command-auditor

An agent that reviews slash-command configuration files, which are Markdown files defining reusable commands for a coding agent. It checks whether their descriptions, arguments, context, and permissions are appropriate.

In plain words
What is it for?
Use it to audit command files, check their quality against best practices, and review security-related settings for commands that modify files, use Git, deploy software, or call other agents.
Why use it?
It helps find unclear instructions, missing argument guidance, missing context, or overly broad tool access before a command is used.

Agent

Part of the create-plugins plugin — 12 skills, 6 commands, 9 agents shipped together

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 agents/vibe-marketer/plugins-and-skills/command-auditor
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 agents.

Per session 234 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,291 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 $0.00234 $0.01291
Opus 5 $0.00117 $0.00646
Sonnet 5 $0.00047 $0.00258
Haiku 4.5 $0.00023 $0.00129

Measured 2d ago against content hash 78cc08238934, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-auditor 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 2d 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.

create-plugins/agents/command-auditor.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<evaluation_areas>

  • description: Clear, specific description of what the command does. No vague terms.
  • allowed-tools: Present when appropriate for security. Properly formatted as array or bash patterns.
  • argument-hint: Present when command uses arguments. Clear indication of expected format.

<contextual_judgment> Simple commands (single action, no state):

  • Dynamic context may not be needed
  • Minimal tool restrictions may be appropriate
  • Brief prompts are fine

State-dependent commands (git, environment-aware):

  • Missing dynamic context is a real issue
  • Tool restrictions become important

Security-sensitive commands (git push, deployment, file modification):

  • Missing tool restrictions is critical
  • Should have specific patterns, not broad access

Delegation commands (invoke skills/agents):

  • allowed-tools: Skill(skill-name) or allowed-tools: Task is appropriate
  • Prompt should focus on what to pass to the skill, not duplicate skill logic </contextual_judgment>

<output_format>

Audit Results: [command-name]

Read the full file on GitHub · 164 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. 2d ago First seen · 164 lines · 234 tokens per session scan A 78cc08238934

Subscribe to this mod's changes

command-auditor is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 234 tokens to every session and 1,291 once invoked, about $0.0012 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.