agentleFS
danielrosehilldanielrosehill/Claude-Security-Auditor-Plugin/skills/audit-machine/SKILL.md

audit-machine

Skill2 starsChanged 7 months agoMITView on GitHub

Use when the user wants to run a security audit on a registered machine.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify the machine is registered:

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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, or report-only; default full)
    • quick — fast checks only (10–30 seconds)
    • full — comprehensive scan (5–15 minutes)
    • report-only — regenerate markdown from the most recent raw data

Procedure

  1. 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
  2. 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.
  3. Invoke the audit:
    bash scripts/audit-machine.sh <machine_name> [--quick|--full|--report-only]
  4. The script runs over SSH, writes reports/<timestamp>/audit-report.md, and updates audit-log.json.
  5. 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.json updated 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.