doc-audit

doc-audit is a skill for Claude Code from marcoguillermaz/Tierward. It costs 48 tokens per session (3,939 once invoked), scanned A, original, MIT.

A static review of documentation files and their relationships, including relative links, code blocks, placeholders, decisions, and selected framework-specific documentation. It reads files but does not run code or fetch web links.

In plain words
What is it for?
Use it to audit documentation paths, README files, architecture decision records, slash-command names, skill counts, and selected Next.js, Django, or Swift references.
Why use it?
It helps find documentation inconsistencies and leftover template markers before they confuse readers or fall out of sync with the project.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths.

Part of the tierward plugin — 29 skills, 1 command, 1 hook, 1 MCP server shipped together

Good fit Use it to audit documentation paths, README files, architecture decision records, slash-command names, skill counts, and selected Next.js, Django, or Swift references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcoguillermaz/tierward/doc-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 marcoguillermaz/Tierward --skill doc-audit
Clone the repo
git clone --depth 1 https://github.com/marcoguillermaz/Tierward

Made for: Claude Code.

Or install tierward, the plugin that ships this one along with the rest of its 29 skills, 1 command, 1 hook, 1 MCP server.

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 doc-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcoguillermaz/tierward/doc-audit/github.svg)](https://agentmods.dev/skills/marcoguillermaz/tierward/doc-audit)
Your own site
<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/doc-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/doc-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 doc-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/doc-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/doc-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,939 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 $0.00048 $0.03939
Opus 5 $0.00024 $0.01969
Sonnet 5 $0.00010 $0.00788
Haiku 4.5 $0.00005 $0.00394

Measured 10d ago against content hash f2b44cc5b0ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

doc-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 10d 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.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls .claude/skills/ | grep -v '^custom-' | wc -l

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

packages/cli/templates/tier-l/.claude/skills/doc-audit/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope for v1

  • Static analysis only. Grep, file parsing, filesystem reads. Does not fetch URLs, does not run builds, does not execute code examples.
  • No auto-fix. Produces a markdown report; corrections are proposed but never applied.
  • Live link check deferred. HTTP/HTTPS targets are out of scope (flaky, rate-limited). Tracked as DOC-live-links.
  • Semantic drift deferred. Prose obsolescence, deprecation-age reasoning, and doc-bloat judgement are judgment-heavy and out of scope for v1.

Configuration (adapt before first run)

Replace these placeholders:

  • [DOC_PATH] - primary location of user-facing docs (e.g. docs/, documentation/, website/). Always included.
  • [README_PATH] - repository README (usually README.md at project root).
  • [ADR_PATH] - ADR directory if present (e.g. docs/adr/, docs/decisions/). Leave empty if none.

Step 0 - Target resolution

Parse $ARGUMENTS for a target: or mode: token.

Pattern Meaning
target:path:<dir> Audit docs under a specific directory only (e.g. target:path:docs/api)
target:file:<glob> Audit files matching the glob (e.g. target:file:docs/**/*.md)
mode:all / no argument Full audit - README, CHANGELOG, every .md under [DOC_PATH], and ADRs under [ADR_PATH] if set.

STRICT PARSING: derive target ONLY from explicit text in $ARGUMENTS. Do NOT infer from conversation context, recent blocks, or memory.

Announce: Running doc-audit - scope: [FULL | target: <resolved>] - stack: <pending detection>


Step 1 - Stack detection

Detect the primary stack in this priority order. First matching marker wins.

Stack Marker file(s)
node-ts tsconfig.json + package.json
node-js package.json (no tsconfig.json)
python pyproject.toml or requirements.txt or setup.py
go go.mod
rust Cargo.toml
swift Package.swift or *.xcodeproj / *.xcworkspace
kotlin build.gradle.kts or build.gradle with kotlin( plugin
dotnet *.csproj or *.sln
ruby Gemfile
java pom.xml or build.gradle (no Kotlin plugin)
generic None of the above

Read the full file on GitHub · 272 lines

Files

What ships with it

1 file 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. 10d ago First seen · 272 lines · 48 tokens per session scan A f2b44cc5b0ec

Subscribe to this mod's changes

doc-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 3,939 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.