Borrowing it
Nothing to install: this file belongs to lee-to/aif-handoff. 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/lee-to/aif-handoff/main/.claude/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/lee-to/aif-handoffWrote 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/lee-to/aif-handoff/pr-review)<a href="https://agentmods.dev/skills/lee-to/aif-handoff/pr-review"><img src="https://agentmods.dev/badge/skills/lee-to/aif-handoff/pr-review/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/lee-to/aif-handoff/pr-review"><img src="https://agentmods.dev/badge/skills/lee-to/aif-handoff/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.05454 |
| Opus 5 | $0.00042 | $0.02727 |
| Sonnet 5 | $0.00017 | $0.01091 |
| Haiku 4.5 | $0.00008 | $0.00545 |
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 11d 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 — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review — Stateful Reviewer with Verdict Comment
Review a GitHub pull request end-to-end and post a single verdict comment. Respects the
aif convention: loads project context (RULES.md, CHECKLIST.md, config.yaml), applies context
gates, stays read-only on .ai-factory/*, and writes only one artifact — the PR comment.
Core focus:
- Code cleanliness — no debug markers, no TODO/FIXME leaks, no dead code, no unreachable branches.
- Duplication — DRY violations, N+1 patterns, repeated blocks that should be extracted or hoisted.
- Docs sync — when code changes, the matching docs (README,
docs/**, sync rules from CLAUDE.md) change too.
Not a lint replacement. Assume CI covers formatting, type errors, and compile failures. Focus on judgment-level findings that humans otherwise miss on review.
Step 0: Load Context
0.1 Load config.yaml
FIRST: Read .ai-factory/config.yaml if it exists to resolve:
- Paths:
paths.description,paths.architecture,paths.rules_file,paths.roadmap, andpaths.rules - Language:
language.ui— use for the final comment's language (default: English) - Git:
git.base_branch— used when the PR targets a non-standard base
If config.yaml is absent, use defaults:
- Paths:
.ai-factory/for all artifacts - Language: English
- Base branch:
main
0.2 Load Project Context
Read in parallel:
.ai-factory/DESCRIPTION.md— tech-stack summary.ai-factory/ARCHITECTURE.md(if present) — dependency boundaries.ai-factory/RULES.md— axioms that the PR MUST respectCHECKLIST.md(repository root) — top-level checklist itemsCLAUDE.md(root) — project instructions; in particular the Sync Rules sections (Docker Sync Rule, Runtime Adapter Sync Rule, and any otherSync when ...rules)
Store the parsed rule/checklist text; cite specific lines in findings rather than paraphrasing.
0.3 Load Skill Context Override
Read .ai-factory/skill-context/pr-review/SKILL.md — MANDATORY if the file exists.
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.
- 11d ago First seen · 543 lines · 83 tokens per session scan A 4091ec09c0af
pr-review is a skill published in the GitHub repository lee-to/aif-handoff (288 stars, last pushed 17d ago), licensed MIT. It adds 83 tokens to every session and 5,454 once invoked, about $0.0004 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 skills, from other repositories
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
external-pr-review
Apply the external contributor PR review procedure. Collect PR information, write mydocs/pr/pr{N}review.md, verify, write pr{N}report.md, and move documents to archives/ when processing is complete. Use only for external contributor PRs, not internal tasks.
storozh
Advisory semantic guard over a changeset manifest before it lands in shared state. Use after a multi-repo session produces a changeset-manifest (mirabilis C1) and before the co-sign push gate — classify each unit's routing against the darwin routing-policy (C3) and NLI-check each unit against the shield corpus (claims…
generator-evaluator-loop
Orchestrate a Coder→Quality iteration loop against a story's Verification contract. Use when a story has a complete Verification section and is ready for execution with automated review.
review-before-commit
Run a behavioral self-check before persisting story results. Verifies diff simplicity, scope adherence, and verifiable completion against enso §10 behavioral principles. Use when a story's implementation is complete and ready to close.
adversarial-review
Run an independent audit gate before any fleet output lands. Use after agent-fleet-orchestration Stage 3 (or any multi-agent build) — before merge, before deploy, before the next phase. Frames the reviewer as an external adversary, not a helper; produces triaged findings with human triage for load-bearing blockers.