Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/steipete/agent-rulesWrote 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/rules/steipete/agent-rules/pr-review)<a href="https://agentmods.dev/rules/steipete/agent-rules/pr-review"><img src="https://agentmods.dev/badge/rules/steipete/agent-rules/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/rules/steipete/agent-rules/pr-review"><img src="https://agentmods.dev/badge/rules/steipete/agent-rules/pr-review.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 | $0.00518 | $0.00518 |
| Opus 5.5 | $0.00207 | $0.00207 |
| Sonnet 5.5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pr-review — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Review
Comprehensive pull request review from multiple perspectives.
Review Roles:
1. Product Manager Review
- Business Value: Does this deliver promised value?
- User Experience: Will users benefit from this change?
- Strategic Alignment: Does it align with product goals?
- Feature Completeness: Are all requirements met?
- Action: Provide directives for maximum impact
2. Developer Review
- Code Quality: Is code clean and maintainable?
- Standards: Does it follow coding conventions?
- Performance: Are there efficiency concerns?
- Scalability: Will it handle growth?
- Refactoring: Any code that needs improvement?
- Action: Suggest specific code improvements
3. Quality Engineer Review
- Test Coverage: Are all paths tested?
- Edge Cases: Are boundary conditions handled?
- Regression Risk: Could this break existing features?
- Test Quality: Are tests comprehensive and clear?
- Action: Identify missing tests and scenarios
4. Security Engineer Review
- Vulnerabilities: Any security risks?
- Data Handling: Is sensitive data protected?
- Authentication: Are auth checks proper?
- Input Validation: Is user input sanitized?
- Compliance: Does it meet security standards?
- Action: Flag security concerns immediately
5. DevOps Review
- CI/CD Integration: Will builds succeed?
- Configuration: Are configs properly managed?
- Infrastructure: Any deployment concerns?
- Monitoring: Are metrics and logs adequate?
- Rollback: Can changes be safely reverted?
- Action: Ensure smooth deployment
6. UI/UX Designer Review
- Visual Consistency: Does it match design system?
- Usability: Is it intuitive to use?
- Accessibility: Is it accessible to all users?
- Responsive: Does it work on all devices?
- Polish: Any rough edges to smooth?
- Action: Ensure delightful user experience
Review Process:
- Read PR description and linked issues
- Review code changes systematically
- Test functionality locally if applicable
- Consider each perspective above
- Leave constructive feedback
- Approve or request changes
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 First seen · 62 lines · 518 tokens per session scan A b1c5d9b2dfdd
pr-review is a cursor rule published in the GitHub repository steipete/agent-rules (5,677 stars, last pushed 5mo ago), licensed MIT. It adds 518 tokens to every session, about $0.0021 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 2026-08-30.
Other cursor rules, from other repositories
knip
Knip dead-code policy: why each override in root knip.jsonc exists, and how the default and production passes feed the PR code-quality report.
quality-report
PR code-quality report: non-blocking Knip and jscpd diff against the merge base, isolated write token, sticky comment, and the .jscpd.json rationale.
code-style
Code style - OXC decides; thin handlers; unknown only at I/O boundaries; oxlint suppression form; strict tsconfig flags.
general_clean_code_principles
Clean code principles for better readability.
review
Structured code review with severity ratings — CRITICAL/HIGH/MEDIUM/LOW.
analyze
Codebase analysis — complexity, coupling, dead code, tech debt hotspots.