Borrowing it
Nothing to install: this file belongs to agentdecksdk/agentdeck. 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/agentdecksdk/agentdeck/dev/.claude/skills/review-pr/SKILL.mdgit clone --depth 1 https://github.com/agentdecksdk/agentdeckWrote 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/skills/agentdecksdk/agentdeck/review-pr)<a href="https://agentmods.dev/skills/agentdecksdk/agentdeck/review-pr"><img src="https://agentmods.dev/badge/skills/agentdecksdk/agentdeck/review-pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentdecksdk/agentdeck/review-pr"><img src="https://agentmods.dev/badge/skills/agentdecksdk/agentdeck/review-pr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.02400 |
| Opus 5.5 | $0.00025 | $0.00960 |
| Sonnet 5.5 | $0.00012 | $0.00480 |
| Haiku 4.5 | $0.00006 | $0.00240 |
Grade A, and why
review-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a PR
A reviewer finds what matters, says it, and stays silent elsewhere. Prove nothing; assert what you found.
Setup
- Read
CLAUDE.md,docs/engineering/(principles.md,coding-standards.md,coding-agents.md, relevant specialized standards), and thedocs/patterns/files for the concerns this PR touches. - Read the linked issue (
gh issue view <n>) and the full diff (gh pr diff <n>). - Check out the branch (
gh pr checkout <n>), seed the worktree (copy.envif present, thenuv venv --python 3.12 && make install), runmake check. It ends by naming the docs-site pages this diff affects: open every page the PR left unchanged and confirm it is still true. No CI job does this; it is where stale prose is caught (#409 shipped five stale references past a ticked box). - Run
uv run scripts/quality_delta.pyandPR_BODY="$(gh pr view <n> --json body -q .body)" uv run scripts/concept_budget.py. Hold the PR to its own## Expected deltaand## Concept budget, whichship-prStage 1 wrote into the draft body before the first source edit and the design gate already passed. Unexplained overrun beyond roughly 2x runs the overrun pass (references/overrun.md); the number itself is never the finding. A body carrying no estimate is a contribution that never ran Stage 1: report the measurement and skip the trigger. - Sibling comparison: for each changed or new module, pick 2-3 canonical siblings from
uv run scripts/repomap.py(same package, same responsibility class), read them, and verify the PR's own## Analogclaim against the code.
Phases
Work in order. Correctness before craft: a wrong design makes naming irrelevant. Copy this checklist into your own response and check off each phase as you complete it:
Review progress:
- [ ] 1. Claims: what does this PR assert, and what must be true
- [ ] 2. Attack: go after those claims (references/attack.md)
- [ ] 3. Craft: patterns, naming, tests as spec (references/craft.md)
- [ ] 4. Scope: should this be two PRs
- [ ] 5. Verdict: post it (references/templates.md)
- [ ] 6. Harvest: usually nothing (references/craft.md)
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +3 lines db7a7570ae76
- 1mo ago Changed · +2 lines c5c1fcc478bb
- 2mo ago First seen · 86 lines · 62 tokens per session scan A c61481d95441
review-pr is a skill published in the GitHub repository agentdecksdk/agentdeck (4 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 2,400 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
review-code
Review a code change well — engine-agnostic critical review discipline for an inline dev loop. Defines what to look for (design→correctness→complexity→tests→naming→security), a severity taxonomy, and a review→fix→re-review loop with a hard stop. Use on "review this code", "review my diff", "is this change good"…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
code-quality
Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.
code-review
AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security). Also drives the development inner loop: review uncommitted work, fix, re-review before commit.
code-review
Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.