lukaszraczylo 78bf0f1e1e Initial commit: ADAM self-improvement layer for Claude Code ...

- 8 friction signals via lightweight hook (correction, retry_loop, weak_agent,
  tool_error_loop, dead_end, edit_churn, build_loop, subagent_dispatch_pattern)
- Deterministic confidence rubric with cross-session evidence gate
- /reflect skill to dispatch the analyst subagent and walk the queue
- Skill overlap detection (prefer skill_edit over skill_new on collision)
- Solution synthesis from transcript context for new skill drafts
- Soft-delete trash, never hard rm
- 18 tests covering all signals

2026-05-10 02:32:13 +01:00

..

reflect.md

Initial commit: ADAM self-improvement layer for Claude Code

2026-05-10 02:32:13 +01:00