documentation-audit

documentation-audit is a skill for Claude Code from karsten-s-nielsen/mad-scientist-skills. It costs 258 tokens per session (14,527 once invoked), scanned A, original, MIT.

A planning and review method for technical documentation. It checks whether documents are clear, well organized, suited to their readers, complete, and up to date.

In plain words
What is it for?
Use it before writing documentation to plan its structure, or on existing documentation to review its wording, organization, learning paths, repository layout, and freshness.
Why use it?
It helps identify confusing language, missing learning steps, inconsistent structure, and documentation that does not answer readers' questions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the mad-scientist-skills plugin — 10 skills, 4 commands shipped together

Good fit Use it before writing documentation to plan its structure, or on existing documentation to review its wording, organization, learning paths, repository layout, and freshness.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karsten-s-nielsen/mad-scientist-skills/documentation-audit
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.

Any agent
npx skills add karsten-s-nielsen/mad-scientist-skills --skill documentation-audit
Clone the repo
git clone --depth 1 https://github.com/karsten-s-nielsen/mad-scientist-skills

Made for: Claude Code.

Or install mad-scientist-skills, the plugin that ships this one along with the rest of its 10 skills, 4 commands.

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 documentation-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/documentation-audit/github.svg)](https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/documentation-audit)
Your own site
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/documentation-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/documentation-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for documentation-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/documentation-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/documentation-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 258 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 14,527 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00258 $0.14527
Opus 5 $0.00129 $0.07264
Sonnet 5 $0.00052 $0.02905
Haiku 4.5 $0.00026 $0.01453

Measured 12d ago against content hash 039f3ad5c095, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

documentation-audit scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **Verification commands:** After complex configuration steps, can the reader confirm success? (e.g., `curl`, `ping`, health check, expected output) | Lemov #7 (Check for Understanding); Carroll (error recognition) | Hi
plugins/mad-scientist-skills/skills/documentation-audit/SKILL.md · 792 lines

How it starts

The opening of the file, as written. The whole thing — 792 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Audit

A comprehensive documentation audit with two modes and a single tier:

Modes:

  • Planning (before docs exist) — documentation strategy design, content type mapping, learning path architecture, scaffolding strategy
  • Audit (on existing docs) — linguistic precision, structural taxonomy, pedagogical effectiveness, consistency, repository architecture, audience calibration, completeness and freshness

Single tier: Unlike security auditing, documentation evaluation is methodology-based (style guide application, framework classification, cognitive load analysis), not tool-licensed. Vale, markdownlint, and the analytical frameworks are all free/open-source. The value is in the analytical framework, not the scanner.

Core question: "Does this documentation teach effectively?"

Academic foundations

This skill synthesizes seven research threads into a single audit methodology:

  1. Classical Composition (Strunk & White 1918/1959) — Omit needless words, active voice, positive form, specific/concrete language, parallel construction. The foundational linguistic layer beneath all documentation quality.

  2. Enterprise Style Standards (Google Developer Documentation Style Guide; Microsoft Writing Style Guide) — Second person, conditions before instructions, timeless language, inclusive terminology, global accessibility. The enforceable ruleset layer with Vale automation support.

  3. Structural Taxonomy (Procida, Diataxis Framework 2017+; augmented by Good Docs Project) — Four epistemic quadrants (Tutorial, How-To, Reference, Explanation) based on study vs. work and practical vs. theoretical axes. Quadrant pollution detection. Augmented with Good Docs Project templates for changelogs, READMEs, ADRs, troubleshooting, and migration guides.

  4. Cognitive Load Theory (Sweller 1988; Chandler & Sweller 1992; Willingham 2009) — Intrinsic/extraneous/germane load taxonomy. Split-attention effect: code samples separated from their explanations force readers to cross-reference, consuming working memory. Guidance fading effect: novices need explicit scaffolding; discovery-style documentation actively harms new users. Forgetting curve (Ebbinghaus 1885): documentation must support elaborative retrieval, not just initial comprehension.

Read the full file on GitHub · 792 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 792 lines · 258 tokens per session scan A 039f3ad5c095

Subscribe to this mod's changes

documentation-audit is a skill published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 258 tokens to every session and 14,527 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

concept

This skill should be used when the user asks to "create a concept spec", "retrofit a module", "check spec drift", "run drift detection", "design a new module", "wyx concept", or wants to generate, update, or drift-check CONCEPT.md files. Supports retrofit, greenfield, drift detection, and discovery modes.

jlifyio/wyx · 73 tokens

map

This skill should be used when the user asks to "generate architecture map", "visualize spec relationships", "create ARCHITECTURE.md", "show concept dependencies", "wyx map", or wants a Mermaid graph with dependency matrix and data flow paths derived from all wyx specs.

jlifyio/wyx · 60 tokens

audit

This skill should be used when the user asks to "audit spec coverage", "find uncovered modules", "scan for missing specs", "check wyx coverage", "get spec TODO list", "wyx audit", "wyx", or wants a prioritized list of wyx skill commands for uncovered modules. Scans for coverage gaps, pipeline/sync candidates, and…

jlifyio/wyx · 81 tokens

sync

This skill should be used when the user asks to "document sync patterns", "map sync handlers", "create SYNCS.md", "review sync coordination", "wyx sync", or wants to understand how concepts communicate through orchestrated workflows. Produces SYNCS.md coordination maps.

jlifyio/wyx · 58 tokens

pipeline

This skill should be used when the user asks to "create a pipeline spec", "document data transformations", "document data flow", "specify pipeline invariants", "wyx pipeline", or wants to design, retrofit, or discover data pipelines with quality invariants and boundary ownership. Produces PIPELINE.md specs.

jlifyio/wyx · 66 tokens

refactor

Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis. Use this skill when the user wants to improve existing code quality, clean up messy code, restructure, simplify, reduce tech debt, or perform…

zircote-plugins/refactor · 112 tokens