docs-audit

A documentation audit command that checks documentation coverage, important files, internal links, code examples, and freshness. It reports separate scores and specific findings, such as undocumented exports, missing files, broken links, or stale pages.

In plain words
What is it for?
Use it to review JSDoc coverage, README and project-file completeness, Markdown links, documentation code blocks, and how closely docs match the current source.
Why use it?
It shows where documentation is incomplete, incorrect, or out of date instead of requiring a manual review of every page and code example.

Command

Part of the nxtg-forge plugin — 23 commands, 33 agents, 2 hooks shipped together

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/nxtg-ai/forge-plugin/docs-audit
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

Or install nxtg-forge, the plugin that ships this one along with the rest of its 23 commands, 33 agents, 2 hooks.

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 1,215 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 $0.01215
Opus 5 $0.00000 $0.00607
Sonnet 5 $0.00000 $0.00243
Haiku 4.5 $0.00000 $0.00121

Measured 3d ago against content hash 54d3826126e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-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 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.

docs/commands/docs-audit.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:docs-audit

Comprehensive documentation quality audit covering JSDoc coverage, key file inventory, link validation, code example verification, and freshness scoring.

Level L1 Vibe Coder
Category Documentation
Syntax /forge:docs-audit

What It Does

/forge:docs-audit is the deep documentation quality assessment. It runs five audit dimensions: coverage analysis (what percentage of exported symbols have JSDoc), file inventory (which key files like README, CHANGELOG, CONTRIBUTING, and LICENSE exist), link validation (do internal markdown links point to real files), code example validation (do code blocks in docs reference existing functions and files), and freshness scoring (how recently were docs updated relative to source).

The output is a multi-score report: Coverage %, Completeness %, Freshness %, and Link Health %, plus an overall average. Each dimension lists specific findings -- undocumented exports, missing key files, broken links, stale pages -- so you know exactly what to fix. The issues are severity-ranked and the recommendations are prioritized by impact.

Without this command, auditing documentation quality means manually checking for broken links, eyeballing JSDoc coverage by scrolling through code, and hoping someone notices when key files are missing. /forge:docs-audit automates the entire audit and gives you concrete scores to track over time.

Syntax & Options

/forge:docs-audit

This command takes no arguments. It always runs the full five-dimension audit.

When to Use It

  • Pre-release quality gate: Ensure documentation meets a minimum quality bar before tagging a release.
  • New maintainer onboarding: Audit the project's documentation to identify what a new contributor would need.
  • Quarterly documentation review: Run it periodically to catch documentation decay.

For a quick health check without the full audit, use /forge:docs-status. For fixing issues found by the audit, use /forge:docs-update.

Read the full file on GitHub · 123 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. 3d ago First seen · 123 lines · 0 tokens per session scan A 54d3826126e7

Subscribe to this mod's changes

docs-audit is a command published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,215 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 2026-08-31.

Related

Other commands, from other repositories

review-synthesize

Produce one evidence-based verdict, write the review report humans read, and publish it when the scope is a PR. You are read-only: never modify project files or commit; your only write outside the artifacts directory is the PR comment below. Read-only extends past the repository: a falsifying command creates its own…

coleam00/Archon · 0 tokens

triage

Confirm whether the work item still names real current work, choose the kind of reasoning owed next, and stop. Write the decisive evidence and handoff to $ARTIFACTSDIR/triage.md. You assess and route only: the repository must be exactly as you found it when you finish. No one watches the run; the report and your…

coleam00/Archon · 0 tokens

paul:help

Show available PAUL commands and usage guide.

ChristopherKahler/paul · 13 tokens

verify

Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…

yonatangross/orchestkit · 92 tokens

paul:verify

Guide manual user acceptance testing of recently built features.

ChristopherKahler/paul · 14 tokens

auto

Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…

yonatangross/orchestkit · 99 tokens