Borrowing it
Nothing to install: this file belongs to PopoverAI/browser-automation. 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/PopoverAI/browser-automation/main/.claude/skills/ci-review-pr/SKILL.mdgit clone --depth 1 https://github.com/PopoverAI/browser-automationWrote 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/popoverai/browser-automation/ci-review-pr)<a href="https://agentmods.dev/skills/popoverai/browser-automation/ci-review-pr"><img src="https://agentmods.dev/badge/skills/popoverai/browser-automation/ci-review-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/popoverai/browser-automation/ci-review-pr"><img src="https://agentmods.dev/badge/skills/popoverai/browser-automation/ci-review-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 | $0.00081 | $0.02070 |
| Opus 5 | $0.00041 | $0.01035 |
| Sonnet 5 | $0.00016 | $0.00414 |
| Haiku 4.5 | $0.00008 | $0.00207 |
Grade A, and why
ci-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 4d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ci-review-pr
You are the reviewer for this pull request, for this round. The PR number was
passed as the skill argument. You run inside a GitHub Actions job whose gh is
authenticated as claude[bot] — every review you submit is a formal review
from the bot, and a formal APPROVE is what stops future rounds (the workflow
skips approved PRs before you are ever invoked, unless a post-approval commit
carries the [re-review] tag in its subject — see step 1).
The engine — the built-in /code-review skill — is how you look at the diff.
It is canonical and not yours to second-guess or evaluate. Everything around it
is yours: what earlier rounds found, how hard to look this time, what the
findings mean, and the verdict.
Your continuity is the PR. There is no session that persists between rounds: prior review bodies, their verdicts, and the unresolved review threads are the complete record, and your review body this round is what the next round gets. Write it accordingly.
The round
1. What you know coming in
gh pr view <N> --json number,title,body,state,headRefOid,baseRefName,author,isDraft
git diff --stat "origin/<baseRefName>...HEAD"
gh api --paginate --slurp "repos/${GITHUB_REPOSITORY}/pulls/<N>/reviews" \
| jq '(add // []) | map(select(.user.login == "claude[bot]") | {state, commit_id, body})'
(gh pr diff has no --stat; the checkout has full history, so plain git
gives the size picture. --paginate --slurp because reviews span pages on a
long-lived PR, and a missed page is a missed approval or a hole in your own
record — piped to jq because gh refuses --slurp together with --jq.)
If state is not OPEN, stop — post nothing. If the latest claude[bot]
review is APPROVED, stop too — unless a commit since that review's
commit_id carries the [re-review] tag in its subject line (the subject
only — a commit body may talk about the tag without requesting a round):
git log --format=%s <approved commit_id>..HEAD | grep -qi '\[re-review\]'
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.
- 4d ago First seen · 170 lines · 81 tokens per session scan A 561256dbe4f2
ci-review-pr is a skill published in the GitHub repository PopoverAI/browser-automation (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,070 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 2026-09-08.
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…