High-signal autonomous PR review posted under your account. A review you'd put your name on — precision over coverage.

Inputs. pr-url from the arg or the current branch's upstream PR. --manifest <path> switches the skill into manifest mode: it skips the generic reviewer fleet and independently verifies only the manifest's contract — it does not merely ground the fleet against author intent. Only in that mode, load references/MANIFEST_MODE.md for the verification mechanics; without --manifest, that reference is never read and review runs the generic review-code fleet. The skill does not auto-discover a manifest from any folder convention. --bundle <urls> plus PR-description linked-PR parsing (Depends on #N, Stack:, Co-changes:, GitHub PR URLs) provides cross-PR context for coupled changes. Resolve the PR, current head SHA, our prior GitHub reviews/comments/replies, open review threads, author commits, PR description, and linked-PR context before deciding what to do.

Self-marking. Posting under your own account means a human reviewer uses the same account, so authorship alone can't tell our automated comments from theirs. Stamp every body this skill posts — new finding comments, thread replies, the summary header, the approval body, and manifest-mode PASS/FAIL — with a trailing hidden marker  — a fixed literal string, byte-identical wherever review-pr runs (don't namespace-rewrite it per distribution, or comments posted by one host stop matching another's); GitHub strips it from the rendered comment but returns it through the API. This marker, not account authorship, is what makes a comment an automated review-pr comment: everywhere this skill says threads/comments we authored or replied to (or our prior reviews/comments) it means the ones carrying this marker, so an unmarked comment on our account reads as human and is left untouched. Manifest mode extends the marker with the criterion id (references/MANIFEST_MODE.md). Judgment-pass findings extend it with a judgment token —  — so a prior judgment finding is distinguishable from an ordinary review-pr comment in both modes (the once-per-PR gate keys on this token). Comments predating this marker are unmarked and so now read as human — review-pr stops advancing its own pre-marker threads, which self-heals as new marked comments accrue.

One-Shot Pass

Every invocation, including non---loop, performs one complete PR-state advance:

Advance our existing threads. For every unresolved thread we authored or replied to, run the per-thread verification below. Post needed thread replies, resolve terminal threads, and leave genuinely pending threads open.
Verify the change. Manifest mode (--manifest): load references/MANIFEST_MODE.md and follow it to verify the manifest contract against the PR head — the generic reviewer fleet is skipped entirely. No-manifest mode: run the generic reviewer fleet over the review range — determine that range from durable GitHub state: if we have a prior review on this PR and the head has moved since, use that review's commit/head SHA as the lower bound and review last-reviewed-by-us..current-head; otherwise review the full PR diff. In both modes, the judgment pass (below) runs in parallel with the fleet/contract verification, gated to once per PR.
Post outcomes. Submit new surviving findings as a single GitHub review with decision comment. Thread replies are posted on their existing threads, not as new review comments. End with the cycle summary below.

The one-shot pass is CI-shaped: it must make useful progress from only GitHub state and the current checkout. Do not rely on session memory such as last-reviewed-sha; derive it from our prior review/comment metadata and the PR history each run.

An invocation always verifies the change. Choosing to run review-pr again is the operator's call — often a risky change worth a second read, under a different model — so a fresh invocation reviews the head even when we already reviewed it and nothing has moved since. There is nothing to pass for this. The review range is then the full PR diff, and the prune below is what keeps the pass to whatever it has new to add: a second read that simply concurs posts nothing.

The unchanged-head skip survives in one place only — a --loop wake after that invocation's first pass (references/LOOP.md). There nobody re-decided anything, and re-reviewing one commit on every wake is the nag the check exists to prevent. Where a PR carries no prior review of ours, the pass is already a full review of the full diff and nothing about it differs.