Write down the steward's PR process and chip's advisory review - #33
Conversation
Hugo's rule from 2026-09-30: the steward no longer pushes to main. It opens a PR, waits for chip's review, answers or fixes every finding, runs its own QA, then merges. Kept in this file (AGENTS.md is a symlink to it) so the rule survives steward restarts. Also records that the chip review workflow is owned by mono and must not be edited here.
|
Important Review skippedBot user detected. To trigger a single review, invoke the ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Advanced Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![chip-peanut-bot[bot]](https://avatars.githubusercontent.com/in/2915219?s=60&v=4){kind=small}
There was a problem hiding this comment.
Chip review — no blocking findings — this is not an approval
No findings in the four-line process-documentation change.
Checked clean
- CLAUDE.md process wording, AGENTS.md symlink, and the mono-owned review workflow copy match the stated process.
- CI check fails on formatting of unchanged .github/workflows/chip-pr-review.yml; the failure is present outside this PR diff. Other completed checks passed.
Security review: did not run — this change has no security, privacy or money surface, so it was not asked. This review is one reviewer short.
Third opinion by claude-opus: 0 finding(s), marked with the model name. It answers only product truth, missing tests and the cross-repo contract, so treat its findings as advice.
Exact head: f47f6a1d8768 · Context: repo, mono · Took 3m (queued 2m)
This adds Hugo's 2026-09-30 process to
CLAUDE.md, under Shipping.AGENTS.mdis a symlink to that file, so it gets the same text.main; Konrad and Hugo still can. Each steward change goes branch → PR → chip review → steward QA → steward merges, with no human approval needed./chip reviewasks for another pass..github/workflows/chip-pr-review.ymlmust stay byte-identical to mono's copy, so any change to it is made in mono.The change is docs only. This is the first PR to go through the new process.
🤖 Generated with Claude Code
https://claude.ai/code/session_01BbTFsJ6NvdFt4NG4UJG57m