ci-review

ci-review is a skill for Claude Code, Codex from yarlson/yarstack. It costs 50 tokens per session (332 once invoked), scanned A, original, MIT.

A review guide for continuous integration (CI), the automated checks that run when code changes. It examines workflow design and reports issues without changing the workflows.

In plain words
What is it for?
Use it to review triggers, jobs, commands, permissions, secrets, caches, artifacts, test matrices, required checks, releases and deployments, then classify each finding as keep, simplify, merge, fix, remove or owner decision.
Why use it?
It helps find stale, duplicated, ineffective or unsafe automation before it causes misleading checks, wasted work or release problems. It also connects each workflow part to the contract it is meant to protect.

Skill for Claude CodeCodex

Part of the yarstack plugin — 38 skills shipped together

Install

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.

agentmods
npx agentmods add skills/yarlson/yarstack/ci-review
Any agent
npx skills add yarlson/yarstack --skill ci-review
Clone the repo
git clone --depth 1 https://github.com/yarlson/yarstack

Made for: Claude Code, Codex.

Or install yarstack, the plugin that ships this one along with the rest of its 38 skills.

Wrote 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.

agentmods badge for ci-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/yarlson/yarstack/ci-review.svg)](https://agentmods.dev/skills/yarlson/yarstack/ci-review)
Your own site
<a href="https://agentmods.dev/skills/yarlson/yarstack/ci-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/ci-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00332
Opus 5 $0.00025 $0.00166
Sonnet 5 $0.00010 $0.00066
Haiku 4.5 $0.00005 $0.00033

Measured 3d ago against content hash b0bd8741146d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

plugins/yarstack/skills/ci-review/SKILL.md · 24 lines

What it actually says

CI Review

Own automation topology and evidence that each component protects a real contract.

Workflow

  1. Confirm repository scope, comparison target, supported platforms, required-check ownership, and whether remote run evidence is authorized.
  2. Map triggers, jobs, called commands, environments, permissions, secrets, caches, artifacts, release paths, deployment paths, and required checks.
  3. Identify each component's consumer and enforced contract using repository and authorized run evidence.
  4. Find duplicated logic, mismatched versions, ineffective filters, unused matrices, ignored results, retry-masked flakes, dead paths, unjustified permissions, and caches or artifacts without consumers.
  5. Classify actionable items as keep, simplify, merge, fix, remove, or owner decision.
  6. Delegate tool provenance to dependency-review, exploit paths to security-review, infrastructure semantics to infra-review, runtime readiness to rollout-readiness-review, and behavioral test sufficiency to test-gap-review.

For each finding report location, affected contract, evidence, consequence, recommended disposition, change risk, and verification. Recommendations do not authorize implementation.

Do not fetch remote evidence without authority, remove a safety gate on speculation, add scanners for appearance, or rewrite workflows broadly.

Finish with prioritized findings or no-findings, scope, evidence limits, and the smallest advisory cleanup sequence.

Changes

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.

  1. 3d ago First seen · 24 lines · 50 tokens per session scan A b0bd8741146d

Subscribe to this mod's changes

ci-review is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 332 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.

Related

Other skills, from other repositories

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

ci

Generate a GitHub Actions workflow that runs a coder-eval suite as a CI gate or on a schedule, using the published composite action — with the agent runtime, credentials, JUnit output and a score floor wired correctly.

UiPath/coder_eval · 45 tokens

continuous-llm-red-teaming-with-promptfoo

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

adriannoes/awesome-agentic-ai · 56 tokens

hooksmith

Use when designing or reviewing safe Grok Build hooks for linting, tests, formatting, notifications, command guards, lifecycle automation, or project hook trust decisions.

DominikTobureto/awesome-grok-build · 35 tokens

release-cli

Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…

851-labs/tokenmaxxing · 73 tokens

agent-first-planning

Create or revise production-ready SDD plans for agent execution, including clarification, specification, freeze inputs, ownership, budgets, and evidence contracts.

avksp/agent-lifecycle-kit · 33 tokens