// Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review
Tripwire check for multi-session drift. Scans state files, recent commits, and file conflicts caused by parallel Claude Code sessions.
Scan for orphaned worktrees and stale branches after crashes or abandoned sessions. Offers safe cleanup options.
Structured session lifecycle for Claude Code — start, checkpoint, end, and daily heartbeat commands that maintain project state across conversations.
Generate a new Claude Code skill file from a plain-language description. Scaffolds the SKILL.md, command file, and CLAUDE.md additions.
| name | code-review |
| description | Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review |
User-invokable orchestrator for code-PR review across any repo. Validated on a Vercel-deployed Next.js app PR across 5 review rounds: Copilot caught ~10 line-level issues; parallel subagents caught the P0 architectural miss (Vercel maxDuration) Copilot missed across all 5 rounds, plus a persistent-replay vector and 4 operational issues.
If you have access to a paid multi-agent review service (e.g. /ultrareview in Claude Code), this skill is the in-flight free version of the same idea — useful when you want this depth without spinning up a billed cloud review.
gh pr view N --json files,additions,deletions,title
Categorize:
| Tier | Examples | Treatment |
|---|---|---|
| Trivial | Typo, copy edit, single-line deps bump, README polish | Skip multi-agent. Copilot alone is enough. |
| Standard | Component refactor, single-feature bug fix, contained logic change | Copilot + 1 subagent (pick the angle that matches the risk shape) |
| High-stakes | Payment, auth, crypto/wallet, RPC, deployment configs, scale-relevant changes, new external SDK integrations | Copilot + 2 parallel subagents minimum (always include adversarial + operational) |
If trivial → stop reading this skill, just request Copilot review and ship.
Three angles that empirically work. Pick by risk shape:
maxDuration was the canonical one).Spawn all chosen subagents in a single tool-call batch so they run in parallel. Prompt templates live in patterns/subagent-prompts.md.
Every subagent prompt must specify:
gh pr edit N --add-reviewer copilot-pull-request-reviewer
Don't wait for Copilot to start before spawning subagents. They run in parallel.
Three buckets:
Real findings — fix now. Push fix to the PR branch.
Stale re-flags — Copilot will sometimes re-flag findings against unmoved diff lines after fixes ship at HEAD. Always read the file at HEAD before re-fixing. If the fix is already there, drop a one-line reply on the comment ("Fixed at ") and move on. Do not re-fix.
Deferred (filed) — tests, refactors, or work outside scope. File as a GitHub issue, link the issue number in the merge commit message, move on. Don't expand the PR.
Maximum 2 Copilot review rounds. Empirically, by round 3 the signal-to-noise ratio collapses (~50% stale re-flags). Ship after round 2. If subagents flag genuinely new issues after round 2, those are issue-tracker items, not PR-blockers.
/security-review if you suspect a problem.Validation case (5 rounds on a high-stakes PR):
maxDuration not set — function would time out under realistic load. Architectural miss invisible at the line level.bodyParser size limit (DoS surface).Subagents are not redundant with Copilot. They cover a different layer.
patterns/subagent-prompts.md — paste-ready prompt templates for the three angles.