Borrowing it
Nothing to install: this file belongs to growthxai/output. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/growthxai/output/main/.claude/commands/pr-review.mdgit clone --depth 1 https://github.com/growthxai/outputWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/growthxai/output/pr-review)<a href="https://agentmods.dev/commands/growthxai/output/pr-review"><img src="https://agentmods.dev/badge/commands/growthxai/output/pr-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.02390 |
| Opus 5 | $0.00003 | $0.01195 |
| Sonnet 5 | $0.00001 | $0.00478 |
| Haiku 4.5 | $0.00001 | $0.00239 |
Grade A, and why
pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
Review this pull request. Do not modify code.
The PR branch is already checked out (shallow clone: fetch-depth: 1 — no full git history/blame). Use gh pr view, gh pr diff, and the local tree.
Tools: mcp__github_inline_comment__create_inline_comment (with confirmed: true) for line pointers only. Do not post a PR summary comment — CI renders it from your structured output.
Scope
Code: Only what this PR adds, changes, or deletes. Neighboring files are fine for conventions; do not file findings against untouched lines unless this PR newly exposes or depends on that problem. No drive-by nits on legacy code.
PR description: Claims to verify (intent, scope, breaks) — not something to grade. Concise is fine. Empty description → at most Nice-to-have; never Must-fix for a weak writeup. If the body claims X and the diff does not support X → a finding under the matching category.
Review process
Work in this order. Do not emit structured output until step 4.
- Draft — Walk Review categories once. Provisional verdict, findings, and category scorecard.
- Temporal lens (when triggered) — In-process only (no subagent). Focus only on Temporal TypeScript SDK correctness, alignment, and wiring. No separate Temporal category; fold into normal findings.
- Trigger if the PR touches
sdk/core/**,api/**, or@temporalio/*dependency adds/version changes (manifest/lockfile). - Review: workflow determinism / sandbox; activity boundaries; retries; heartbeats; cancellation; signals/queries/updates; payloads; replay / patching / versioning; client/worker lifecycle; APIs match the SDK version in use; workers, clients, task queues, interceptors, sinks, schedules coherent with the SDK model.
- When unsure, check Temporal TS SDK docs or upstream for the version this PR uses — do not guess.
- Skipping this step when triggered = incomplete review.
- Trigger if the PR touches
- Adversarial challenge — Attack the draft before finishing (not a second category walk, not a scorecard row):
- Claims the diff does not fully support
- Half-finished wiring (exported but unused, flags with no path, TODOs that leave behavior broken)
- Silent compatibility / contract changes under-called
- Failure modes the happy path ignores
- Generous
PASScategory rows — upgrade toFAILand add a Must-fix finding if the challenge sticks
- Finalize — Merge surviving Temporal/adversarial points into normal findings (upgrade to Must-fix when needed). Drop weak speculation. Emit structured output and any inline comments.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 159 lines · 7 tokens per session scan A 8baefa028ed0
pr-review is a command published in the GitHub repository growthxai/output (435 stars, last pushed 3d ago), licensed Apache-2.0. It adds 7 tokens to every session and 2,390 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
gh-triage
GitHub OSS maintainer lifecycle triage, review, and approval management.
pn-audit-data
Design or review database schema — normalization, indexing strategy, migration plan, and data model decisions. Surgical command for database design. Use standalone or as part of pn-backend-audit.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.
pn-audit-security
OWASP-guided security review — auth posture, input validation, secrets, CORS, JWT, rate limiting. Surgical command for backend security. Use standalone or as part of pn-backend-audit.
pn-distill
Remove content, sections, and features that don't earn their place — information architecture reduction. Use when there's too much stuff on the page. For visual decoration reduction, use pn-quieter.