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.
npx agentmods add skills/fmind/dot/zizmornpx skills add fmind/dot --skill zizmorgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/zizmor)<a href="https://agentmods.dev/skills/fmind/dot/zizmor"><img src="https://agentmods.dev/badge/skills/fmind/dot/zizmor.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00722 |
| Opus 5 | $0.00017 | $0.00361 |
| Sonnet 5 | $0.00007 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
zizmor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zizmor
Static security audit for .github/workflows/*.yml and composite actions; actionlint checks correctness, zizmor checks what an attacker could do with the workflow, and github-actions wires both into check:actions.
Commands
zizmor --offline .github/workflows/ # default gate: no network, no token needed
zizmor --offline --min-severity medium .github/ # bound noise in large repositories
zizmor --offline --persona pedantic .github/ # stricter pass before a release
zizmor --offline --format sarif .github/ > zizmor.sarif
zizmor --offline --collect dependabot --strict-collection . # audit .github/dependabot.yml too: schema plus rules such as dependabot-cooldown
GH_TOKEN="$(gh auth token)" zizmor .github/ # online audits (impostor commits, ref confusion)
zizmor --fix .github/workflows/ # experimental; the default mode applies only safe fixes, review the diff
Common Findings and Fixes
| Finding | Fix |
|---|---|
template-injection |
Never expand ${{ ... }} inside run:; pass values through env: and read $VAR. |
artipacked |
actions/checkout with persist-credentials: false unless a later step must push. |
excessive-permissions |
Top-level permissions: contents: read; widen per job only (id-token: write for OIDC). |
unpinned-uses |
Pin actions to a major tag at minimum; .github/zizmor.yml records the accepted policy. |
cache-poisoning |
Disable caches (cache: false) in release and deploy jobs that produce signed artifacts. |
dangerous-triggers |
Avoid pull_request_target and workflow_run unless the job never checks out PR code. |
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.
- 2d ago First seen · 49 lines · 35 tokens per session scan A 1ca5952a10cc
zizmor is a skill published in the GitHub repository fmind/dot (4 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 722 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 2026-09-03.
Other skills, from other repositories
mise
Configure pinned mise tools and canonical install, format, check, test, build, and watch tasks shared by hooks and CI.
dependabot
Automated dependency updates using GitHub Dependabot — configuration, ecosystem mapping, and validation.
github-actions
Configure GitHub Actions CI/CD so workflows run the same mise format, check, test, and build gate as local hooks; lint with actionlint and Zizmor; use keyless deploy templates.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.