Borrowing it
Nothing to install: this file belongs to bobberrisford/affiliatemcp. 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/bobberrisford/affiliatemcp/main/.claude/skills/review-pr/SKILL.mdgit clone --depth 1 https://github.com/bobberrisford/affiliatemcpWrote 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/bobberrisford/affiliatemcp/review-pr)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/review-pr"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/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/bobberrisford/affiliatemcp/review-pr"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/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 | $0.00047 | $0.01053 |
| Opus 5 | $0.00023 | $0.00526 |
| Sonnet 5 | $0.00009 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
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 12d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a pull request
Follow the delivery and review protocol in AGENTS.md. This skill is the
independent engineering backstop for fast agent-authored and maintainer-authored
work, including Rob-authored PRs where no separate human reviewer exists. Find
material problems without turning preferences or hypothetical future needs into
blockers.
1. Establish the review target
Gather current evidence:
git status --short --branch
git fetch origin
gh pr view <number> --json number,title,url,author,isDraft,baseRefName,headRefName,mergeable,mergeStateStatus,reviewDecision,reviewRequests,statusCheckRollup,body,files,commits,reviews
gh pr diff <number> --patch
gh pr checks <number>
Read the applicable repo instructions, PR body, complete diff, changed tests, adjacent ownership boundaries, accepted decisions, and direct dependency diffs. Do not rely on the PR summary alone. Treat implementation beyond an unresolved decision as a sequencing blocker even when the PR is draft or CI is green.
2. Review in risk order
Review these concerns in order:
- Public contracts, shared behaviour, authentication, security, writes, payments, releases, deployment, and cross-client or cross-network semantics.
- Dependency and sequencing validity: accepted decisions, semantic conflicts, intended merge order, and whether a foundation has a concrete first consumer.
- Concrete correctness failures, unhappy paths, error handling, and data loss.
- Tests that are absent, misleading, or unable to catch the claimed behaviour.
- Ownership and maintainability: logic in the wrong layer, hidden coupling, duplicated domain behaviour, or an abstraction that obscures rather than simplifies.
- Product and customer journey: technically correct but confusing behaviour, unclear tool names or descriptions, hidden network limitations, or a changed journey that the PR does not explain.
- Documentation accuracy across the README, MCP tool docs, examples, skills, roadmap or product docs, contribution docs, and release notes when relevant.
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.
- 12d ago First seen · 114 lines · 47 tokens per session scan A 3649d1a9e657
review-pr is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,053 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…