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/GktuOktay/ai-skillsWrote 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/gktuoktay/ai-skills/git-pr-reviewer)<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/git-pr-reviewer"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/git-pr-reviewer/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/gktuoktay/ai-skills/git-pr-reviewer"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/git-pr-reviewer.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 | $0.00000 | $0.00648 |
| Opus 5 | $0.00000 | $0.00324 |
| Sonnet 5 | $0.00000 | $0.00130 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
git-pr-reviewer 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 7d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request and Code Review Guide
This skill provides guidelines for creating excellent pull requests and conducting effective, constructive code reviews.
Writing Good PR Descriptions
A PR description should answer the "What, Why, and How" to give reviewers context.
Essential Components
- What: Briefly summarize the changes introduced.
- Why: Explain the motivation (link to issue/ticket).
- How: Highlight key implementation details or architectural decisions.
- Testing: How can the reviewer test these changes?
Example PR Description
## What
Added email verification step during user registration.
## Why
Fixes #456. We need to ensure users provide valid email addresses before granting access.
## How
- Integrated SendGrid API for sending verification emails.
- Added `is_verified` flag to `users` table.
- Created `/verify-email` endpoint.
## Testing Steps
1. Register a new account.
2. Check your email for the verification link.
3. Click the link and verify the account activates successfully.
Conducting Constructive Code Reviews
Code reviews should improve code quality and facilitate knowledge sharing, not criticize the author.
Principles
- Be Respectful: Critique the code, not the author. Use "we" instead of "you".
- Be Specific: Point exactly to the line and suggest an alternative.
- Explain Why: Don't just say "change this"; explain the benefit (e.g., performance, readability).
- Praise Good Code: Acknowledge elegant solutions.
Merge Strategies
Choose the right merge strategy based on project conventions.
1. Squash and Merge
- Best for: Feature branches with many messy, WIP commits.
- Result: Combines all commits into a single, clean commit on the main branch.
2. Rebase and Merge
- Best for: Branches with clean, logical, and atomic commits.
- Result: Appends all commits to the main branch history linearly (no merge commit).
3. Merge Commit
- Best for: Large feature branches where keeping the branch history intact is valuable.
- Result: Creates a dedicated merge commit showing when the branch was merged.
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.
- 7d ago First seen · 77 lines · 648 tokens per session scan A dab820ddabbf
git-pr-reviewer is a cursor rule published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 648 tokens. 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 2026-09-03.
Other cursor rules, from other repositories
pr
Create a GitHub Pull Request with full AI review.
pre-release-review
Principal-level code review checklist — run before any release is cut.
git-workflow
Git workflow: commits, branches, PRs, history management.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.