docs-verify

docs-verify is a skill for Claude Code, Codex from changoo89/claude-pilot. It costs 23 tokens per session (1,300 once invoked), scanned B, original, MIT.

A documentation checker validates a three-level documentation system, including line limits, cross-references, and file counts. Cross-references are links from one documentation file to another.

In plain words
What is it for?
It is for checking changed Markdown files, validating referenced paths, and verifying documentation structure after plans or documentation updates.
Why use it?
It helps find broken references and documentation that does not follow the project's size and structure rules before changes are committed.

Skill for Claude CodeCodex

Part of the claude-pilot plugin — 32 skills, 11 commands, 14 agents, 2 MCP servers 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/changoo89/claude-pilot/docs-verify
Any agent
npx skills add changoo89/claude-pilot --skill docs-verify
Clone the repo
git clone --depth 1 https://github.com/changoo89/claude-pilot

Made for: Claude Code, Codex.

Or install claude-pilot, the plugin that ships this one along with the rest of its 32 skills, 11 commands, 14 agents, 2 MCP servers.

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 docs-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/changoo89/claude-pilot/docs-verify.svg)](https://agentmods.dev/skills/changoo89/claude-pilot/docs-verify)
Your own site
<a href="https://agentmods.dev/skills/changoo89/claude-pilot/docs-verify"><img src="https://agentmods.dev/badge/skills/changoo89/claude-pilot/docs-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,300 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00023 $0.01300
Opus 5 $0.00012 $0.00650
Sonnet 5 $0.00005 $0.00260
Haiku 4.5 $0.00002 $0.00130

Measured 5d ago against content hash fbcaac30e65b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

docs-verify scanned grade B 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 5d 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 skillsmediumAgent snooping

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

ACTUAL=$(find .claude/skills -name "SKILL.md" | wc -l | tr -d ' ')
.claude/skills/docs-verify/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: Documentation Verification

Purpose: Validate 3-Tier documentation system compliance - line limits, cross-references, file counts


Quick Start

When to Use

  • After closing plan (/03_close)
  • After running /document
  • Before committing documentation changes

Quick Reference

# Pure bash link check (no external deps)
for file in CLAUDE.md docs/ai-context/*.md; do
  [ -f "$file" ] || continue
  grep -oE '@[^][:space:]]+' "$file" | while read ref; do
    ref_path="${ref#@}"
    [ ! -e "$ref_path" ] && echo "Broken: $ref in $file"
  done
done

Change Detection (MANDATORY FIRST STEP)

Before running verification, check if docs changed:

# Get changed markdown files (with fallback)
CHANGED_MD=$(git diff --name-only HEAD~1 -- "*.md" 2>/dev/null || git diff --name-only -- "*.md" 2>/dev/null || echo "FALLBACK_FULL_VERIFY")

# Fallback: If git diff fails, run full verification
if [ "$CHANGED_MD" = "FALLBACK_FULL_VERIFY" ]; then
    echo "Cannot detect changes, running full verification"
    CHANGED_MD=$(find . -name "*.md" -type f ! -path "*/.git/*" ! -path "*/.trash/*")
fi

if [ -z "$CHANGED_MD" ]; then
    echo "No markdown files changed"
    echo "Skipping documentation verification"
    exit 0
fi

echo "Changed markdown files:"
echo "$CHANGED_MD"

Core Concepts

3-Tier System

Tier 1 (3 files, ≤200 lines each):

  • CLAUDE.md - Project architecture, features, Quick Start
  • docs/ai-context/project-structure.md - Tech stack, file tree
  • docs/ai-context/docs-overview.md - Documentation navigation

Tier 2: Component CONTEXT.md files (unlimited)

Tier 3: Feature-specific CONTEXT.md files


Verification Checks

1. Tier 1 Line Limits (Changed Files Only)

Limit: ≤200 lines per file

TIER1_FILES=(
  "CLAUDE.md"
  "docs/ai-context/project-structure.md"
  "docs/ai-context/docs-overview.md"
)

for file in "${TIER1_FILES[@]}"; do
  # Only check if file was changed
  if echo "$CHANGED_MD" | grep -q "$file"; then
    LINES=$(wc -l < "$file" | tr -d ' ')
    if [ "$LINES" -gt 200 ]; then
      echo "FAIL: $file has $LINES lines (limit: 200)"
      exit 1
    fi
    echo "$file: $LINES lines"
  fi
done

Read the full file on GitHub · 186 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. 5d ago First seen · 186 lines · 23 tokens per session scan B fbcaac30e65b

Subscribe to this mod's changes

docs-verify is a skill published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 1,300 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

harness-diet

Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to reference files, convert rules to path-scoped or skill-triggered loading, and verify zero governance loss with deterministic preservation checks. Use on "harness…

sangrokjung/claude-forge · 140 tokens

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

sangrokjung/claude-forge · 33 tokens

ai-ml-development

AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.

travisjneuman/.claude · 43 tokens

case-interview-practice

Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.

travisjneuman/.claude · 39 tokens

finance

Financial analysis expertise for financial modeling (DCF, LBO, M&A), valuation, financial statement analysis, capital allocation, treasury management, and corporate finance decisions. Use when building financial models, analyzing statements, or making investment decisions.

travisjneuman/.claude · 48 tokens

i18n-localization

Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.

travisjneuman/.claude · 32 tokens