Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.claude/skills/pr-review-readiness/SKILL.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/pr-review-readiness)<a href="https://agentmods.dev/skills/rajbos/ai-engineering-fluency/pr-review-readiness"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/pr-review-readiness/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/rajbos/ai-engineering-fluency/pr-review-readiness"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/pr-review-readiness.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 | $0.00078 | $0.04714 |
| Opus 5.5 | $0.00031 | $0.01886 |
| Sonnet 5.5 | $0.00016 | $0.00943 |
| Haiku 4.5 | $0.00008 | $0.00471 |
Grade A, and why
pr-review-readiness 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 yesterday.
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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Readiness Skill
Answers one question: is it safe to read this PR's review state right now, or is GitHub's automatic Copilot review still in flight for the current head commit? Acting too early is the failure mode this skill prevents — an agent that checks a PR seconds after a push can see stale or incomplete review state and conclude "no findings" when the review simply hasn't posted yet, or act on comments left against an older commit.
This is a lookup skill, not a workflow: run the check, get one of the outcomes below — one safe-to-act outcome, and several distinct not-ready outcomes (still running, a draft or dismissed review, a failed or cancelled run, inconclusive pagination) that all mean the same thing in practice — don't act yet — but for different reasons worth telling apart when you're deciding whether to reschedule, investigate, or just retry.
When to Use This Skill
- Before treating "no new review comments" as a real signal while driving a PR to green
- Before replying to or resolving a thread that belongs to the matched native Copilot review, to confirm that review is current for
sha— this gate establishes only that; it says nothing about whether an arbitrary human or older-bot thread targets the current commit, which needs its own check - On any PR-activity webhook event that might race a fresh push against GitHub's review
- Any time you're about to read a PR's review state right after a push
Two unrelated review-ish signals — don't confuse them
This repository's PRs carry two independent families of check runs that both look like "review" but answer different questions:
- GitHub's native automatic Copilot PR review — the actual line-level
review comments this skill gates on. It posts as the
copilot-pull-request-reviewer[bot]GitHub App and is backed by a real check run literally namedcopilot-pull-request-reviewer, with the standard lifecyclequeued→in_progress→completed. In the PR timeline UI, "Review requested due to automatic review settings" is this check being queued, and "Copilot started reviewing... [View session]" is it running — that link is this same check run's own Actions job URL. - This repository's own CI-driven review — a separate check run from
this repo's own GitHub Actions workflows:
Review risk(thepr-risk-reviewskill). It is unrelated to #1 and never answers "is the automatic review done" — it is explicitly advisory-only and never blocks merge.
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.
- yesterday First seen · 303 lines · 78 tokens per session scan A e712a504f2d5
pr-review-readiness is a skill published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 4,714 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…