Borrowing it
Nothing to install: this file belongs to wintermeyer/heinzel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wintermeyer/heinzel/main/.claude/skills/heinzel-fleet-audit/SKILL.mdgit clone --depth 1 https://github.com/wintermeyer/heinzelWrote 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/wintermeyer/heinzel/heinzel-fleet-audit)<a href="https://agentmods.dev/skills/wintermeyer/heinzel/heinzel-fleet-audit"><img src="https://agentmods.dev/badge/skills/wintermeyer/heinzel/heinzel-fleet-audit/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.
<a href="https://agentmods.dev/skills/wintermeyer/heinzel/heinzel-fleet-audit"><img src="https://agentmods.dev/badge/skills/wintermeyer/heinzel/heinzel-fleet-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.00974 |
| Opus 5 | $0.00056 | $0.00487 |
| Sonnet 5 | $0.00022 | $0.00195 |
| Haiku 4.5 | $0.00011 | $0.00097 |
Grade A, and why
heinzel-fleet-audit 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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
heinzel-fleet-audit
Cross-server policy audit. Heinzel knows every host
individually but has nothing that holds hosts against each
other. This skill closes that gap by probing the same set of
settings on every server in memory/servers/ and rendering a
side-by-side comparison so silent drift becomes visible.
No configuration changes. The audit never alters any host's configuration. The only write is a single audit-trail line to each host's system journal (step 6 below). Acting on findings is a separate step (heinzel-housekeeping for per-host fixes, or manual edits with explicit user approval).
Never run automatically — only on explicit user request.
When to use
- "Run a fleet audit"
- "Vergleiche die Policies auf allen Servern"
- "Drift check across the fleet"
- After fixing a config bug on one host: "which other hosts have the same problem?"
Do NOT auto-invoke for generic phrases like "check my servers" — that maps to single-host housekeeping.
Workflow
-
Discover hosts. List directories under
memory/servers/whose name resolves to a real host (skip placeholders likeserver1.example.comand192.168.64.20unless the user names them explicitly). The user may pass an explicit subset as arguments — in that case audit only those. -
Resolve SSH users. Read
memory/user.mdfor the per-host SSH user. Hosts without a mapping go on a "skipped: no SSH user known" list (do not prompt — just report). -
Probe in parallel. For each in-scope host, run the probes from
references/probes.mdin a single batched SSH command. Usessh -o BatchMode=yes -o ConnectTimeout=5. Hosts that time out or refuse the connection go on a "skipped: unreachable" list. -
Render comparison. Build one table per probe category using the format in
references/output-format.md. Hosts are columns, settings are rows. Cells that differ across columns get visual emphasis. -
Surface drift. After the tables, emit a short "Drift detected" section that lists each disagreement and the recommended fix (link to the relevant rule or skill). Do not change anything.
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.
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.
- 9d ago First seen · 107 lines · 112 tokens per session scan A e97a28a1ebab
heinzel-fleet-audit is a skill published in the GitHub repository wintermeyer/heinzel (91 stars, last pushed 22d ago), licensed MIT. It adds 112 tokens to every session and 974 once invoked, about $0.0006 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.
Other skills, from other repositories
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
figma-create-design-system-rules
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…
figma-generate-design
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the…
figma-generate-library
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. This skill teaches WHAT to build and in WHAT ORDER — it…
figma-use
MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call. NEVER call usefigma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in…