gitea
cc2e97bd43
The agent scanned tasks in invest-copilot while working on automaton framework, wasting time on unrelated work. Added a rule with concrete failure example limiting work to the current project's .automaton/tasks/ only.
1.8 KiB
1.8 KiB
.rules.md
Task-Driven Development
- All changes must go through a task in tasks/{name}/ with SPEC.md → phases → VERDICT.md
- Never edit files directly without a corresponding task
- Never create task directories manually (mkdir tasks/) — use the Orchestrator instead
VRAM-Aware Task Sizing
- Before creating or scoping a task, check ~/.automaton/config.md for VRAM limits
- Verify the task fits within max peak context (default: 12k tokens)
- If no config exists, default to 8k with 25% headroom
Changelog
- When a task reaches Resolution (VERDICT.md written), append an entry to CHANGELOG.md
- Use the format:
- description (#task-name)under the appropriate [unreleased] section
Self-Improvement
- Add one rule per observed failure mode with a concrete example
- Consolidate contradictions monthly. Remove stale rules.
- No rule without a real example of the problem it prevents
Session Discipline
- After writing a SPEC.md for a new task, stop and wait for user approval before implementing
- Do not implement a task in the same session it was created unless explicitly told to
- Past failure: agent created pre-commit-hook task, wrote SPEC.md, then immediately built and committed the hook without waiting — bypassing review 3 times in one session despite promises to follow the process
Scope Confinement
- Only work on tasks in the current project's
.automaton/tasks/directory - Never scan, read, or modify tasks in other projects on the system
- The
{project}in the Orchestrator prompt is the project root where the session started — do not broaden scope - Past failure: agent scanned tasks in
~/ai-env/projects/invest-copilot/while working on the automaton framework itself, wasting time on unrelated work across project boundaries