Borrowing it
Nothing to install: this file belongs to julien777z/code-review-action. 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/julien777z/code-review-action/main/.agents/skills/ci-review/SKILL.mdgit clone --depth 1 https://github.com/julien777z/code-review-actionWrote 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/julien777z/code-review-action/ci-review)<a href="https://agentmods.dev/skills/julien777z/code-review-action/ci-review"><img src="https://agentmods.dev/badge/skills/julien777z/code-review-action/ci-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/julien777z/code-review-action/ci-review"><img src="https://agentmods.dev/badge/skills/julien777z/code-review-action/ci-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 | $0.00059 | $0.00718 |
| Opus 5 | $0.00030 | $0.00359 |
| Sonnet 5 | $0.00012 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
ci-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 9d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review (CI runner)
Run the code-review skill (included after this section) to review the pull request, adapted for a CI runner. Apply code-review's scope, review lenses, severity rubric, calibration, selectivity bar, and false-positive rules unchanged — the adaptations below only change what the runner already does for you and how you return findings.
The runner owns the GitHub work
The CI runner has already verified eligibility, fetched the diff (embedded in your prompt), and listed previously posted findings (embedded in your prompt); it posts every comment, re-gates the head commit, and resolves stale threads itself. So, overriding the corresponding code-review steps:
- Skip Step 1 (eligibility) and Step 2 (context fetch). Do not discover the PR, check whether it is closed / draft / already reviewed, or fetch the diff — it is in your prompt.
- Skip Step 5 (re-gate) and Step 6 (posting and thread resolution). Do not post a review, resolve threads, or write a summary body — the runner does all of that.
- Never call GitHub. The repository checkout is read context only: read source files and run local
git blame/git logon the changed lines, but do not use any GitHub tool. - In Step 3, drop the prior-PRs lens — it needs GitHub history you should not fetch. Keep the rules, bugs, history, and comments lenses.
- In Step 4, do not fetch existing comments — the prompt already lists prior findings, so re-report any that still apply with the same path and title. Do not cap or drop low findings yourself — emit every finding that clears the severity bar and let the runner apply the low-findings cap.
Run the core review yourself, file by file
Run the core review lenses (rules, bugs, history, comments) yourself in one thread — do not fan them out to sub-agents, which each re-read the diff and rules and delay your first finding. Work through the changed files one at a time, applying those lenses to each file.
The one exception is a separate code-simplification pass: when the runner enables it (its instruction appears below), run that pass in its own sub-agent, in parallel, so the heavier simplification analysis never slows your per-file core review. Emit the sub-agent's suggestions when it returns.
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.
- 9d ago First seen · 31 lines · 59 tokens per session scan A 863a79d23509
ci-review is a skill published in the GitHub repository julien777z/code-review-action (2 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 718 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.
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.
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.
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…