Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add danielrosehill/Claude-Security-Auditor-Plugin/plugin install security-auditorWrote 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/danielrosehill/claude-security-auditor-plugin/audit-machine)<a href="https://agentmods.dev/skills/danielrosehill/claude-security-auditor-plugin/audit-machine"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-security-auditor-plugin/audit-machine.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 | $0.00018 | $0.00524 |
| Opus 5 | $0.00009 | $0.00262 |
| Sonnet 5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
audit-machine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Machine
Execute a security audit over SSH on a single registered machine. The audit checks for configuration drift, hardening gaps, policy compliance, and other findings. Output is timestamped and appended to the machine's audit log.
When to use
- User wants to run a fresh security scan on a machine
- Periodic audit checkpoints before/after changes
- Compliance validation for a specific target
Inputs to gather
- Machine name (required; must be registered)
- Audit depth (optional;
quick,full, orreport-only; defaultfull)quick— fast checks only (10–30 seconds)full— comprehensive scan (5–15 minutes)report-only— regenerate markdown from the most recent raw data
Procedure
-
Resolve the data directory:
DATA_DIR="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/security-auditor/data" REPO_BASE="$DATA_DIR" export REPO_BASE -
Verify the machine is registered:
cd /home/daniel/repos/github/my-repos/Claude-Security-Auditor-Plugin bash scripts/list-machines.sh <machine_name> --json | jq .Fail gracefully if the machine is not found.
-
Invoke the audit:
bash scripts/audit-machine.sh <machine_name> [--quick|--full|--report-only] -
The script runs over SSH, writes
reports/<timestamp>/audit-report.md, and updatesaudit-log.json. -
Extract the report path from the output and read the markdown for a brief summary. Display path and key findings to the user.
Output / side effects
- New timestamped report in
${CLAUDE_USER_DATA}/security-auditor/data/machines/<machine-name>/reports/<ISO8601-timestamp>/audit-report.md audit-log.jsonupdated with entry for this run- Return the report path and a one-paragraph summary of critical findings
Safety / constraints
- Audit may require root privileges on the target for comprehensive checks.
- Network latency can affect runtime; full audits may take 10+ minutes on slow links.
- The script reads system files on the target; ensure proper credentials and permissions.
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.
- 6d ago First seen · 60 lines · 18 tokens per session scan A e3a4447deb9a
audit-machine is a skill published in the GitHub repository danielrosehill/Claude-Security-Auditor-Plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 524 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…