generate graphify-out/cypher.txt for Neo4j +/graphify --neo4j-push bolt://localhost:7687 # push directly to Neo4j +/graphify --mcp # start MCP stdio server for agent access +/graphify --watch # watch folder, auto-rebuild on code changes (no LLM needed) +/graphify add # fetch URL, save to ./raw, update graph +/graphify add --author "Name" # tag who wrote it +/graphify add --contributor "Name" # tag who added it to the corpus +/graphify query "" # BFS traversal - broad context +/graphify query "" --dfs # DFS - trace a specific path +/graphify query "" --budget 1500 # cap answer at N tokens +/graphify path "AuthModule" "Database" # shortest path between two concepts +/graphify explain "SwinTransformer" # plain-language explanation of a node +``` + +## What graphify is for + +graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. + +Three things it does that Claude alone cannot: +1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. +2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. +3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. + +Use it for: +- A codebase you're new to (understand architecture before touching anything) +- A reading list (papers + tweets + notes → one navigable graph) +- A research corpus (citation graph + concept graph in one) +- Your personal /raw folder (drop everything in, let it grow, query it) + +## What You Must Do When Invoked + +If no path was given, use `.` (current directory). Do not ask the user for a path. + +Follow these steps in order. Do not skip steps. + +### Step 1 - Ensure graphify is installed + +```bash +# Detect the correct Python interpreter (handles pipx, venv, system installs) +GRAPHIFY_BIN=$(which graphify 2>/dev/null) +if [ -n "$GRAPHIFY_BIN" ]; then + PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!') +else + PYTHON="python3" +fi +$PYTHON -c "import graphify" 2>/dev/null || pip install graphifyy -q --break-system-packages 2>&1 | tail -3 +# Write interpreter path for all subsequent steps +$PYTHON -c "import sys; open('.graphify_python', 'w').write(sys.executable)" +``` + +If the import succeeds, print nothing and move straight to Step 2. + +**In every subsequent bash block, replace `python3` with `$(cat .graphify_python)` to use the correct interpreter.** + +### Step 2 - Detect files + +```bash +$(cat .graphify_python) -c " +import json +from graphify.detect import detect +from pathlib import Path +result = detect(Path('INPUT_PATH')) +print(json.dumps(result)) +" > .graphify_detect.json +``` + +Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead: + +``` +Corpus: X files · ~Y words + code: N files (.py .ts .go ...) + docs: N files (.md .txt ...) + papers: N files (.pdf ...) + images: N files +``` + +Then act on it: +- If `total_files` is 0: stop with "No supported files found in [path]." +- If `skipped_sensitive` is non-empty: mention file count skipped, not the file names. +- If `total_words` > 2,000,000 OR `total_files` > 200: show the warning and the top 5 subdirectories by file count, then ask which subfolder to run on. Wait for the user's answer before proceeding. +- Otherwise: proceed directly to Step 3 - no need to ask anything. + +### Step 3 - Extract entities and relationships + +**Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. + +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). + +**Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** + +Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers. + +#### Part A - Structural extraction for code files + +For any code files detected, run AST extraction in parallel with Part B subagents: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.extract import collect_files, extract +from pathlib import Path +import json + +code_files = [] +detect = json.loads(Path('.graphify_detect.json').read_text()) +for f in detect.get('files', {}).get('code', []): + code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)]) + +if code_files: + result = extract(code_files) + Path('.graphify_ast.json').write_text(json.dumps(result, indent=2)) + print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges') +else: + Path('.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0})) + print('No code files - skipping AST extraction') +" +``` + +#### Part B - Semantic extraction (parallel subagents) + +**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do. + +**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.** + +Before dispatching subagents, print a timing estimate: +- Load `total_words` and file counts from `.graphify_detect.json` +- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25) +- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit)) +- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys" + +**Step B0 - Check extraction cache first** + +Before dispatching any subagents, check which files already have cached extraction results: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.cache import check_semantic_cache +from pathlib import Path + +detect = json.loads(Path('.graphify_detect.json').read_text()) +all_files = [f for files in detect['files'].values() for f in files] + +cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files) + +if cached_nodes or cached_edges or cached_hyperedges: + Path('.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges})) +Path('.graphify_uncached.txt').write_text('\n'.join(uncached)) +print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction') +" +``` + +Only dispatch subagents for files listed in `.graphify_uncached.txt`. If all files are cached, skip to Part C directly. + +**Step B1 - Split into chunks** + +Load files from `.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context). + +**Step B2 - Dispatch ALL subagents in a single message (OpenCode)** + +> **OpenCode platform:** Uses `@mention` dispatch instead of the Agent tool. All mentions in a single message run in parallel. + +Dispatch one `@mention` per chunk — ALL in the same response: + +``` +@agent Chunk CHUNK_NUM of TOTAL_CHUNKS: [extraction prompt below with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE substituted] + +@agent Chunk 2 of TOTAL_CHUNKS: [next chunk] +``` + +Wait for all agents to return. Parse each response as JSON. Accumulate nodes/edges/hyperedges across all results and write to `.graphify_semantic_new.json`. + +The extraction prompt each agent receives (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE): + +``` +You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment. +Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble. + +Files (chunk CHUNK_NUM of TOTAL_CHUNKS): +FILE_LIST + +Rules: +- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2") +- INFERRED: reasonable inference (shared data structure, implied dependency) +- AMBIGUOUS: uncertain - flag for review, do not omit + +Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns). + Do not re-extract imports - AST already has those. +Doc/paper files: extract named concepts, entities, citations. Also extract rationale — sections that explain WHY a decision was made, trade-offs chosen, or design intent. These become nodes with `rationale_for` edges pointing to the concept they explain. +Image files: use vision to understand what the image IS - do not just OCR. + UI screenshot: layout patterns, design decisions, key elements, purpose. + Chart: metric, trend/insight, data source. + Tweet/post: claim as node, author, concepts mentioned. + Diagram: components and connections. + Research figure: what it demonstrates, method, result. + Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS. + +DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps, + shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting. + +Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples: +- Two functions that both validate user input but never call each other +- A class in code and a concept in a paper that describe the same algorithm +- Two error types that handle the same failure mode differently +Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things. + +Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples: +- All classes that implement a common protocol or interface +- All functions in an authentication flow (even if they don't all call each other) +- All concepts from a paper section that form one coherent idea +Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk. + +If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author, + contributor onto every node from that file. + +confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default: +- EXTRACTED edges: confidence_score = 1.0 always +- INFERRED edges: reason about each edge individually. + Direct structural evidence (shared data structure, clear dependency): 0.8-0.9. + Reasonable inference with some uncertainty: 0.6-0.7. + Weak or speculative: 0.4-0.5. Most edges should be 0.6-0.9, not 0.5. +- AMBIGUOUS edges: 0.1-0.3 + +Output exactly this JSON (no other text): +{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"relative/path","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"relative/path"}],"input_tokens":0,"output_tokens":0} +``` + +**Step B3 - Collect, cache, and merge** + +Wait for all subagents. For each result: +- If a subagent returned valid JSON with `nodes` and `edges`, include it and save each file's nodes/edges to the cache +- If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort + +If more than half the chunks failed, stop and tell the user. + +Save new results to cache: +```bash +$(cat .graphify_python) -c " +import json +from graphify.cache import save_semantic_cache +from pathlib import Path + +new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', [])) +print(f'Cached {saved} files') +" +``` + +Merge cached + new results into `.graphify_semantic.json`: +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path + +cached = json.loads(Path('.graphify_cached.json').read_text()) if Path('.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} + +all_nodes = cached['nodes'] + new.get('nodes', []) +all_edges = cached['edges'] + new.get('edges', []) +all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', []) +seen = set() +deduped = [] +for n in all_nodes: + if n['id'] not in seen: + seen.add(n['id']) + deduped.append(n) + +merged = { + 'nodes': deduped, + 'edges': all_edges, + 'hyperedges': all_hyperedges, + 'input_tokens': new.get('input_tokens', 0), + 'output_tokens': new.get('output_tokens', 0), +} +Path('.graphify_semantic.json').write_text(json.dumps(merged, indent=2)) +print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)') +" +``` +Clean up temp files: `rm -f .graphify_cached.json .graphify_uncached.txt .graphify_semantic_new.json` + +#### Part C - Merge AST + semantic into final extraction + +```bash +$(cat .graphify_python) -c " +import sys, json +from pathlib import Path + +ast = json.loads(Path('.graphify_ast.json').read_text()) +sem = json.loads(Path('.graphify_semantic.json').read_text()) + +# Merge: AST nodes first, semantic nodes deduplicated by id +seen = {n['id'] for n in ast['nodes']} +merged_nodes = list(ast['nodes']) +for n in sem['nodes']: + if n['id'] not in seen: + merged_nodes.append(n) + seen.add(n['id']) + +merged_edges = ast['edges'] + sem['edges'] +merged_hyperedges = sem.get('hyperedges', []) +merged = { + 'nodes': merged_nodes, + 'edges': merged_edges, + 'hyperedges': merged_hyperedges, + 'input_tokens': sem.get('input_tokens', 0), + 'output_tokens': sem.get('output_tokens', 0), +} +Path('.graphify_extract.json').write_text(json.dumps(merged, indent=2)) +total = len(merged_nodes) +edges = len(merged_edges) +print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)') +" +``` + +### Step 4 - Build graph, cluster, analyze, generate outputs + +```bash +mkdir -p graphify-out +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from graphify.export import to_json +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +detection = json.loads(Path('.graphify_detect.json').read_text()) + +G = build_from_json(extraction) +communities = cluster(G) +cohesion = score_all(G, communities) +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} +# Placeholder questions - regenerated with real labels in Step 5 +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +to_json(G, communities, 'graphify-out/graph.json') + +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, + 'questions': questions, +} +Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2)) +if G.number_of_nodes() == 0: + print('ERROR: Graph is empty - extraction produced no nodes.') + print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.') + raise SystemExit(1) +print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities') +" +``` + +If this step prints `ERROR: Graph is empty`, stop and tell the user what happened - do not proceed to labeling or visualization. + +Replace INPUT_PATH with the actual path. + +### Step 5 - Label communities + +Read `.graphify_analysis.json`. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading"). + +Then regenerate the report and save the labels for the visualizer: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +detection = json.loads(Path('.graphify_detect.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} + +# LABELS - replace these with the names you chose above +labels = LABELS_DICT + +# Regenerate questions with real community labels (labels affect question phrasing) +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +Path('.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()})) +print('Report updated with community labels') +" +``` + +Replace `LABELS_DICT` with the actual dict you constructed (e.g. `{0: "Attention Mechanism", 1: "Training Pipeline"}`). +Replace INPUT_PATH with the actual path. + +### Step 6 - Generate Obsidian vault (opt-in) + HTML + +**Generate HTML always** (unless `--no-viz`). **Obsidian vault only if `--obsidian` was explicitly given** — skip it otherwise, it generates one file per node. + +If `--obsidian` was given: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_obsidian, to_canvas +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +n = to_obsidian(G, communities, 'graphify-out/obsidian', community_labels=labels or None, cohesion=cohesion) +print(f'Obsidian vault: {n} notes in graphify-out/obsidian/') + +to_canvas(G, communities, 'graphify-out/obsidian/graph.canvas', community_labels=labels or None) +print('Canvas: graphify-out/obsidian/graph.canvas - open in Obsidian for structured community layout') +print() +print('Open graphify-out/obsidian/ as a vault in Obsidian.') +print(' Graph view - nodes colored by community (set automatically)') +print(' graph.canvas - structured layout with communities as groups') +print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries') +" +``` + +Generate the HTML graph (always, unless `--no-viz`): + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_html +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +if G.number_of_nodes() > 5000: + print(f'Graph has {G.number_of_nodes()} nodes - too large for HTML viz. Use Obsidian vault instead.') +else: + to_html(G, communities, 'graphify-out/graph.html', community_labels=labels or None) + print('graph.html written - open in any browser, no server needed') +" +``` + +### Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag) + +**If `--neo4j`** - generate a Cypher file for manual import: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_cypher +from pathlib import Path + +G = build_from_json(json.loads(Path('.graphify_extract.json').read_text())) +to_cypher(G, 'graphify-out/cypher.txt') +print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt') +" +``` + +**If `--neo4j-push `** - push directly to a running Neo4j instance. Ask the user for credentials if not provided: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster +from graphify.export import push_to_neo4j +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} + +result = push_to_neo4j(G, uri='NEO4J_URI', user='NEO4J_USER', password='NEO4J_PASSWORD', communities=communities) +print(f'Pushed to Neo4j: {result[\"nodes\"]} nodes, {result[\"edges\"]} edges') +" +``` + +Replace `NEO4J_URI`, `NEO4J_USER`, `NEO4J_PASSWORD` with actual values. Default URI is `bolt://localhost:7687`, default user is `neo4j`. Uses MERGE - safe to re-run without creating duplicates. + +### Step 7b - SVG export (only if --svg flag) + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_svg +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) +labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {} + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} +labels = {int(k): v for k, v in labels_raw.items()} + +to_svg(G, communities, 'graphify-out/graph.svg', community_labels=labels or None) +print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs') +" +``` + +### Step 7c - GraphML export (only if --graphml flag) + +```bash +$(cat .graphify_python) -c " +import json +from graphify.build import build_from_json +from graphify.export import to_graphml +from pathlib import Path + +extraction = json.loads(Path('.graphify_extract.json').read_text()) +analysis = json.loads(Path('.graphify_analysis.json').read_text()) + +G = build_from_json(extraction) +communities = {int(k): v for k, v in analysis['communities'].items()} + +to_graphml(G, communities, 'graphify-out/graph.graphml') +print('graph.graphml written - open in Gephi, yEd, or any GraphML tool') +" +``` + +### Step 7d - MCP server (only if --mcp flag) + +```bash +python3 -m graphify.serve graphify-out/graph.json +``` + +This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `get_neighbors`, `get_community`, `god_nodes`, `graph_stats`, `shortest_path`. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live. + +To configure in Claude Desktop, add to `claude_desktop_config.json`: +```json +{ + "mcpServers": { + "graphify": { + "command": "python3", + "args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"] + } + } +} +``` + +### Step 8 - Token reduction benchmark (only if total_words > 5000) + +If `total_words` from `.graphify_detect.json` is greater than 5,000, run: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.benchmark import run_benchmark, print_benchmark +from pathlib import Path + +detection = json.loads(Path('.graphify_detect.json').read_text()) +result = run_benchmark('graphify-out/graph.json', corpus_words=detection['total_words']) +print_benchmark(result) +" +``` + +Print the output directly in chat. If `total_words <= 5000`, skip silently - the graph value is structural clarity, not token compression, for small corpora. + +--- + +### Step 9 - Save manifest, update cost tracker, clean up, and report + +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path +from datetime import datetime, timezone +from graphify.detect import save_manifest + +# Save manifest for --update +detect = json.loads(Path('.graphify_detect.json').read_text()) +save_manifest(detect['files']) + +# Update cumulative cost tracker +extract = json.loads(Path('.graphify_extract.json').read_text()) +input_tok = extract.get('input_tokens', 0) +output_tok = extract.get('output_tokens', 0) + +cost_path = Path('graphify-out/cost.json') +if cost_path.exists(): + cost = json.loads(cost_path.read_text()) +else: + cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0} + +cost['runs'].append({ + 'date': datetime.now(timezone.utc).isoformat(), + 'input_tokens': input_tok, + 'output_tokens': output_tok, + 'files': detect.get('total_files', 0), +}) +cost['total_input_tokens'] += input_tok +cost['total_output_tokens'] += output_tok +cost_path.write_text(json.dumps(cost, indent=2)) + +print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens') +print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)') +" +rm -f .graphify_detect.json .graphify_extract.json .graphify_ast.json .graphify_semantic.json .graphify_analysis.json .graphify_labels.json .graphify_python +rm -f graphify-out/.needs_update 2>/dev/null || true +``` + +Tell the user (omit the obsidian line unless --obsidian was given): +``` +Graph complete. Outputs in PATH_TO_DIR/graphify-out/ + + graph.html - interactive graph, open in browser + GRAPH_REPORT.md - audit report + graph.json - raw graph data + obsidian/ - Obsidian vault (only if --obsidian was given) +``` + +Replace PATH_TO_DIR with the actual absolute path of the directory that was processed. + +Then paste these sections from GRAPH_REPORT.md directly into the chat: +- God Nodes +- Surprising Connections +- Suggested Questions + +Do NOT paste the full report - just those three sections. Keep it concise. + +Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask: + +> "The most interesting question this graph can answer: **[question]**. Want me to trace it?" + +If the user says yes, run `/graphify query "[question]"` on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report. + +The graph is the map. Your job after the pipeline is to be the guide. + +--- + +## For --update (incremental re-extraction) + +Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time. + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.detect import detect_incremental, save_manifest +from pathlib import Path + +result = detect_incremental(Path('INPUT_PATH')) +new_total = result.get('new_total', 0) +print(json.dumps(result, indent=2)) +Path('.graphify_incremental.json').write_text(json.dumps(result)) +if new_total == 0: + print('No files changed since last run. Nothing to update.') + raise SystemExit(0) +print(f'{new_total} new/changed file(s) to re-extract.') +" +``` + +If new files exist, first check whether all changed files are code files: + +```bash +$(cat .graphify_python) -c " +import json +from pathlib import Path + +result = json.loads(open('.graphify_incremental.json').read()) if Path('.graphify_incremental.json').exists() else {} +code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts'} +new_files = result.get('new_files', {}) +all_changed = [f for files in new_files.values() for f in files] +code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed) +print('code_only:', code_only) +" +``` + +If `code_only` is True: print `[graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed)`, run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8. + +If `code_only` is False (any changed file is a doc/paper/image): run the full Steps 3A–3C pipeline as normal. + +Then: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.export import to_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load existing graph +existing_data = json.loads(Path('graphify-out/graph.json').read_text()) +G_existing = json_graph.node_link_graph(existing_data, edges='links') + +# Load new extraction +new_extraction = json.loads(Path('.graphify_extract.json').read_text()) +G_new = build_from_json(new_extraction) + +# Merge: new nodes/edges into existing graph +G_existing.update(G_new) +print(f'Merged: {G_existing.number_of_nodes()} nodes, {G_existing.number_of_edges()} edges') +" +``` + +Then run Steps 4–8 on the merged graph as normal. + +After Step 4, show the graph diff: + +```bash +$(cat .graphify_python) -c " +import json +from graphify.analyze import graph_diff +from graphify.build import build_from_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load old graph (before update) from backup written before merge +old_data = json.loads(Path('.graphify_old.json').read_text()) if Path('.graphify_old.json').exists() else None +new_extract = json.loads(Path('.graphify_extract.json').read_text()) +G_new = build_from_json(new_extract) + +if old_data: + G_old = json_graph.node_link_graph(old_data, edges='links') + diff = graph_diff(G_old, G_new) + print(diff['summary']) + if diff['new_nodes']: + print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5])) + if diff['new_edges']: + print('New edges:', len(diff['new_edges'])) +" +``` + +Before the merge step, save the old graph: `cp graphify-out/graph.json .graphify_old.json` +Clean up after: `rm -f .graphify_old.json` + +--- + +## For --cluster-only + +Skip Steps 1–3. Load the existing graph from `graphify-out/graph.json` and re-run clustering: + +```bash +$(cat .graphify_python) -c " +import sys, json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections +from graphify.report import generate +from graphify.export import to_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +detection = {'total_files': 0, 'total_words': 99999, 'needs_graph': True, 'warning': None, + 'files': {'code': [], 'document': [], 'paper': []}} +tokens = {'input': 0, 'output': 0} + +communities = cluster(G) +cohesion = score_all(G, communities) +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} + +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, '.') +Path('graphify-out/GRAPH_REPORT.md').write_text(report) +to_json(G, communities, 'graphify-out/graph.json') + +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, +} +Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2)) +print(f'Re-clustered: {len(communities)} communities') +" +``` + +Then run Steps 5–9 as normal (label communities, generate viz, benchmark, clean up, report). + +--- + +## For /graphify query + +Two traversal modes - choose based on the question: + +| Mode | Flag | Best for | +|------|------|----------| +| BFS (default) | _(none)_ | "What is X connected to?" - broad context, nearest neighbors first | +| DFS | `--dfs` | "How does X reach Y?" - trace a specific chain or dependency path | + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +Load `graphify-out/graph.json`, then: + +1. Find the 1-3 nodes whose label best matches key terms in the question. +2. Run the appropriate traversal from each starting node. +3. Read the subgraph - node labels, edge relations, confidence tags, source locations. +4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact. +5. If the graph lacks enough information, say so - do not hallucinate edges. + +```bash +$(cat .graphify_python) -c " +import sys, json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +question = 'QUESTION' +mode = 'MODE' # 'bfs' or 'dfs' +terms = [t.lower() for t in question.split() if len(t) > 3] + +# Find best-matching start nodes +scored = [] +for nid, ndata in G.nodes(data=True): + label = ndata.get('label', '').lower() + score = sum(1 for t in terms if t in label) + if score > 0: + scored.append((score, nid)) +scored.sort(reverse=True) +start_nodes = [nid for _, nid in scored[:3]] + +if not start_nodes: + print('No matching nodes found for query terms:', terms) + sys.exit(0) + +subgraph_nodes = set() +subgraph_edges = [] + +if mode == 'dfs': + # DFS: follow one path as deep as possible before backtracking. + # Depth-limited to 6 to avoid traversing the whole graph. + visited = set() + stack = [(n, 0) for n in reversed(start_nodes)] + while stack: + node, depth = stack.pop() + if node in visited or depth > 6: + continue + visited.add(node) + subgraph_nodes.add(node) + for neighbor in G.neighbors(node): + if neighbor not in visited: + stack.append((neighbor, depth + 1)) + subgraph_edges.append((node, neighbor)) +else: + # BFS: explore all neighbors layer by layer up to depth 3. + frontier = set(start_nodes) + subgraph_nodes = set(start_nodes) + for _ in range(3): + next_frontier = set() + for n in frontier: + for neighbor in G.neighbors(n): + if neighbor not in subgraph_nodes: + next_frontier.add(neighbor) + subgraph_edges.append((n, neighbor)) + subgraph_nodes.update(next_frontier) + frontier = next_frontier + +# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token) +token_budget = BUDGET # default 2000 +char_budget = token_budget * 4 + +# Score each node by term overlap for ranked output +def relevance(nid): + label = G.nodes[nid].get('label', '').lower() + return sum(1 for t in terms if t in label) + +ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True) + +lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes'] +for nid in ranked_nodes: + d = G.nodes[nid] + lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]') +for u, v in subgraph_edges: + if u in subgraph_nodes and v in subgraph_nodes: + d = G.edges[u, v] + lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}') + +output = '\n'.join(lines) +if len(output) > char_budget: + output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)' +print(output) +" +``` + +Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`, and `BUDGET` with the token budget (default `2000`, or whatever `--budget N` specifies). Then answer based on the subgraph output above. + +After writing the answer, save it back into the graph so it improves future queries: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='QUESTION', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='query', + source_nodes=SOURCE_NODES, # list of node labels cited, or [] +) +print('Query result saved to graphify-out/memory/') +" +``` + +Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph. + +--- + +## For /graphify path + +Find the shortest path between two named concepts in the graph. + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +```bash +$(cat .graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +a_term = 'NODE_A' +b_term = 'NODE_B' + +def find_node(term): + term = term.lower() + scored = sorted( + [(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True + ) + return scored[0][1] if scored and scored[0][0] > 0 else None + +src = find_node(a_term) +tgt = find_node(b_term) + +if not src or not tgt: + print(f'Could not find nodes matching: {a_term!r} or {b_term!r}') + sys.exit(0) + +try: + path = nx.shortest_path(G, src, tgt) + print(f'Shortest path ({len(path)-1} hops):') + for i, nid in enumerate(path): + label = G.nodes[nid].get('label', nid) + if i < len(path) - 1: + edge = G.edges[nid, path[i+1]] + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + print(f' {label} --{rel}--> [{conf}]') + else: + print(f' {label}') +except nx.NetworkXNoPath: + print(f'No path found between {a_term!r} and {b_term!r}') +except nx.NodeNotFound as e: + print(f'Node not found: {e}') +" +``` + +Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant. + +After writing the explanation, save it back: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='Path from NODE_A to NODE_B', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='path_query', + source_nodes=PATH_NODES, # list of node labels on the path +) +print('Path result saved to graphify-out/memory/') +" +``` + +--- + +## For /graphify explain + +Give a plain-language explanation of a single node - everything connected to it. + +First check the graph exists: +```bash +$(cat .graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +```bash +$(cat .graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +term = 'NODE_NAME' +term_lower = term.lower() + +# Find best matching node +scored = sorted( + [(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True +) +if not scored or scored[0][0] == 0: + print(f'No node matching {term!r}') + sys.exit(0) + +nid = scored[0][1] +data_n = G.nodes[nid] +print(f'NODE: {data_n.get(\"label\", nid)}') +print(f' source: {data_n.get(\"source_file\",\"unknown\")}') +print(f' type: {data_n.get(\"file_type\",\"unknown\")}') +print(f' degree: {G.degree(nid)}') +print() +print('CONNECTIONS:') +for neighbor in G.neighbors(nid): + edge = G.edges[nid, neighbor] + nlabel = G.nodes[neighbor].get('label', neighbor) + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + src_file = G.nodes[neighbor].get('source_file', '') + print(f' --{rel}--> {nlabel} [{conf}] ({src_file})') +" +``` + +Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations. + +After writing the explanation, save it back: + +```bash +$(cat .graphify_python) -c " +from graphify.ingest import save_query_result +from pathlib import Path +save_query_result( + question='Explain NODE_NAME', + answer='ANSWER', + memory_dir=Path('graphify-out/memory'), + query_type='explain', + source_nodes=['NODE_NAME'], +) +print('Explanation saved to graphify-out/memory/') +" +``` + +--- + +## For /graphify add + +Fetch a URL and add it to the corpus, then update the graph. + +```bash +$(cat .graphify_python) -c " +import sys +from graphify.ingest import ingest +from pathlib import Path + +try: + out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR') + print(f'Saved to {out}') +except ValueError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +except RuntimeError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +" +``` + +Replace `URL` with the actual URL, `AUTHOR` with the user's name if provided, `CONTRIBUTOR` likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the `--update` pipeline on `./raw` to merge the new file into the existing graph. + +Supported URL types (auto-detected): +- Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author +- arXiv → abstract + metadata saved as `.md` +- PDF → downloaded as `.pdf` +- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Any webpage → converted to markdown via html2text + +--- + +## For --watch + +Start a background watcher that monitors a folder and auto-updates the graph when files change. + +```bash +python3 -m graphify.watch INPUT_PATH --debounce 3 +``` + +Replace INPUT_PATH with the folder to watch. Behavior depends on what changed: + +- **Code files only (.py, .ts, .go, etc.):** re-runs AST extraction + rebuild + cluster immediately, no LLM needed. `graph.json` and `GRAPH_REPORT.md` are updated automatically. +- **Docs, papers, or images:** writes a `graphify-out/needs_update` flag and prints a notification to run `/graphify --update` (LLM semantic re-extraction required). + +Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file. + +Press Ctrl+C to stop. + +For agentic workflows: run `--watch` in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual `/graphify --update` after those waves. + +--- + +## For git commit hook + +Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor. + +```bash +graphify hook install # install +graphify hook uninstall # remove +graphify hook status # check +``` + +After every `git commit`, the hook detects which code files changed (via `git diff HEAD~1`), re-runs AST extraction on those files, and rebuilds `graph.json` and `GRAPH_REPORT.md`. Doc/image changes are ignored by the hook - run `/graphify --update` manually for those. + +If a post-commit hook already exists, graphify appends to it rather than replacing it. + +--- + +## For native CLAUDE.md integration + +Run once per project to make graphify always-on in Claude Code sessions: + +```bash +graphify claude install +``` + +This writes a `## graphify` section to the local `CLAUDE.md` that instructs Claude to check the graph before answering codebase questions and rebuild it after code changes. No manual `/graphify` needed in future sessions. + +```bash +graphify claude uninstall # remove the section +``` + +--- + +## Honesty Rules + +- Never invent an edge. If unsure, use AMBIGUOUS. +- Never skip the corpus check warning. +- Always show token cost in the report. +- Never hide cohesion scores behind symbols - show the raw number. +- Never run HTML viz on a graph with more than 5,000 nodes without warning the user. diff --git a/pyproject.toml b/pyproject.toml index b7759a9f..b24133c5 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -49,4 +49,4 @@ where = ["."] include = ["graphify*"] [tool.setuptools.package-data] -graphify = ["skill.md"] +graphify = ["skill.md", "skill-codex.md", "skill-opencode.md", "skill-claw.md"] diff --git a/tests/test_install.py b/tests/test_install.py new file mode 100644 index 00000000..5cee5904 --- /dev/null +++ b/tests/test_install.py @@ -0,0 +1,85 @@ +"""Tests for graphify install --platform routing.""" +from pathlib import Path +from unittest.mock import patch +import pytest + + +PLATFORMS = { + "claude": (".claude/skills/graphify/SKILL.md",), + "codex": (".agents/skills/graphify/SKILL.md",), + "opencode": (".config/opencode/skills/graphify/SKILL.md",), + "claw": (".claw/skills/graphify/SKILL.md",), +} + + +def _install(tmp_path, platform): + from graphify.__main__ import install + with patch("graphify.__main__.Path.home", return_value=tmp_path): + install(platform=platform) + + +def test_install_default_claude(tmp_path): + _install(tmp_path, "claude") + assert (tmp_path / ".claude" / "skills" / "graphify" / "SKILL.md").exists() + + +def test_install_codex(tmp_path): + _install(tmp_path, "codex") + assert (tmp_path / ".agents" / "skills" / "graphify" / "SKILL.md").exists() + + +def test_install_opencode(tmp_path): + _install(tmp_path, "opencode") + assert (tmp_path / ".config" / "opencode" / "skills" / "graphify" / "SKILL.md").exists() + + +def test_install_claw(tmp_path): + _install(tmp_path, "claw") + assert (tmp_path / ".claw" / "skills" / "graphify" / "SKILL.md").exists() + + +def test_install_unknown_platform_exits(tmp_path): + with pytest.raises(SystemExit): + _install(tmp_path, "unknown") + + +def test_codex_skill_contains_spawn_agent(): + """Codex skill file must reference spawn_agent.""" + import graphify + skill = (Path(graphify.__file__).parent / "skill-codex.md").read_text() + assert "spawn_agent" in skill + + +def test_opencode_skill_contains_mention(): + """OpenCode skill file must reference @mention.""" + import graphify + skill = (Path(graphify.__file__).parent / "skill-opencode.md").read_text() + assert "@mention" in skill + + +def test_claw_skill_is_sequential(): + """OpenClaw skill file must describe sequential extraction.""" + import graphify + skill = (Path(graphify.__file__).parent / "skill-claw.md").read_text() + assert "sequential" in skill.lower() + assert "spawn_agent" not in skill + assert "@mention" not in skill + + +def test_all_skill_files_exist_in_package(): + """All four platform skill files must be present in the installed package.""" + import graphify + pkg = Path(graphify.__file__).parent + for name in ("skill.md", "skill-codex.md", "skill-opencode.md", "skill-claw.md"): + assert (pkg / name).exists(), f"Missing: {name}" + + +def test_claude_install_registers_claude_md(tmp_path): + """Claude platform install writes CLAUDE.md; others do not.""" + _install(tmp_path, "claude") + assert (tmp_path / ".claude" / "CLAUDE.md").exists() + + +def test_codex_install_does_not_write_claude_md(tmp_path): + _install(tmp_path, "codex") + assert not (tmp_path / ".claude" / "CLAUDE.md").exists()