• ClawSweeper keeps one durable marker-backed review comment per issue or PR.
• Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
• A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
• PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
• Maintainers can also comment @clawsweeper review to request a fresh review only.
• Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
• Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
• Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

• 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
• 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
• 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
• 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
• 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
• 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
• 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

Best possible solution:

Settle the parent policy tool-posture PR first, then rebase this follow-up so reviewers can evaluate the policy reference tables as the remaining change.

Do we have a high-confidence way to reproduce the issue?

Not applicable: this is a stacked policy/docs PR rather than a bug report. The review used the PR body, related parent context, current-main source, and the local PR commits instead of a failing reproduction path.

Is this the best way to solve the issue?

Yes for the docs direction, but not as a direct merge while it carries the parent feature. The maintainable path is to decide the parent policy contract first and then land this as a rebased docs follow-up.

Label justifications:

• P2: This is a normal-priority policy/docs improvement with limited blast radius but real maintainer sequencing risk.
• merge-risk: 🚨 compatibility: Direct merge would introduce new policy fields and check outputs from the still-open parent PR.
• merge-risk: 🚨 security-boundary: The carried policy checks describe security-sensitive tool posture and must match the maintainer-approved security contract.
• rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🐚 platinum hermit, patch quality is 🐚 platinum hermit, and The patch has sufficient proof and no blocking finding, with merge readiness mainly gated on parent sequencing and policy contract review.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body gives exact docs validation commands, and the linked parent context includes redacted live CLI output for the carried tool-posture policy behavior.
• proof: sufficient: Contributor real behavior proof is sufficient. The PR body gives exact docs validation commands, and the linked parent context includes redacted live CLI output for the carried tool-posture policy behavior.

What I checked:

• Protected maintainer handling: The provided live GitHub context lists the maintainer label on this PR, which prevents conservative cleanup closing and requires explicit maintainer handling.
• Stacked parent is still open: The PR body says it is stacked on Policy: add tool posture conformance checks #85482, and the related-item context shows that parent policy tool-posture PR is still open.
• Actual branch surface includes parent implementation: The branch diff against its recorded base adds 1,499 lines across policy docs, source, and tests, so this is not a docs-only merge candidate until the parent lands or the branch is rebased. (042bd01c14ce)
• Parent policy checks carried by this branch: The carried parent commit registers the new tool-posture policy health checks, including profile, filesystem, exec, elevated, and required-deny checks. (extensions/policy/src/doctor/register.ts:161, 87bb37325b4a)
• Docs table change is the follow-up commit: The head commit adds the policy rule reference section, including field tables for tool posture and the other policy categories. Public docs: docs/cli/policy.md. (docs/cli/policy.md:168, 042bd01c14ce)
• Current main did not alter the touched policy files since the PR base: No output for the touched policy/docs files, so current main has not independently changed those files since the PR's recorded base. (edbd8333511c)

Likely related people:

• steipete: In this shallow/grafted checkout, git blame and git log --follow for the central policy docs/code all trace current-main lines back to Peter Steinberger's grafted import commit, so this is the only concrete current-main routing signal available. (role: current-main source-history signal; confidence: low; commits: 9c26b87114c9; files: docs/cli/policy.md, extensions/policy/src/doctor/register.ts, extensions/policy/src/policy-state.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against edbd8333511c.

• Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
• The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
• Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
• The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
• Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.