@@ -13,7 +13,7 @@ Skills own workflows; root owns hard policy and routing.
1313- Review default: read the whole changed function/module plus callers, callees, sibling implementations, adjacent tests, scoped docs, and dependency/Codex contracts before saying `good`, `bad`, `best fix`, `proof sufficient`, or posting a comment. If challenged, keep reading first; do not defend the earlier verdict until the missing path is checked.
1414- Dependency-touching work: direct dependency inspection is mandatory when feasible; do not rely on assumptions, wrappers, or memory. Most dependencies are OSS, so read their source/docs/types. Codex-related work has a hard gate: the acting agent must personally inspect sibling `../codex` source for the exact protocol/runtime behavior before any verdict, comment, approval, merge recommendation, code change, or `proof sufficient` claim. If missing, clone `https://github.com/openai/codex.git` there first. Subagent reports, PR text, OpenClaw wrappers, generated schemas, memory, and prior bot reviews do not satisfy this gate. No direct `../codex` check means no Codex verdict. Cite Codex files/lines checked in final/review/comment.
1515- Dependency-backed behavior: read upstream docs/source/types first. No API/default/error/timing guesses.
16-- External API work: Google/search for additional proof. Prefer official docs/source/types; cite current proof. No memory-only API claims.
16+- External API work: live test required. Google/search for additional proof. Prefer official docs/source/types; cite current proof. No memory-only API claims.
1717- Live-verify when feasible. Never print secrets.
1818- Missing deps: `pnpm install`, retry once, then report first actionable error.
1919- CODEOWNERS: maint/refactor/tests ok. Larger behavior/product/security/ownership: owner ask/review.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。