github-actions-reviewer

A review workflow for GitHub Actions, the automation system built into GitHub repositories. It examines all workflows together because their settings and assumptions can affect one another.

In plain words
What is it for?
Auditing existing GitHub Actions workflows, checking their consistency and security, and producing an analysis and improvement plan.
Why use it?
It helps uncover inconsistent action versions, unsafe permissions, missing controls for overlapping runs, and incomplete file or path filters that can cause security or CI problems.

Skill for Claude CodeCodex

Part of the infra-review plugin — 7 skills, 7 commands, 5 agents, 2 hooks 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/infraspecdev/tesseract/github-actions-reviewer
Any agent
npx skills add infraspecdev/tesseract --skill github-actions-reviewer
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract

Made for: Claude Code, Codex.

Or install infra-review, the plugin that ships this one along with the rest of its 7 skills, 7 commands, 5 agents, 2 hooks.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 858 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 $0.00043 $0.00858
Opus 5 $0.00022 $0.00429
Sonnet 5 $0.00009 $0.00172
Haiku 4.5 $0.00004 $0.00086

Measured 2d ago against content hash 2c0b8d99aebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-actions-reviewer 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 2d 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.

infra-review/skills/github-actions-reviewer/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Actions Reviewer

Overview

Structured review of GitHub Actions workflows for consistency, security, and operational best practices.

Core principle: Workflows in the same repo form a system. Review them as a group, not individually — inconsistencies between workflows cause the hardest-to-debug CI failures.

When to Use

  • Reviewing CI/CD workflows in any repository
  • Auditing workflow permissions and security posture
  • Checking for version drift across workflows
  • After adding a new workflow to verify consistency with existing ones
  • Periodic hygiene check on GitHub Actions setup
  • Re-grading after improvements (creates fresh analysis and plan)

When NOT to Use

  • Debugging a single workflow run failure (use GitHub's run logs instead)
  • Writing new workflows from scratch (this skill reviews existing ones)
  • Non-GitHub CI systems (Jenkins, GitLab CI, CircleCI)
  • Reviewing application code that happens to be triggered by workflows

Workflow

Read All Workflows + Config -> Evaluate Against Checklist -> Write analysis.md -> Write plan.md -> Ask User to Confirm -> (proceed: Execute / stop: Done / edit: revise plan.md)

Critical Rules

  1. ALWAYS write analysis.md and plan.md — Even on re-reviews or when no issues found. Never skip file output.
  2. ALWAYS ask user before executing — Never auto-proceed to implementation.
  3. Show the user what was written — Summarize key findings after writing files.

Steps

1. Read All Workflows and Config

Read every file in .github/workflows/ plus related config: release tooling configs (release-please-config.json, .releaserc.json, etc.), versions.tf, .tflint.hcl, package.json.

2. Evaluate Against Checklist

Run through the 8-point checklist covering version consistency, plugin/config alignment, permissions, concurrency control, path filters, reusable patterns, action pinning, and secrets handling. See checklist.md for detailed criteria, examples, and red flags.

3. Write analysis.md

Read the full file on GitHub · 80 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 80 lines · 43 tokens per session scan A 2c0b8d99aebe

Subscribe to this mod's changes

github-actions-reviewer is a skill published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 858 once invoked, about $0.0002 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

multi-agent-release-manager

Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.

chromium/chromium · 27 tokens

dsh-web-pre-push-checks

Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.

zhu1090093659/dsh-web · 45 tokens

babysit

Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…

kirodotdev/KiroCrew · 137 tokens

azsdk-common-pipeline-analysis

Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…

Azure/azure-sdk-for-net · 192 tokens

harness-setup

HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.

Chachamaru127/claude-code-harness · 57 tokens

managing-github-actions-secrets

Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API token, package registry credential, deploy key, or any value referenced via ${{ secrets. }} in .github/workflows/.

PostHog/posthog-foss · 67 tokens