docs-verify

A checker for documentation quality and freshness across a repository. It examines Markdown structure, links, AI-readable file indexes, images, and badge URLs locally or in continuous integration (CI), the automated checks that run when code changes.

In plain words
What is it for?
Use it before a release or in CI to find broken links, missing files, stale `llms.txt` entries, invalid image references, heading problems, and broken badges.
Why use it?
Documentation can become inaccurate or broken even when the code still works, and these problems may reach users unnoticed.

Skill for Claude CodeCodex

Part of the pitchdocs plugin — 16 skills, 15 commands, 4 agents 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 skills/littlebearapps/pitchdocs/docs-verify
Any agent
npx skills add littlebearapps/pitchdocs --skill docs-verify
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/pitchdocs

Made for: Claude Code, Codex.

Or install pitchdocs, the plugin that ships this one along with the rest of its 16 skills, 15 commands, 4 agents.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,263 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 $0.00050 $0.01263
Opus 5 $0.00025 $0.00632
Sonnet 5 $0.00010 $0.00253
Haiku 4.5 $0.00005 $0.00126

Measured 3d ago against content hash e54c75e42c0b, 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 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.

.claude/skills/docs-verify/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Verifier

Philosophy

Generating documentation is a solved problem. Preventing documentation decay is not. This skill validates that generated docs remain accurate, linked, and fresh over time.

Verification Checks

1. Markdown Lint

Check heading hierarchy and structural consistency across all .md files. Verify: heading hierarchy (no H1 > H3 skips — critical for RAG/GEO), single H1 per doc, consistent formatting (trailing whitespace, list markers, blank lines around headings), no bare URLs.

2. Link Validation

Check all internal and external links. Internal: verify target file exists, anchor links match headings, check case-sensitivity (Linux vs macOS). External: check HTTP status, timeout 10s, skip authenticated URLs, flag 404s/5xx. Enhanced detection patterns (case-sensitivity, fragments, redirect chains, nested relative links) in SKILL-reference.md.

3. llms.txt Sync Check

Verify llms.txt references match actual files on disk. Check for: missing files, orphaned docs not listed in llms.txt, description drift (first paragraph check), stale llms-full.txt.

4. Image Validation

Check all image references in Markdown. Verify: file exists on disk, alt text present (flag empty ![]()), absolute URLs for registry-published packages (see SKILL-reference.md for platform URL patterns), file size under 1MB.

5. Freshness Check

Flag stale docs using git log last-modification dates. See SKILL-reference.md for per-file staleness thresholds. Compare against latest commit date, not calendar date — dormant projects with no commits shouldn't trigger warnings.

6. Feature Coverage Sync

Compare README features against actual code using feature-benefits skill extraction. Flag undocumented features (code evidence exists, not in README) and over-documented features (claimed but no code evidence).

7. Badge URL Validation

Verify shields.io badge URLs return valid responses (HTTP 200, not error SVGs). Flag broken badges and outdated URL formats.

Read the full file on GitHub · 89 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. 3d ago First seen · 89 lines · 50 tokens per session scan A e54c75e42c0b

Subscribe to this mod's changes

docs-verify is a skill published in the GitHub repository littlebearapps/pitchdocs (7 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 1,263 once invoked, about $0.0003 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.