agentleFS
danielrosehilldanielrosehill/Claude-Security-Auditor-Plugin/skills/compare-audits/SKILL.md

compare-audits

Skill2 starsChanged 7 months agoMITView on GitHub

Use when the user wants to compare two audits and see what changed.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    If no timestamps are given, locate the two most recent reports:

    line 30
  2. Distinctive:

    Read both reports and parse sections (findings, metadata, status).

    line 37
  3. Distinctive:

    Use text diffing and semantic analysis to identify:

    line 39
  4. Distinctive:

    No modifications to audit reports themselves

    line 51

≈ “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

Compare Audits

Diff the two most recent audits for a machine (or two specific timestamps) and surface what changed: new findings, resolved issues, and unchanged items.

When to use

  • Review what security posture changed after a patching cycle
  • Track remediation progress for a known issue
  • Understand the impact of configuration changes
  • Compliance trend analysis

Inputs to gather

  • Machine name (required)
  • Two timestamps (optional; ISO8601 format; defaults to the two most recent reports)

Procedure

  1. Resolve the data directory:
    DATA_DIR="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/security-auditor/data"
    MACHINE_DIR="$DATA_DIR/machines/<machine_name>"
  2. If no timestamps are given, locate the two most recent reports:
    REPORTS=($(ls -t "$MACHINE_DIR/reports"/*/audit-report.md | head -2))
    REPORT_OLD="${REPORTS[1]}"
    REPORT_NEW="${REPORTS[0]}"
  3. Read both reports and parse sections (findings, metadata, status).
  4. Use text diffing and semantic analysis to identify:
    • New findings — present in the new report but not the old
    • Resolved findings — in the old report but not the new
    • Unchanged findings — present in both
    • Status changes — severity or category shifts
  5. Generate a structured markdown delta document with three sections: New, Resolved, Unchanged. Include a summary count (e.g., "5 new findings, 2 resolved, 8 unchanged").

Output / side effects

  • Markdown delta document displayed to the user
  • Optional: save delta to $MACHINE_DIR/deltas/<timestamp>-diff.md for record-keeping
  • No modifications to audit reports themselves

Safety / constraints

  • Comparison relies on consistent report formatting; if reports are formatted inconsistently, diffs may be imprecise.
  • Large diffs (50+ changes) should be summarized with a table of contents.
  • Resolved findings should be flagged as "confirm resolution" — some may be reclassified rather than truly fixed.

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.