workflow-review

workflow-review is a command for Claude Code from sigistry/marketplace. It costs 12 tokens per session (688 once invoked), scanned A, original, MIT.

A command that reviews GitHub Actions workflows, which are automated build, test, and deployment instructions. It checks their security settings and how efficiently they run.

In plain words
What is it for?
Use it before or after changing workflow files, or during a periodic audit. It can review one named workflow or all workflow files in the repository.
Why use it?
It can reveal overly broad permissions, unsafe secret handling, mutable action versions, script-injection risks, and settings that make pipelines slow or costly.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter.

Part of the ci-incident-medic plugin — 4 skills, 5 commands, 3 agents shipped together

Good fit Use it before or after changing workflow files, or during a periodic audit. It can review one named workflow or all workflow files in the repository.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sigistry/marketplace/workflow-review
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.

Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Made for: Claude Code.

Or install ci-incident-medic, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 3 agents.

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 workflow-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/sigistry/marketplace/workflow-review/github.svg)](https://agentmods.dev/commands/sigistry/marketplace/workflow-review)
Your own site
<a href="https://agentmods.dev/commands/sigistry/marketplace/workflow-review"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/workflow-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.

agentmods 80×15 button for workflow-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/sigistry/marketplace/workflow-review"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/workflow-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 688 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.00688
Opus 5 $0.00006 $0.00344
Sonnet 5 $0.00002 $0.00138
Haiku 4.5 $0.00001 $0.00069

Measured 8d ago against content hash 5940900cb81a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

workflow-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 8d 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/ci-incident-medic/commands/workflow-review.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a GitHub Actions workflow for SECURITY and SPEED before it causes an incident or a slow, expensive pipeline. Use this on new or changed workflows, or as a periodic audit. $ARGUMENTS is the workflow file to review; if omitted, review every file under .github/workflows/.

Process

Step 1: Load the workflow(s)

  • Read the file named in $ARGUMENTS, or glob .github/workflows/*.yml and *.yaml.
  • Note each job, its runs-on, permissions, concurrency, timeout-minutes, and every uses: action reference and run: step.

Step 2: Audit for security

Draw on the gha-failure-taxonomy skill's permissions-and-secrets.md reference. Check:

Check Risk if violated
Actions pinned to a commit SHA @main/@v4 tags are mutable, supply-chain / tag-hijack risk
Least-privilege permissions: default is often too broad; write scope enables token abuse
pull_request_target usage runs with secrets against untrusted PR code, RCE / secret exfil
Secrets not echoed / interpolated into run: secrets printed to logs bypass masking
No run: ${{ ... }} of untrusted input script injection via PR title/body/branch name
OIDC over long-lived cloud keys static keys leak and never rotate

Step 3: Audit for speed and cost

Check Waste if missing
Dependency caching (actions/cache / setup-* cache) cold installs every run
concurrency with cancel-in-progress stale runs burn minutes on superseded commits
timeout-minutes per job hung jobs run to the 6-hour default cap
Parallelizable jobs not serialized by needless needs: wall-clock time inflated
fail-fast / matrix sized correctly redundant or over-broad matrix legs
Path/branch filters scope the triggers workflow runs on irrelevant changes

Step 4: Report

Produce a findings table ordered by severity, then corrected snippets:

Severity Finding Location (file:line) Fix

Read the full file on GitHub · 50 lines

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. 8d ago First seen · 50 lines · 12 tokens per session scan A 5940900cb81a

Subscribe to this mod's changes

workflow-review is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 688 once invoked, about $0.0001 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.