doc

doc is a command for coding agents from MadAppGang/claude-code. It costs 28 tokens per session (3,181 once invoked), scanned A, original, MIT.

A documentation workflow for creating, analyzing, fixing, or validating software documentation such as READMEs, API references, tutorials, and changelogs.

In plain words
What is it for?
It is for generating documentation, assessing its quality, correcting problems, and checking it against documentation standards.
Why use it?
It gives documentation work defined checks and review stages, helping reveal missing, unclear, or outdated information. It also separates analysis from edits and validation.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the dev plugin — 47 skills, 12 commands, 14 agents 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 commands/madappgang/claude-code/doc
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Or install dev, the plugin that ships this one along with the rest of its 47 skills, 12 commands, 14 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/madappgang/claude-code/doc.svg)](https://agentmods.dev/commands/madappgang/claude-code/doc)
Your own site
<a href="https://agentmods.dev/commands/madappgang/claude-code/doc"><img src="https://agentmods.dev/badge/commands/madappgang/claude-code/doc.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,181 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 $0.00028 $0.03181
Opus 5 $0.00014 $0.01590
Sonnet 5 $0.00006 $0.00636
Haiku 4.5 $0.00003 $0.00318

Measured 2d ago against content hash 0fa6019ad942, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • doc — 86% identical, 69 lines differ
plugins/dev/commands/doc.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<user_request> $ARGUMENTS </user_request>

  Before starting, create todo list based on action:
  - GENERATE: Detect type, gather context, generate, validate
  - ANALYZE: Read docs, score quality, detect anti-patterns, report
  - FIX: Analyze issues, apply fixes, validate improvements
  - VALIDATE: Check against best practices, generate report

  **Tasks Ownership Rules:**
  - You (the orchestrator) OWN the Tasks list exclusively
  - Sub-agents (doc-writer, doc-analyzer, doc-fixer) MUST NOT modify Tasks
  - Sub-agents report progress via their return messages only
  - Use 1-based phase numbering (Phase 1, 2, 3...)
  - Maintain exactly ONE todo in_progress at any time
</todowrite_requirement>

<orchestrator_role>
  **You are an ORCHESTRATOR, not IMPLEMENTER.**

  **You MUST:**
  - Use Task tool to delegate ALL documentation work to agents
  - Enforce quality gates between phases
  - Use file-based communication for large outputs

  **You MUST NOT:**
  - Write or edit documentation files directly
  - Skip quality validation
</orchestrator_role>

<approval_gates>
  **User Approval Required for Destructive Changes:**

  Before FIX mode applies changes, you MUST:
  1. Show preview of changes to user
  2. Use AskUserQuestion: "Ready to apply {fix_count} fixes to {file_count} files.
     Preview: {summary}. Proceed? (yes/no)"
  3. Wait for explicit confirmation before delegating to doc-fixer

  Before GENERATE overwrites existing files:
  1. Check if target file exists
  2. If exists, use AskUserQuestion: "File {path} already exists. Overwrite? (yes/no/backup)"
  3. If "backup", save existing file before generating new one
</approval_gates>

<delegation_rules>
  **Agent Delegation:**
  - README generation: doc-writer agent
  - API documentation: doc-writer agent
  - Tutorial creation: doc-writer agent
  - Changelog generation: doc-writer agent
  - Quality analysis: doc-analyzer agent
  - Anti-pattern detection: doc-analyzer agent
  - Issue fixing: doc-fixer agent
  - Voice/style transformation: doc-fixer agent
</delegation_rules>

</critical_constraints>

<action_detection> Analyze $ARGUMENTS to determine action:

**GENERATE** (triggers: "create", "generate", "write", "document", "add docs"):
- Generate new documentation
- Identify doc type: README | API | Tutorial | Changelog | Error | ADR

**ANALYZE** (triggers: "analyze", "check", "score", "review", "audit"):
- Analyze existing documentation quality
- Score against 42-point checklist
- Detect anti-patterns

**FIX** (triggers: "fix", "improve", "update", "refactor"):
- Fix identified issues
- Apply transformations (passive -> active voice)
- Add missing sections

**VALIDATE** (triggers: "validate", "verify", "test"):
- Check against best practices
- Verify examples work
- Check links

</action_detection>

Read the full file on GitHub · 395 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 · 395 lines · 28 tokens per session scan A 0fa6019ad942

Subscribe to this mod's changes

doc is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 3,181 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 2026-09-03.