Restructures the rsl-siege-manager evaluation to match upstream's
worked/karpathy-repos/ convention before opening against safishamsi/graphify:
- Move evaluations/rsl-siege-manager/ -> worked/rsl-siege-manager/
- Flatten graphify-out-with-tests/ artifacts to the case directory root
(matches karpathy-repos layout: README.md, review.md, GRAPH_REPORT.md,
graph.html, graph.json, manifest.json at top level).
- Drop the codebase-only artifact set; keep only the tests-included run as
the more realistic default (most users won't pre-configure .graphifyignore).
- Rename runbook.md -> README.md (corpus description + reproduction steps).
- Rename results.md -> review.md (matches karpathy-repos), and reframe from
"do not adopt" verdict to neutral findings + suggested follow-ups.
- Drop evaluations/README.md fork-only index.
- Revert .gitignore evaluations/ exception block — no longer needed now that
artifacts live at worked/rsl-siege-manager/ (no graphify-out/ in path).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
style: replace all em dashes with hyphens
fix: explain hidden .graphify/ folder in skill output and README
fix: rename .graphify/ to graphify-out/ so output is visible by default
- Add GitHub Actions CI workflow (Python 3.10 and 3.12)
- Add CI badge to README
- Add ARCHITECTURE.md: pipeline overview, module table, schema, how to
add a language extractor, security summary
- Move eval reports from tests/ to worked/httpx/ and worked/mixed-corpus/
- Fix README: test count 163→212, language table (13 languages via
tree-sitter), extract.py description, worked examples links
benchmark: 8.8x token reduction on nanoGPT + minGPT + micrograd
- Run AST extraction on 29 Python files across 3 Karpathy repos
- 177 nodes, 246 edges, 17 communities (Leiden)
- 8.8x avg token reduction vs naive full-corpus context stuffing
- Notable: micrograd cleanly splits into engine/nn communities;
nanoGPT model vs training loop correctly separated
- Honest: stdlib import noise flagged, config isolates documented
benchmark: 71.5x token reduction on mixed corpus (code+papers+images)
Full run: nanoGPT+minGPT+micrograd + 5 research papers + 4 images
285 nodes, 340 edges, 53 communities
Average BFS query: 1,726 tokens vs 123,488 naive (71.5x)
Code-only (AST) sub-benchmark: 8.8x on 13k-word corpus
Christopher Beaulieu