write_documentation

A command that creates Markdown documentation for every plugin in a marketplace. It reads marketplace settings and each plugin’s commands and agents to build the documents.

In plain words
What is it for?
Generating one documentation file per plugin with metadata, command examples, agents, use cases, and requirements.
Why use it?
It avoids writing and updating separate plugin documentation by hand.

Command 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 commands/jeffh/claude-plugins/write_documentation
Clone the repo
git clone --depth 1 https://github.com/jeffh/claude-plugins

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 637 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 $0.00010 $0.00637
Opus 5 $0.00005 $0.00318
Sonnet 5 $0.00002 $0.00127
Haiku 4.5 $0.00001 $0.00064

Measured 2d ago against content hash 65b5b8a7be4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write_documentation 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 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.

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/commands/write_documentation.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Plugin Documentation

You are tasked with generating comprehensive documentation for all plugins in this marketplace.

Process:

  1. Read the marketplace configuration:

    • Read .claude-plugin/marketplace.json to get the list of all plugins
    • Extract plugin metadata: name, description, version, author, category
  2. For each plugin, gather information:

    • Read all command files from {plugin}/commands/*.md
    • Read all agent files from {plugin}/agents/*.md
    • Extract frontmatter metadata where available (description, model, etc.)
    • Extract command/agent names, descriptions, and key features from content
  3. Generate documentation file for each plugin:

    • Create docs/{plugin-name}.md for each plugin

    • Use the existing docs/humanlayer.md as a reference format

    • Include:

      • Plugin overview with metadata (category, version, author)
      • Commands section with usage examples
      • Agents section (if applicable) with use cases
      • Requirements section (if applicable)
    • Format:

      # {Plugin Name} Plugin
      
      **Category:** {category}
      **Version:** {version}
      **Author:** {author}
      
      {description}
      
      ## Commands
      
      ### `/{command-name}`
      
      {Description from frontmatter or content}
      
      **Features:**
      - {List key features extracted from content}
      
      **Usage:**
      ```bash
      /{command-name} [args]
      

      Agents

      {agent-name}

      {Description}

      Use when you need to:

      • {Use cases}

      Tools: {List from frontmatter if available}


      Requirements

      {Any special requirements or setup needed}

  4. Update README.md:

    • Read the current README.md
    • Update the "Available Plugins" section to include ALL plugins
    • For each plugin:
      • Add a subsection with plugin name
      • Add a link to its documentation: **[Full Documentation →](docs/{plugin-name}.md)**
      • Add a quick overview listing main commands and agents
    • Ensure formatting is consistent
    • Preserve existing content structure

Read the full file on GitHub · 98 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 · 98 lines · 10 tokens per session scan A 65b5b8a7be4f

Subscribe to this mod's changes

write_documentation is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 17d ago), licensed Apache-2.0. It adds 10 tokens to every session and 637 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 2026-08-30.