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 kimgoetzke/coding-agent-configs --skill review-prgit clone --depth 1 https://github.com/kimgoetzke/coding-agent-configsWrote 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/kimgoetzke/coding-agent-configs/review-pr)<a href="https://agentmods.dev/skills/kimgoetzke/coding-agent-configs/review-pr"><img src="https://agentmods.dev/badge/skills/kimgoetzke/coding-agent-configs/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 | $0.00085 | $0.04455 |
| Opus 5 | $0.00043 | $0.02227 |
| Sonnet 5 | $0.00017 | $0.00891 |
| Haiku 4.5 | $0.00009 | $0.00445 |
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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR
You are tasked with reviewing a GitHub pull request in the current repository. You will analyse the diff, check for issues across multiple dimensions, verify and triage the raw findings from the review sub-agents to cut noise, identify which skills were used during the review, assign a purple-red-amber-green score to each review dimension, and produce a structured review saved to disk and presented to the user.
Two rules that override everything else in this skill:
- Never auto-post to GitHub. Even when running non-interactively or in an "auto" mode, you MUST NOT post review comments to the PR without explicit sign-off from the user. See step 9. The only exception is when the user granted that sign-off up front when invoking the skill (e.g. "review PR 42 and post the comments").
- Verify before you report. Sub-agent findings are unverified. Every finding passes through the triage step (step 6) — you confirm it is true and worth raising before it reaches the review. This is how we keep out the noise.
Step 1: Check prerequisites
Verify that the GitHub CLI is available:
- Run
gh --version - If
ghis not found: inform the user thatgh(GitHub CLI) is required for this skill to work as expected and that without it you may not be able to perform the intended review. Ask the user explicitly whether they wish to continue regardless. If they decline, stop.
Step 2: Resolve the PR
If an argument was provided (PR number or URL):
- If the argument is a URL pointing to a different repository, respond with: "This skill only supports reviewing PRs in the current repository. Please switch to the relevant repo and try again." then stop.
- Otherwise, extract the PR number and proceed.
If no argument was provided:
- Run
gh pr view --json number,title,url 2>/dev/nullto detect a PR from the current branch. - If no PR is found, ask the user for a PR number.
Validate the PR exists: gh pr view {number} --json number,title,headRefName,baseRefName,url,body,author,state
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 · 312 lines · 85 tokens per session scan A 7274f1d637d2
review-pr is a skill published in the GitHub repository kimgoetzke/coding-agent-configs (2 stars, last pushed 17d ago), licensed MIT. It adds 85 tokens to every session and 4,455 once invoked, about $0.0004 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
review-pr
Use when asked to review a GitHub Pull Request or GitLab Merge Request, including PR/MR URLs, identifiers, discussions, findings, inline comments, approvals, or request-changes actions.
create-gitlab-mr
Create a feature branch from current Git changes, commit and push it, and open a GitLab Merge Request with the official glab CLI. Use when asked to create, open, or publish a GitLab merge request from local work.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…