Methodology-aware configuration for AI agents. Read by any AI agent (Claude, Gemini, Copilot, etc.) at session start.
| File | Purpose |
|---|---|
|
Default mode, invariants, ring ceiling, priority weights, convergent budget |
|
Session coverage tracking — what was visited, what was skipped, what has MUSTs |
|
Meander debt — things found but not fixed, carried between sessions |
-
Read
methodology.a2mlat session start — know mode, invariants, ceiling -
Read
coverage.a2ml— know what was visited last time, what was skipped -
Read
debt.a2ml— know what’s outstanding from previous sessions -
At session end, update
coverage.a2mlanddebt.a2ml
-
AGENTIC.a2mlsays WHAT agents can do (permissions, gating) -
bot_directives/says HOW agents should work (methodology) -
bot_directives/says what the gitbot-fleet does (fleet-specific) -
CLAUDE.mdsays how Claude specifically should work (Claude-specific)