Single-commit clean baseline after security scrub of niche-tells, project codenames, internal jargon, and contributor-email leaks. Contents: - 100 Rust crates (_primitives/_rust/) - 37 agent manifests (_manifests/) + generated specs (_generated/) - 67 user-invocable skills (skills/) - 33 hooks (hooks/) - Composition blocks (_blocks/) - Documentation (docs/, README.md) - TS adapter packages (_ts_packages/) - Assembler (_assembler/) - Roles (_roles/) - Templates (_templates/) - Forgejo CI (.forgejo/) Author: Denis Parfionovich <info@greendragon.info> License: see LICENSE.
1,012 B
1,012 B
MEMORY PROTOCOL
At start:
- Read
~/.claude/memory/MEMORY.md(or your index file) → find relevant project file - Read
memory/{project}.md→ constraints, stack, status, learnings - If ML / research work: also check your
wrong-paths.mdnotes (dead ends worth avoiding)
At end (if stage completed — feature/phase/milestone/audit/bug+fix/deploy/decision/blocker):
- Append to
memory/{project}.mdwith format:### Feature Name (YYYY-MM-DD) [E-grade] - Result: specific metrics (numbers, not "works well") - Decision: what was done - Benchmark: numbers vs baseline - Learnings: what was learned - Next: what's next - If dead end / wrong path → append to your
wrong-paths.md - If architectural decision → project's
DECISIONS.md - Session chatlog (if significant):
memory/chatlogs/{ml|projects}/YYYY-MM-DD-{topic}.md
Forbidden: transitioning without saving; writing "works" without metrics; leaving credentials only in conversation context.