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-security/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-security)<a href="https://agentmods.dev/skills/wintermeyer/heinzel/heinzel-security"><img src="https://agentmods.dev/badge/skills/wintermeyer/heinzel/heinzel-security/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-security"><img src="https://agentmods.dev/badge/skills/wintermeyer/heinzel/heinzel-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 65 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Tool Misuse · line 91 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00137 | $0.01164 |
| Opus 5.5 | $0.00055 | $0.00466 |
| Sonnet 5.5 | $0.00027 | $0.00233 |
| Haiku 4.5 | $0.00014 | $0.00116 |
Grade A, and why
heinzel-security 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
heinzel-security
Security configuration audit for a server or the local machine. Never run automatically — only on explicit user request. The whole of the heinzel first-connection onboarding pipeline still applies before any of this runs.
Workflow
- Load overrides. Before running any check, apply the full
heinzel rule-override chain (later wins):
memory/custom-rules/heinzel-security.mdif present (global custom overrides for this skill —## Add:,## Replace:,## Remove:prefixes perCLAUDE.md).memory/servers/<hostname>/memory.mdfor context (services, legitimate external bindings, VPN role).memory/servers/<hostname>/rules.mdif present (per-server rule overrides — same prefixes as above, highest precedence). Note:memory/custom-rules/all.mdis already loaded by the CLAUDE.md session-start preflight — do not re-read it.
- Run checks in 2–3 parallel batches for speed — not one massive batch. If a single parallel tool call errors, Claude Code cancels sibling calls, so grouping limits blast radius. Put commands with complex quoting (awk, sed) in their own batch so a quoting mistake does not cancel simple commands.
- Probe shape: no taboo word as data (the guard denies the
whole batch), no
!(zsh mangles it over SSH), and report what you do not recognize instead of printing only what you expect. The System Accounts check inreferences/user-accounts.mdshows all three. - Select checks per the references below. Use the preferred method when privileges allow; fall back to the unprivileged method otherwise.
- Emit the report using the format in
references/report-format.md. - Do NOT update
memory.md. These are config observations, not state changes. Memory tracks what is installed and running, not security posture details. - Log the summary to the system journal and mirror to the
local changelog per
rules/changelog.md:
What ships with it
11 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.
- references/file-permissions.md 1.8 KB
- references/firewall-nftables-docker.md 4.6 KB
- references/firewall.md 1.6 KB
- references/intrusion-prevention.md 339 B
- references/kernel-os.md 919 B
- references/listening-services.md 1.1 KB
- references/macos-security.md 345 B
- references/report-format.md 1.2 KB
- references/ssh.md 3.8 KB
- references/unprivileged.md 1.2 KB
- references/user-accounts.md 2.0 KB
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.
- 1mo ago Changed · +3 lines 20cde117124e
- 1mo ago Changed · +1 lines cd449629d815
- 1mo ago First seen · 97 lines · 137 tokens per session scan A 3b4631868a57
heinzel-security is a skill published in the GitHub repository wintermeyer/heinzel (101 stars, last pushed 6d ago), licensed MIT. It adds 137 tokens to every session and 1,164 once invoked, about $0.0005 per session on Opus 5.5. 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-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-code-connect-components
Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For…
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-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…