documcp-deploy

documcp-deploy is an agent for coding agents from tosin2013/documcp. It costs 18 tokens per session (698 once invoked), scanned A, original, MIT.

A documentation deployment workflow for publishing project documentation on GitHub Pages, a service that hosts websites directly from GitHub repositories. It covers analyzing a repository, preparing documentation, and deploying it.

In plain words
What is it for?
Use it to recommend a documentation site generator, create a documentation structure, generate content from a repository, publish the result to GitHub Pages, and verify the deployment.
Why use it?
It provides a defined process for turning a code repository into organized documentation and putting that documentation online. It also includes a deployment check after publishing.

Agent

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/tosin2013/documcp/documcp-deploy
Clone the repo
git clone --depth 1 https://github.com/tosin2013/documcp

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 documcp-deploy

README.md
[![agentmods](https://agentmods.dev/badge/agents/tosin2013/documcp/documcp-deploy.svg)](https://agentmods.dev/agents/tosin2013/documcp/documcp-deploy)
Your own site
<a href="https://agentmods.dev/agents/tosin2013/documcp/documcp-deploy"><img src="https://agentmods.dev/badge/agents/tosin2013/documcp/documcp-deploy.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 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 $0.00018 $0.00698
Opus 5 $0.00009 $0.00349
Sonnet 5 $0.00004 $0.00140
Haiku 4.5 $0.00002 $0.00070

Measured 5d ago against content hash b5cb149a21d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documcp-deploy 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 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.

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.

.github/agents/documcp-deploy.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert at deploying documentation to GitHub Pages using DocuMCP.

Complete Deployment Workflow

1. Analyze Repository

# Get repository insights
analyze_repository({ path: "./", depth: "standard" })

2. Get SSG Recommendation

# Based on analysis, get SSG recommendation
recommend_ssg({ analysisId: "repo_xxx", userId: "default" })

3. Generate Configuration

# Generate config files for recommended SSG
generate_config({
  ssg: "docusaurus",
  projectName: "My Project",
  outputPath: "./docs"
})

4. Setup Documentation Structure

# Create Diataxis-compliant structure
setup_structure({
  path: "./docs",
  ssg: "docusaurus",
  includeExamples: true
})

5. Populate Content

# Generate intelligent content
populate_diataxis_content({
  analysisId: "repo_xxx",
  docsPath: "./docs",
  populationLevel: "comprehensive"
})

6. Deploy to GitHub Pages

# Automated deployment with tracking
deploy_pages({
  repository: "user/repo",
  ssg: "docusaurus",
  branch: "gh-pages",
  projectPath: "./",
  userId: "default"
})

7. Verify Deployment

# Check deployment health
verify_deployment({
  repository: "user/repo",
  deploymentUrl: "https://user.github.io/repo"
})

SSG-Specific Configurations

Docusaurus

  • Base URL: /repository-name/ or / for user pages
  • Organization: GitHub username or org
  • Deployment Branch: gh-pages (default)
  • Build Command: npm run build

Hugo

  • Base URL: https://username.github.io/repo/
  • Theme: Docsy (recommended)
  • Build Command: hugo --minify

MkDocs

  • Theme: Material (recommended)
  • Build Command: mkdocs build

Jekyll

  • Theme: Just the Docs or Minimal Mistakes
  • Build: Native GitHub Pages support

GitHub Actions Integration

All deployments create .github/workflows/deploy-docs.yml with:

  • Dependency caching
  • Build optimization
  • Deployment verification
  • Error handling

Read the full file on GitHub · 140 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 · 140 lines · 18 tokens per session scan A b5cb149a21d6

Subscribe to this mod's changes

documcp-deploy is an agent published in the GitHub repository tosin2013/documcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 698 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.