agentmods.dev

plugin-audit

A full audit process for checking a skill directory. A skill directory is a folder of instructions and supporting files that an AI coding assistant can use.

In plain words
What is it for?
Use it to inspect a skill's files, validate its structure, detect related commands and components, run checks, and automatically fix non-critical problems.
Why use it?
It finds missing files, structural problems, weak documentation, security issues, and other quality concerns before a skill is shared or released.

Command for Claude Code

25k 2d ago A scan 14 tokens original MIT
View the source file alirezarezvani/claude-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/alirezarezvani/claude-skills/plugin-audit
Clone the repo
git clone --depth 1 https://github.com/alirezarezvani/claude-skills

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,539 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.01539
Opus 5 $0.00007 $0.00770
Sonnet 5 $0.00003 $0.00308
Haiku 4.5 $0.00001 $0.00154

Measured yesterday against content hash cd656f6c9fe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-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 yesterday.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/commands/plugin-audit.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the comprehensive plugin audit pipeline on the skill at $ARGUMENTS. If no argument provided, ask the user for the skill path.

Execute all 8 phases sequentially. Auto-fix non-critical issues. Only prompt the user for critical decisions (external dependencies, security findings, breaking changes).

Phase 1: Discovery

  1. Verify $ARGUMENTS exists and contains SKILL.md. If not, error and stop.
  2. Read SKILL.md frontmatter — extract name, description, Category, Tier.
  3. Detect components:
    • scripts/*.py → Python tools (count them)
    • references/*.md → reference docs (count them)
    • assets/ → templates/samples
    • expected_outputs/ → test fixtures
    • agents/*.md → embedded agents
    • skills/*/SKILL.md → sub-skills (compound skill)
    • .claude-plugin/plugin.json → standalone plugin
    • settings.json → command registrations
  4. Detect domain from path (engineering/, product-team/, marketing-skill/, etc.)
  5. Search commands/ for a .md file matching the skill name.
  6. Display discovery summary.

Phase 2: Structure Validation

Run:

python3 engineering/skill-tester/scripts/skill_validator.py $ARGUMENTS --json

Parse JSON. If score < 75:

  • Auto-fix missing frontmatter fields, missing section headings, missing directories.
  • Re-run. If still < 75, mark as FAIL but continue collecting results.

Phase 3: Quality Scoring

Run:

python3 engineering/skill-tester/scripts/quality_scorer.py $ARGUMENTS --detailed --json

Parse JSON. If score < 60, report improvement roadmap items.

Phase 4: Script Testing

If $ARGUMENTS/scripts/ contains .py files, run:

python3 engineering/skill-tester/scripts/script_tester.py $ARGUMENTS --json --verbose

All scripts must PASS. If any script uses external imports, ask the user whether the dependency is acceptable.

Phase 5: Security Audit

Run:

python3 engineering/skill-security-auditor/scripts/skill_security_auditor.py $ARGUMENTS --strict --json

Read the full file on GitHub · 154 lines

Changes

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.

  1. yesterday First seen · 154 lines · 14 tokens per session scan A cd656f6c9fe7

Subscribe to this mod's changes

plugin-audit is a command published in the GitHub repository alirezarezvani/claude-skills (25,247 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 1,539 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 2026-08-30.

agentic-aianthropic-claudeclaude-aiclaude-codeclaude-code-skillsclaude-skills
Related

Other commands, from other repositories

become

Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue, and instincts.

drobins25/craft · 39 tokens

cycle-start

Activate a cycle and start implementing its stories.

drobins25/craft · 12 tokens

research-verify

Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.

drobins25/craft · 28 tokens

story-continue

Resume an interrupted story from where you left off.

drobins25/craft · 14 tokens

story-archive

Move a story from a cycle back to the backlog.

drobins25/craft · 15 tokens

memory-list

DEPRECATED: Use Serena listmemories instead. Lists recent memories from Forgetful with optional project filtering.

rjmurillo/ai-agents · 21 tokens