docs-verify

A documentation checker that scans Markdown files for broken links, outdated content, formatting problems, missing images, and mismatches in llms.txt. llms.txt is a file that lists documentation for AI tools to read.

In plain words
What is it for?
Use it before releases or in continuous integration to check links, freshness, Markdown structure, images, and documentation listings.
Why use it?
Documentation can become inaccurate or disconnected from the codebase as files move and projects change. This command finds those problems and can return CI output or enforce a minimum quality score.

Command

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/littlebearapps/pitchdocs/docs-verify
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/pitchdocs
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 645 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 $0.00015 $0.00645
Opus 5 $0.00008 $0.00322
Sonnet 5 $0.00003 $0.00129
Haiku 4.5 $0.00002 $0.00064

Measured 2d ago against content hash 638a057801ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-verify 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 2d 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.

commands/docs-verify.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/docs-verify

Validate that documentation remains accurate, linked, and fresh over time. Catches broken links, stale content, and llms.txt drift before they reach users.

Behaviour

  1. Load the docs-verify skill for the verification checks
  2. Scan all Markdown files in the repository
  3. Run the requested checks (or all checks if no arguments)
  4. Report findings with severity levels

Arguments

  • No arguments: Run all checks and report findings
  • links: Link validation only (internal + external)
  • freshness: Staleness check only (git blame-based)
  • ci: All checks, output in CI-friendly format (exit code 1 on errors, file:line format)
  • score: Run all checks and output the quality score only
  • --min-score N: Fail if the quality score falls below N (useful for CI gates)

Checks Performed

Check What It Catches
Markdown lint Heading hierarchy skips, single H1 rule, formatting
Link validation Broken relative paths, dead external URLs, missing anchors
llms.txt sync Files referenced in llms.txt that no longer exist, orphaned docs
Image validation Missing image files, empty alt text, relative URLs for npm/PyPI projects
Freshness Docs not updated in 90+ days (configurable via git blame)
Feature coverage README features vs actual code — undocumented and over-documented
Badge URLs Shields.io badges returning errors or outdated formats
Token audit Skill files exceeding recommended token budgets
Quality score Numeric 0–100 score across 6 dimensions with grade band and actionable fix suggestions

Output Format

📋 Documentation Verification: [project-name]

Markdown Lint:       ✓ 12 files checked, 0 issues
Link Validation:     ⚠ 45 links checked, 2 warnings, 1 error
llms.txt Sync:       ✓ 12/12 references valid
Image Validation:    ⚠ 3 images checked, 1 warning
Freshness:           ⚠ 2 files stale (>90 days)
Feature Coverage:    ✓ 8/10 features documented (80%)
Badge URLs:          ✓ 5/5 badges valid

Errors (must fix):
  ✗ README.md:89 — broken link: docs/guides/migration.md (file not found)

Warnings (should fix):
  ⚠ docs/guides/deployment.md — stale: last updated 95 days ago
  ⚠ README.md:15 — relative image path, will break on npm

📊 Quality Score: 74/100 (C — Needs work)
   Top fix: README.md:89 broken link → fixes +5 points

Read the full file on GitHub · 68 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. 2d ago First seen · 68 lines · 15 tokens per session scan A 638a057801ff

Subscribe to this mod's changes

docs-verify is a command published in the GitHub repository littlebearapps/pitchdocs (7 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 645 once invoked, about $0.0001 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 2026-08-31.