ingenious: Command for Claude Code

.claude/commands/ai-config/verify-claude-md.md

verify-claude-md is a command for Claude Code from Insight-Services-APAC/ingenious. It costs 0 tokens per session (431 once invoked), scanned A, original, MIT.

A procedure for checking whether `CLAUDE.md`, an instruction and project-context file for Claude, matches the current codebase.

In plain words
What is it for?
Use it to audit the file against the repository and document important entry points, tests, environment setup, and patterns.
Why use it?
It catches stale commands, paths, dependencies, configuration details, and missing setup information that could mislead an agent.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Insight-Services-APAC/ingenious's own configuration. It tells Claude Code how to work on ingenious itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ingenious configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Insight-Services-APAC/ingenious. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Insight-Services-APAC/ingenious/main/.claude/commands/ai-config/verify-claude-md.md
Clone the repo
git clone --depth 1 https://github.com/Insight-Services-APAC/ingenious

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 verify-claude-md

README.md
[![agentmods](https://agentmods.dev/badge/commands/insight-services-apac/ingenious/verify-claude-md.svg)](https://agentmods.dev/commands/insight-services-apac/ingenious/verify-claude-md)
Your own site
<a href="https://agentmods.dev/commands/insight-services-apac/ingenious/verify-claude-md"><img src="https://agentmods.dev/badge/commands/insight-services-apac/ingenious/verify-claude-md.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 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00431
Opus 5 $0.00000 $0.00216
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 3d ago against content hash b3ede5470352, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verify-claude-md 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 3d 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/ai-config/verify-claude-md.md · 55 lines

What it actually says

Verify CLAUDE.md Accuracy

Audit CLAUDE.md to ensure it accurately reflects the current state of the codebase.

Step 1: Read Current CLAUDE.md

Read and understand all instructions currently in CLAUDE.md.

Step 2: Verify Each Section Against Reality

For each section or instruction in CLAUDE.md:

  1. Repository Context - Verify the description matches actual project purpose and structure
  2. Package Management - Check if the specified package manager (uv, npm, pip, etc.) is actually used
    ls pyproject.toml uv.lock package.json pnpm-lock.yaml yarn.lock 2>/dev/null
    
  3. Build/Run Commands - Test that documented commands actually work
  4. File Structure - Verify any documented paths or directories exist
  5. Dependencies - Check if mentioned tools/libraries are in dependency files
  6. Configuration - Verify any documented config files exist and match descriptions

Step 3: Scan Codebase for Missing Context

Identify important aspects not documented in CLAUDE.md:

  1. Entry Points - Main files, scripts, or commands to run the application
  2. Testing - How to run tests, test frameworks used
  3. Environment Setup - Required environment variables, .env files
  4. Key Patterns - Architectural patterns, coding conventions used consistently
  5. External Services - APIs, databases, or services the code interacts with

Step 4: Check for Outdated Information

Look for:

  • References to deleted files or directories
  • Deprecated commands or workflows
  • Old dependency versions or removed packages
  • Obsolete configuration instructions

Step 5: Update CLAUDE.md

Fix any inaccuracies found:

  • Remove outdated or incorrect information
  • Add missing critical context
  • Update commands that have changed
  • Correct file paths or directory structures

Step 6: Validate Changes

After updates, verify:

  • All documented commands execute successfully
  • All referenced paths exist
  • Instructions are clear and actionable
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. 3d ago First seen · 55 lines · 0 tokens per session scan A b3ede5470352

Subscribe to this mod's changes

verify-claude-md is a command published in the GitHub repository Insight-Services-APAC/ingenious (24 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 431 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 2026-09-04.