audit-docs

audit-docs is a command for Claude Code from FlorianBruniaux/ctxharness. It costs 41 tokens per session (1,298 once invoked), scanned A, original, MIT.

A repository documentation checker that reviews files such as the README, changelog, contributor guide, and documentation folders against 30 stated practices. It produces a scored report and can suggest missing files.

In plain words
What is it for?
Use it to review documentation structure, quick-start instructions, version files, examples, automation notes, and other repository guidance.
Why use it?
It helps find incomplete, inconsistent, or hard-to-use project documentation before a release or when a new contributor joins.

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/florianbruniaux/ctxharness/audit-docs
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/ctxharness

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-docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/florianbruniaux/ctxharness/audit-docs.svg)](https://agentmods.dev/commands/florianbruniaux/ctxharness/audit-docs)
Your own site
<a href="https://agentmods.dev/commands/florianbruniaux/ctxharness/audit-docs"><img src="https://agentmods.dev/badge/commands/florianbruniaux/ctxharness/audit-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,298 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 $0.00041 $0.01298
Opus 5 $0.00020 $0.00649
Sonnet 5 $0.00008 $0.00260
Haiku 4.5 $0.00004 $0.00130

Measured 4d ago against content hash 99e66879ab35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-docs 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/audit-docs.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Audit

Score this repository's documentation against 30 criteria across 5 categories.

Usage

/audit-docs              # Audit only, generate markdown report
/audit-docs --generate   # Audit + propose creating missing files

Phase 1: Discovery

ls -la README.md VERSION CHANGELOG.md CLAUDE.md CONTRIBUTING.md LICENSE .gitignore 2>/dev/null
ls -la docs/ guide/ 2>/dev/null
find examples/ -type f 2>/dev/null | head -10
grep -n "Quick Start\|Getting Started\|Installation" README.md 2>/dev/null | head -3
grep -c "\!\[.*\](.*badge.*)" README.md 2>/dev/null || echo "0"
head -20 CHANGELOG.md 2>/dev/null
cat VERSION 2>/dev/null

Phase 2: Evaluation (30 Criteria)

Score each as: ✅ (present) / ⚠️ (partial) / ❌ (missing)

Category 1: Root Files (8 criteria, weight ×3)

# Criterion Detection
1.1 README.md with Quick Start < 40 lines `head -50 README.md
1.2 VERSION (single semver line) cat VERSION matches ^\d+\.\d+\.\d+$
1.3 CHANGELOG.md (Keep a Changelog format) Has ## [Unreleased] or ## [x.y.z] sections
1.4 CLAUDE.md (project instructions) File exists with > 10 lines
1.5 CONTRIBUTING.md File exists
1.6 LICENSE File exists
1.7 .gitignore (categorized sections) Has comment sections # Category
1.8 Functional badges in README At least 2 badge images

Category 2: Documentation Structure (7 criteria, weight ×2)

# Criterion
2.1 Dedicated docs/ or guide/ folder
2.2 Metadata in docs (YAML frontmatter)
2.3 Table of Contents with anchors
2.4 TL;DR or Quick Start section
2.5 Time estimates mentioned
2.6 Cheatsheet available
2.7 Examples in dedicated folder (> 3 files)

Category 3: Machine-Readable (5 criteria, weight ×1)

# Criterion
3.1 llms.txt or equivalent
3.2 Index YAML/JSON < 3K tokens
3.3 Line numbers in doc references
3.4 Version synchronized across files
3.5 Keywords/tags in frontmatter

Read the full file on GitHub · 159 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 · 159 lines · 41 tokens per session scan A 99e66879ab35

Subscribe to this mod's changes

audit-docs is a command published in the GitHub repository FlorianBruniaux/ctxharness (21 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,298 once invoked, about $0.0002 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.