grepai is a local command-line tool that searches source code by meaning and traces function call graphs, rather than matching only exact words. Developers and coding agents use it to find relevant code, understand relationships between functions, and provide focused context for changes while keeping the code on the local machine. The catalogue entries expose its commands, skills, agent, and instruction for coding-agent workflows.
Borrowing it
Nothing to install: this file belongs to yoanbernabeu/grepai. 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/yoanbernabeu/grepai/main/.claude/commands/review-pr.mdgit clone --depth 1 https://github.com/yoanbernabeu/grepaiWrote 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/yoanbernabeu/grepai/review-pr)<a href="https://agentmods.dev/commands/yoanbernabeu/grepai/review-pr"><img src="https://agentmods.dev/badge/commands/yoanbernabeu/grepai/review-pr.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 5.1 | $0.00000 | $0.00632 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR Command
You are a Pull Request review assistant. Follow these steps in order:
Step 1: Retrieve PR Information
Use gh pr view $ARGUMENTS --json number,title,body,state,author,headRefName,baseRefName,additions,deletions,changedFiles,labels to get PR details.
If no argument is provided, list open PRs with gh pr list and ask the user which one to review.
Step 2: Check CI Status
Use gh pr checks $ARGUMENTS to verify all GitHub Actions checks pass.
- If any checks fail, display the details and ask the user if they want to continue anyway
- If all checks pass, continue
Step 3: Analyze the Code
- Get the diff with
gh pr diff $ARGUMENTS - Analyze the modified code:
- Code quality
- Adherence to project conventions
- Potential bugs or security issues
- Tests added/modified if relevant
- Provide a summary of your analysis with observations
Step 4: Determine Change Type
Analyze the PR title and modified files to determine the type:
feat: New featurefix: Bug fixdocs: Documentation onlychore: Maintenancerefactor: Refactoringtest: Tests only
Step 5: Request Custom Message
Use the AskUserQuestion tool to ask the user:
- If they want to add a custom comment on the PR before merging
- If yes, what message to add
If the user provides a message, add it as a comment on the PR with gh pr comment $ARGUMENTS --body "MESSAGE".
Step 6: Merge the PR
- Ask for user confirmation before merging
- Merge with
gh pr merge $ARGUMENTS --squash --delete-branch - Update local branch with
git checkout main && git pull origin main
Step 7: Create a Release (if applicable)
If the change type is feat or fix (not docs, chore, test):
- Get the latest version with
gh release list --limit 1 - Parse the current version number (semver format vX.Y.Z)
- Ask the user with AskUserQuestion:
- For
feat: propose a Minor version (vX.Y+1.0) or ask if it's a Major (vX+1.0.0) - For
fix: propose a Patch version (vX.Y.Z+1)
- For
- Generate release notes based on commits since the last release
- Create the release with
gh release create vX.Y.Z --generate-notes --title "vX.Y.Z"
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.
- 6d ago First seen · 70 lines · 0 tokens per session scan A 75a51dc7731c
review-pr is a command published in the GitHub repository yoanbernabeu/grepai (1,838 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 632 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 2026-08-30.
Other commands, from other repositories
review
Review the current changes with the code-reviewer subagent.
sdd-apply
Implement SDD tasks — writes code following specs and design.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
note
Add a note to the active task - progress, decisions, context. --session (aliases --snapshot, --pre-compact, --compact) writes a resume-grade session snapshot without ending the session.