audit

audit is a command for Claude Code from ngocsangyem/MeowKit. It costs 0 tokens per session (514 once invoked), scanned A, original, MIT.

A command that performs a broad security audit of a project and creates a security report. It checks the code and infrastructure for issues such as exposed secrets, unsafe database queries, missing authorization, and insecure storage.

In plain words
What is it for?
Use it on the whole project or a chosen file or directory to review application code, infrastructure, authentication, database security, and platform-specific risks.
Why use it?
It brings common security checks together across the project's detected platforms and highlights patterns that could expose data or weaken access control.

Command for Claude Code

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/ngocsangyem/meowkit/audit
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

Wrote 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.

agentmods badge for audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/ngocsangyem/meowkit/audit.svg)](https://agentmods.dev/commands/ngocsangyem/meowkit/audit)
Your own site
<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/audit"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00000 $0.00514
Opus 5 $0.00000 $0.00257
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00051

Measured 4d ago against content hash 2ba715dcf870, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

.claude/commands/mk/audit.md · 60 lines

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 — Full Security Audit

Usage

/audit [optional: specific directory or file]

Behavior

Runs a comprehensive security audit using mk:review (structural) + mk:cso (infrastructure) skills across all platforms detected in the project. Generates a security report.

Execution Steps

  1. Detect platforms. Scan the project to identify which platforms/frameworks are in use (e.g., NestJS, Vue, Swift/iOS, Supabase, PostgreSQL).

  2. Run mk:cso security audit for each detected platform. Check for all blocked patterns defined in rules/security-rules.md:

    • Hardcoded secrets (API keys, passwords, tokens, JWT secrets in source)
    • any type in TypeScript (should use unknown + type guards)
    • SQL queries with string interpolation/template literals
    • localStorage for auth tokens
    • v-html with user-provided content
    • UserDefaults for sensitive data (Swift)
    • Row Level Security disabled or missing
    • Controllers without auth guards (unless explicitly public and documented)
    • process.env access without ConfigService wrapper (NestJS)
    • anon key used in server-side context
    • Disabled certificate validation (Swift)
    • CASCADE DELETE without explicit approval
  3. Classify findings by severity:

    • PASS: No issues found in this area.
    • WARN: Potential issue that should be reviewed but does not block shipping.
    • BLOCK: Critical security issue that MUST be resolved before shipping. No exceptions.
  4. Generate security report. Write to:

    tasks/reviews/YYMMDD-security-report.md
    

    Report includes: per-platform findings, severity per finding, file and line references, remediation guidance.

  5. Print summary. Display findings grouped by severity:

    🐱 Security Audit Results:
    BLOCK (2): [list]
    WARN  (3): [list]
    PASS  (8): [list]
    

Scope

  • If a specific directory or file is provided, audit only that scope.
  • If no scope is provided, audit the entire project.

Read the full file on GitHub · 60 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. 4d ago First seen · 60 lines · 0 tokens per session scan A 2ba715dcf870

Subscribe to this mod's changes

audit is a command published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 514 tokens. 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.