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 skills add mir-am/skills-agents-ai-coding --skill gh-pr-reviewgit clone --depth 1 https://github.com/mir-am/skills-agents-ai-codingWrote 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/mir-am/skills-agents-ai-coding/gh-pr-review)<a href="https://agentmods.dev/skills/mir-am/skills-agents-ai-coding/gh-pr-review"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/gh-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/mir-am/skills-agents-ai-coding/gh-pr-review"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/gh-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 | $0.00017 | $0.03704 |
| Opus 5 | $0.00009 | $0.01852 |
| Sonnet 5 | $0.00003 | $0.00741 |
| Haiku 4.5 | $0.00002 | $0.00370 |
Grade A, and why
gh-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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
- Validate GitHub CLI (
gh) is installed and authenticated - Fetch PR metadata (title, body, author, branches, state)
- Retrieve full diff and list of changed files
- Generate structured code review with severity-based feedback
- Write review to
.opencode/review/directory as markdown - Warn on large PRs (>20 files) and ask user to confirm
When to use me
Use this skill when the user asks to review a GitHub Pull Request by its number.
Trigger examples:
- "Review PR #123"
- "Review pull request 456"
- "Analyze PR 789"
Prerequisites
-
GitHub CLI installed:
ghmust be available- Check:
command -v gh >/dev/null 2>&1 - If not found: "Error: GitHub CLI not found. Install from: https://cli.github.com/"
- Check:
-
Authenticated with GitHub: User must be logged in
- Check:
gh auth status - If not authenticated: "Error: Not authenticated with GitHub. Run: gh auth login"
- Check:
-
GitHub remote: Repository must have a GitHub remote configured
- Check:
gh repo view --json nameWithOwner - If fails: "Error: This repository does not have a GitHub remote configured."
- Check:
PR Number Extraction
Extract the PR number from user input:
- Pattern:
#?(\d+)(supports with or without#) - Examples: "#123" → 123, "PR 456" → 456, "pull request 789" → 789
- If no number found: "Error: Please provide a valid PR number (e.g., 'review PR #123')."
Validation Workflow
-
Validate prerequisites (run in parallel):
command -v gh >/dev/null 2>&1 && echo "gh found" || echo "gh not found"gh auth statusgh repo view --json nameWithOwner -q .nameWithOwner -
Validate PR exists:
gh pr view <PR_NUMBER> --json number,state- If fails: "Error: PR # not found. Verify the PR number and repository."
Data Gathering Workflow
After validation passes, fetch PR data in parallel:
1. Get PR Metadata
gh pr view <PR_NUMBER> --json title,body,author,baseRefName,headRefName,number,state,url,additions,deletions
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 · 481 lines · 17 tokens per session scan A 334287bee8d3
gh-pr-review is a skill published in the GitHub repository mir-am/skills-agents-ai-coding (2 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 3,704 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
git-workflow
Conventional commits, PR creation, and quality gate verification.
review-gate
HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, blocks PR creation if requirements not met.
hunk-extensions
Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.