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.
npx agentmods add commands/fotoetienne/gru/pr_reviewgit clone --depth 1 https://github.com/fotoetienne/gruWrote 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/commands/fotoetienne/gru/pr_review)<a href="https://agentmods.dev/commands/fotoetienne/gru/pr_review"><img src="https://agentmods.dev/badge/commands/fotoetienne/gru/pr_review.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00616 |
| Opus 5 | $0.00005 | $0.00308 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a GitHub pull request: fetch details, analyze changes, and provide feedback.
Pull Request: $ARGUMENTS
Workflow:
1. Fetch PR Details
- Use
gh pr view $ARGUMENTS --json headRefNameto get the branch name - Use
gh pr view $ARGUMENTSto get the PR title, body, and metadata - Use
gh pr view $ARGUMENTS --json filesto get a quick overview of changed files - Fetch existing review comments:
gh api repos/{owner}/{repo}/pulls/{pr#}/comments - Understand the scope and intent of the PR, and any prior discussion
- The code should already be checked out in the current directory
- If this PR is addressing an Issue, read Issue details to understand the problem and context. Does this PR address the issue completely? Are there any missing details or assumptions?
- You don't need to run tests - CI will handle that.
2. Analyze the Changes
- Review each file changed in the diff
- For complex changes, use Read to examine full file context around the changes
- Check CLAUDE.md for project-specific conventions and patterns
- Consider:
- Code correctness and logic
- Error handling
- Edge cases
- Security implications
- Performance considerations
- Test coverage
3. Provide Feedback
- List any issues found (bugs, security concerns, style problems)
- Suggest improvements if applicable
- Give an overall assessment (approve, request changes, or needs discussion)
4. Submit Review
- BEFORE submitting: Check if this is your own PR:
- Use
gh pr view $ARGUMENTS --json author --jq '.author.login'to get the PR author - Use
gh api user --jq '.login'to get your GitHub username - If they match, you CANNOT use
--approveor--request-changes(GitHub will reject it)
- Use
- Use
gh pr review $ARGUMENTSwith:--comment -b "review content"for general feedback (use this for your own PRs)--approve -b "review content"if explicitly approving AND it's not your own PR--request-changes -b "review content"if changes are required AND it's not your own PR
- Use a HEREDOC for multi-line review content to preserve formatting
- IMPORTANT: ALWAYS verify the gh command succeeded by checking its output. If it returns empty or fails, inform the user of the issue
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.
- 5d ago First seen · 51 lines · 9 tokens per session scan A 0bd2fad4fad8
pr_review is a command published in the GitHub repository fotoetienne/gru (11 stars, last pushed 28d ago), licensed Apache-2.0. It adds 9 tokens to every session and 616 once invoked, about $0.0000 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 commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
test
Generate comprehensive tests.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
commit
智能生成 Git 提交信息并提交.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.