Add scope confinement rule to prevent cross-project task scanning
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.
This commit is contained in:
@@ -23,3 +23,9 @@
|
|||||||
- After writing a SPEC.md for a new task, **stop and wait for user approval** before implementing
|
- 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
|
- 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
|
- 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
|
||||||
|
|||||||
Reference in New Issue
Block a user