zizmor

zizmor is a command for Claude Code from nitinjain999/platform-skills. It costs 175 tokens per session (6,195 once invoked), scanned A, original, Apache-2.0.

A security audit for GitHub Actions workflows, reusable actions, Dependabot settings, and pre-commit configuration. GitHub Actions are automated jobs that run inside a repository.

In plain words
What is it for?
Use it to audit workflow security, apply supported fixes, define policies, set severity-based CI checks, and upload findings in SARIF format.
Why use it?
It finds ways automation could expose credentials, accept unsafe input, use unpinned code, or grant excessive permissions.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the platform-skills plugin — 1 skill, 43 commands shipped together

Good fit Use it to audit workflow security, apply supported fixes, define policies, set severity-based CI checks, and upload findings in SARIF format.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/nitinjain999/platform-skills/zizmor
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/nitinjain999/platform-skills

Made for: Claude Code.

Or install platform-skills, the plugin that ships this one along with the rest of its 1 skill, 43 commands.

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 zizmor

README.md
[![agentmods](https://agentmods.dev/badge/commands/nitinjain999/platform-skills/zizmor/github.svg)](https://agentmods.dev/commands/nitinjain999/platform-skills/zizmor)
Your own site
<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/zizmor"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/zizmor/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 zizmor

Your own site · 80×15
<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/zizmor"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/zizmor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 175 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,195 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 $0.00175 $0.06195
Opus 5 $0.00088 $0.03097
Sonnet 5 $0.00035 $0.01239
Haiku 4.5 $0.00017 $0.00619

Measured 10d ago against content hash 775fe704a169, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

zizmor 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 10d 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.

commands/zizmor.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit GitHub Actions workflows for security findings — before an attacker reads them for you.

Read references/zizmor.md before responding. It contains bootstrap steps, the full 41-audit catalogue with persona and online gating, zizmor.yml schema and discovery rules, exit-code semantics, auto-fix blast radius, and the CI and pre-commit templates.

This command is interactive by default. With no arguments, run the three-layer wizard below. Never dump a raw zizmor invocation and stop — the useful output is a triaged verdict, not a finding list.

Ownership boundary (enforced at the menu)

Question Authoritative command
"Is this workflow valid?" (syntax, schema, shell bugs) /platform-skills:github-actions — actionlint
"Is this workflow safe?" (injection, permissions, pinning) this command
"Is my action.yml well designed?" /platform-skills:composite-actions
"How do I keep these SHA pins current?" /platform-skills:renovate
"Is there a misconfig in my Terraform / Helm / Dockerfile?" /platform-skills:checkov
"Does this image or dependency have CVEs?" /platform-skills:trivy
"How do I sign images / generate an SBOM?" /platform-skills:supply-chain

Zizmor and actionlint are complements. A workflow can be perfectly valid and still hand an attacker a shell. When the user asks for "workflow checks" without qualifying, run both and say which tool produced which finding.


Mode dispatch

Parse the first word of $ARGUMENTS as the mode. When $ARGUMENTS is empty, run the three-layer interactive wizard.

Mode What it does
scan Default-persona audit of the current repo — the everyday run
audit Deep sweep: --persona=auditor --min-confidence=low, all collectors, online
fix --fix=safe (or all on request), show the diff, re-audit what remains
triage Walk existing findings one at a time → fix / inline-ignore / config-ignore / remap / disable
config Generate or repair .github/zizmor.yml — pinning policy, allowlists, suppressions
ci Emit the GitHub Actions workflow — SARIF alerts, hard-fail gate, or both
precommit Add the zizmor-pre-commit hook and explain the offline caveat
explain Explain one audit id or one finding, and how to fix it properly
(empty) Three-layer interactive wizard

Read the full file on GitHub · 396 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. 10d ago First seen · 396 lines · 175 tokens per session scan A 775fe704a169

Subscribe to this mod's changes

zizmor is a command published in the GitHub repository nitinjain999/platform-skills (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 175 tokens to every session and 6,195 once invoked, about $0.0009 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 2026-08-30.