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 naorpeled/awesome-oss-skills --skill green-prgit clone --depth 1 https://github.com/naorpeled/awesome-oss-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/skills/naorpeled/awesome-oss-skills/green-pr)<a href="https://agentmods.dev/skills/naorpeled/awesome-oss-skills/green-pr"><img src="https://agentmods.dev/badge/skills/naorpeled/awesome-oss-skills/green-pr/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/naorpeled/awesome-oss-skills/green-pr"><img src="https://agentmods.dev/badge/skills/naorpeled/awesome-oss-skills/green-pr.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 | $0.00055 | $0.00770 |
| Opus 5 | $0.00028 | $0.00385 |
| Sonnet 5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
green-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 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Green PR
Use this skill to work an existing pull request toward a fully green state: every automated review comment resolved, every CI check passing, and every human review thread addressed.
Primary inputs
- the pull request's diff, commits, and description
- automated code review comments (e.g. Qodo, Copilot code review, CodeQL, Baz, CodeRabbit, Greptile, BugBot)
- CI check runs and their logs (unit tests, lint, type checks, mutation testing, platform-specific test jobs)
- human reviewer comments and review threads
- repository conventions from
CONTRIBUTING.md,AGENTS.md, or similar
Instructions
1. Resolve AI code review comments
- Collect every open comment from automated reviewers (bots such as Qodo, Copilot code review, Baz, CodeRabbit, Greptile, or BugBot, and static analysis like CodeQL).
- For each finding, verify it against the actual code before acting — AI review comments can be stale, duplicated, or based on a misunderstanding.
- Apply a fix for genuine issues. If a finding is a false positive, leave it unresolved with a short note explaining why, rather than silently dismissing it.
- Mark each addressed thread as resolved once the fix is committed.
2. Make CI pass
- List all required CI checks for the PR (tests across platforms, lint, type-check, security scans, mutation testing, etc.).
- For each failing check, pull the job logs and fix the root cause rather than only the symptom.
- Re-run or wait for checks after each fix, and keep iterating until every required check is green.
3. Address human review feedback
- For each human reviewer comment or requested change, make the corresponding code change first.
- Do not post a reply on the maintainer's or reviewer's behalf. Instead,
prompt the user with a suggested reply for each thread:
- concise and minimal
- human-readable
- includes a precise explanation of what changed and why (or a precise answer if it was a question)
- Let the user approve, edit, or reject each suggested reply before it is posted.
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 · 87 lines · 55 tokens per session scan A f39d8de49d36
green-pr is a skill published in the GitHub repository naorpeled/awesome-oss-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 770 once invoked, about $0.0003 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
gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.
squid-implement-night
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.
pr-babysitter
Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
review
Review before merge. Stage-1 spec-compliance gate, then risk-selected Stage-2 review axes from the canonical set. analyst always runs, callers can pin extra always-on axes, and explicit deep review runs the full 16-axis set. Run after /test. Do NOT invoke code-qualities-assessment, doc-accuracy, golden-principles, or…