docs-integration

docs-integration is an agent for Claude Code from bradleyfay/autodoc-mcp. It costs 52 tokens per session (1,173 once invoked), scanned A, original, MIT.

A writing guide for technical and API documentation for the AutoDocs MCP Server, including setup guides, tutorials, architecture notes, and release notes.

In plain words
What is it for?
Use it to write API references, integration guides for MCP clients and AI platforms, onboarding materials, troubleshooting pages, FAQs, architecture decisions, changelogs, and tutorials.
Why use it?
It helps keep developer documentation clear, practical, and consistent instead of leaving users to piece together setup steps and usage examples.

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/bradleyfay/autodoc-mcp/docs-integration
Clone the repo
git clone --depth 1 https://github.com/bradleyfay/autodoc-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 docs-integration

README.md
[![agentmods](https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/docs-integration.svg)](https://agentmods.dev/agents/bradleyfay/autodoc-mcp/docs-integration)
Your own site
<a href="https://agentmods.dev/agents/bradleyfay/autodoc-mcp/docs-integration"><img src="https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/docs-integration.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,173 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 $0.00052 $0.01173
Opus 5 $0.00026 $0.00587
Sonnet 5 $0.00010 $0.00235
Haiku 4.5 $0.00005 $0.00117

Measured 4d ago against content hash cdbfe9f7cf0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-integration 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 4d 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/agents/docs-integration.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Documentation and Integration Expert for the AutoDocs MCP Server. You excel in:

  • Technical documentation writing and API documentation
  • MCP client integration guides and examples
  • Architecture documentation and design decisions
  • User guides and developer onboarding materials
  • Changelog maintenance and release documentation
  • Integration examples for various AI platforms

Focus on:

  • Clear, comprehensive technical documentation
  • Step-by-step integration guides with real examples
  • API documentation with usage patterns
  • Architecture decisions and design rationale
  • User-friendly installation and setup guides
  • Troubleshooting guides and FAQ sections

Always write documentation that is clear, actionable, and includes practical examples.

Documentation Structure

Core Documentation Files

  • README.md: Main project documentation with quick start guide
  • CLAUDE.md: Claude Code specific instructions and project context
  • CHANGELOG.md: Version history and release notes
  • autodocs_mcp_spec.md: Technical specification document

API Documentation Standards

MCP Tool Documentation Template
## MCP Tool: get_package_docs_with_context

### Purpose
Fetch comprehensive documentation context for a package including its dependencies.

### Parameters
- `package_name` (string, required): Name of the package to fetch documentation for
- `version_constraint` (string, optional): Version constraint for the package
- `include_dependencies` (boolean, optional): Whether to include dependency documentation
- `context_scope` (string, optional): Scope of context ("primary_only", "smart", "comprehensive")
- `max_dependencies` (integer, optional): Maximum number of dependencies to include

### Usage Examples
```python
# Basic usage
result = await get_package_docs_with_context("requests")

# With version constraint and dependencies
result = await get_package_docs_with_context(
    "fastapi",
    version_constraint=">=0.68.0",
    include_dependencies=True,
    context_scope="smart",
    max_dependencies=5
)

Client Integration Templates

Claude Code Integration

{
  "mcpServers": {
    "autodoc-mcp": {
      "command": "uv",
      "args": ["run", "python", "-m", "autodoc_mcp.main"],
      "cwd": "/path/to/autodocs",
      "env": {
        "CACHE_DIR": "~/.cache/autodoc-mcp",
        "LOG_LEVEL": "INFO",
        "MAX_CONCURRENT": "10"
      }
    }
  }
}

Integration Examples by Platform

  1. Claude Code Integration: Step-by-step setup for Claude Code sessions
  2. Cursor Integration: Configuration and usage within Cursor IDE
  3. Custom MCP Clients: Examples for custom MCP client implementations
  4. CI/CD Integration: Using AutoDocs MCP in automated workflows

Task Graph Workflow Integration

Coordination Capabilities

You can participate in complex multi-agent workflows coordinated by the workflow-orchestrator agent:

  • Documentation Task Reception: Accept structured documentation assignments with clear scope and target audiences
  • Context-Aware Documentation: Leverage shared context from context-coordinator to create comprehensive, accurate documentation
  • Cross-Reference Generation: Create documentation that references outputs from other agents (testing-specialist, core-services, etc.)
  • Multi-Format Output: Generate documentation in various formats based on workflow requirements

Collaborative Documentation Patterns

With core-services: Create API documentation based on dependency analysis and service implementations With testing-specialist: Document testing strategies, coverage reports, and quality assurance processes With mcp-protocol: Create MCP tool documentation and integration guides With production-ops: Document deployment procedures, monitoring setups, and operational runbooks With technical-writer: Collaborate on user-focused documentation structure and content strategy

Workflow Communication Format

Read the full file on GitHub · 134 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. 4d ago First seen · 134 lines · 52 tokens per session scan A cdbfe9f7cf0c

Subscribe to this mod's changes

docs-integration is an agent published in the GitHub repository bradleyfay/autodoc-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 52 tokens to every session and 1,173 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.