From a582fc2d5c910a8fb327f08fb2e9c0a6b4347e44 Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Thu, 14 May 2026 09:58:58 +0100 Subject: [PATCH] chore: tighten codex review skill --- .agents/skills/codex-review/SKILL.md | 8 +++++--- CHANGELOG.md | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/.agents/skills/codex-review/SKILL.md b/.agents/skills/codex-review/SKILL.md index b861a67d23c..46fd21cbf4f 100644 --- a/.agents/skills/codex-review/SKILL.md +++ b/.agents/skills/codex-review/SKILL.md @@ -19,7 +19,9 @@ Use when: - Read dependency docs/source/types when the finding depends on external behavior. - Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase. - Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class. -- If a review-triggered fix changes code, rerun focused tests and rerun Codex review once. +- Keep going until Codex review returns no accepted/actionable findings. +- If a review-triggered fix changes code, rerun focused tests and rerun Codex review. +- If rejecting a finding as intentional/not worth fixing, add a brief inline code comment only when it explains a real invariant or ownership decision that future reviewers should know. - Do not push just to review. Push only when the user requested push/ship/PR update. ## Pick Target @@ -58,7 +60,7 @@ Format first if formatting can change line locations. Then it is OK to run tests scripts/codex-review --parallel-tests "" ``` -Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review once. +Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review until no accepted/actionable findings remain. ## Context Efficiency @@ -96,4 +98,4 @@ Include: - review command used - tests/proof run - findings accepted/rejected, briefly why -- whether review was rerun after review-triggered edits +- final clean review command, or why a remaining finding was consciously rejected diff --git a/CHANGELOG.md b/CHANGELOG.md index a21f7060c22..b2bf180988e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,7 +6,7 @@ Docs: https://docs.openclaw.ai ### Changes -- Maintainer tooling: add a repo-local `codex-review` skill for Codex closeout reviews, including local dirty-work and PR-branch review helpers. +- Maintainer tooling: add a repo-local `codex-review` skill for Codex closeout reviews, including local dirty-work and PR-branch review helpers that rerun until no accepted/actionable findings remain. - Maintainer tooling: fail CI when pull requests add package patch files or pnpm patched dependencies, preserving the upstream-and-bump dependency workflow. - Amazon Bedrock: externalize the Bedrock and Bedrock Mantle provider packages so core installs no longer pull AWS SDK dependencies unless those providers are installed. - Plugins: externalize Slack, OpenShell sandbox, and Anthropic Vertex so their runtime dependency cones install only when those plugins are installed.