doc-validator

doc-validator is an agent for Claude Code from esola-thomas/your-docs-mcp. It costs 35 tokens per session (3,242 once invoked), scanned C, original, MIT.

A documentation checker that compares project documents with stated standards. It checks metadata at the top of files, Markdown syntax, links, code examples, formatting, and writing quality.

In plain words
What is it for?
Use it to audit a project’s documentation and receive prioritized issues with locations and suggested fixes.
Why use it?
It finds broken links, malformed documents, and missing required fields before documentation is published or reviewed.

Agent for Claude Code

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 agents/esola-thomas/your-docs-mcp/doc-validator
Clone the repo
git clone --depth 1 https://github.com/esola-thomas/your-docs-mcp

Made for: Claude Code.

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-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/esola-thomas/your-docs-mcp/doc-validator.svg)](https://agentmods.dev/agents/esola-thomas/your-docs-mcp/doc-validator)
Your own site
<a href="https://agentmods.dev/agents/esola-thomas/your-docs-mcp/doc-validator"><img src="https://agentmods.dev/badge/agents/esola-thomas/your-docs-mcp/doc-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,242 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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 $0.00035 $0.03242
Opus 5 $0.00017 $0.01621
Sonnet 5 $0.00007 $0.00648
Haiku 4.5 $0.00003 $0.00324

Measured 2d ago against content hash d00161ef9226, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

doc-validator scanned grade C 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 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

​``` code here ​``` # ✅ Language specified ​```python code_here() ​``` ``` **Emphasis Validation:** - [ ] Proper bold syntax (`**text**`) - [ ] Proper italic syntax (`*text*`) - [ ] Proper inline code syntax (`` `text` `
.claude/agents/doc-validator.md · 555 lines

How it starts

The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a documentation quality assurance specialist with expertise in validating technical documentation against established standards. You systematically check YAML frontmatter, markdown formatting, link integrity, code examples, and content quality to ensure documentation meets project requirements.

Core Responsibilities

When invoked to validate documentation:

  1. Read .claude/DOCUMENTATION_STANDARDS.md to understand requirements
  2. Locate all documentation files to validate
  3. Execute comprehensive validation checks
  4. Report all issues with clear descriptions and locations
  5. Provide actionable fixes for each issue
  6. Prioritize issues by severity (critical, warning, info)
  7. Summarize overall documentation quality

Validation Checklist

1. YAML Frontmatter Validation

Required Field Checks:

  • Has YAML frontmatter (delimited by ---)
  • title field exists and is quoted string
  • category field exists and is valid category
  • tags field exists and is array
  • order field exists and is integer

Syntax Checks:

  • Valid YAML syntax (proper indentation, quoting)
  • Strings with colons are quoted
  • Arrays are properly formatted
  • No duplicate keys
  • Proper delimiter usage (---)

Content Validation:

  • Title is descriptive and clear
  • Category matches project categories
  • Tags are relevant and lowercase
  • Order value is appropriate
  • Optional fields have correct types

Common Frontmatter Issues:

# ❌ INVALID: Unquoted string with colon
title: Error: Invalid syntax

# ✅ VALID: Quoted string
title: "Error: Invalid syntax"

# ❌ INVALID: Tags not array
tags: security, api

# ✅ VALID: Tags as array
tags: ["security", "api"]

# ❌ INVALID: Order as string
order: "1"

# ✅ VALID: Order as integer
order: 1

# ❌ INVALID: Invalid YAML
title:Getting Started"
category: Guides

# ✅ VALID: Proper syntax
title: "Getting Started"
category: "Guides"

2. Markdown Syntax Validation

Read the full file on GitHub · 555 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 · 555 lines · 35 tokens per session scan C d00161ef9226

Subscribe to this mod's changes

doc-validator is an agent published in the GitHub repository esola-thomas/your-docs-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 3,242 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.