36 lines
1.2 KiB
Markdown
36 lines
1.2 KiB
Markdown
# Codex and Claude collaboration
|
|
|
|
## Operating model
|
|
|
|
One agent writes; the other reviews. Roles can rotate between tasks, but ownership cannot be ambiguous within a task.
|
|
|
|
## Handoff format
|
|
|
|
```markdown
|
|
Task: TASK-###
|
|
Role completed: implementer | reviewer
|
|
Commit/diff: <identifier>
|
|
Writable scope used: <paths>
|
|
Acceptance criteria status: <list>
|
|
Checks run: <commands and outcomes>
|
|
Open findings: <P0-P3 list>
|
|
Known limitations: <list>
|
|
Next owner/action: <one concrete action>
|
|
```
|
|
|
|
## Conflict handling
|
|
|
|
1. Product requirements and human decisions win.
|
|
2. `AGENTS.md` wins over agent-specific files.
|
|
3. Task acceptance criteria win over implementation preference.
|
|
4. Automated evidence wins over an unsupported assertion.
|
|
5. Security-sensitive ambiguity is escalated to the human owner.
|
|
|
|
## Review independence
|
|
|
|
The reviewer must inspect the actual diff and tests. Do not provide the implementer's reasoning as a substitute for evidence; it can anchor the reviewer and hide alternative failure modes.
|
|
|
|
## Serial development
|
|
|
|
Implementation is serial: one writer owns the working tree at a time, and both agents append completion and handoff records to `docs/development-log.md`. The current ownership map and delivery sequence are recorded in `docs/workstreams.md`.
|