docs

A documentation command hub for explaining code, creating documentation, summarizing features or modules, and checking documentation-site SEO.

In plain words
What is it for?
Use it to explore and explain code, generate docs, write high-level overviews for stakeholders, or audit documentation for search-engine visibility.
Why use it?
It helps when code or features are difficult to understand or explain, and when documentation needs to be created or reviewed.

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/smart-ai-memory/empathy-framework/docs
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/empathy-framework

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,779 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 $0.00014 $0.01779
Opus 5 $0.00007 $0.00890
Sonnet 5 $0.00003 $0.00356
Haiku 4.5 $0.00001 $0.00178

Measured yesterday against content hash 5267e3429ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs 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 yesterday.

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/docs.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation

Aliases: /documentation

Documentation operations powered by Socratic agents that help you understand and explain code.

Quick Examples

/docs                         # Interactive menu
/docs explain                 # Get code explanation with context
/docs generate                # Generate documentation
/docs overview                # Feature or module overview
/docs seo                     # SEO audit for documentation site

Discovery

Question:
  header: "Task"
  question: "What documentation task do you need?"
  options:
    - label: "Explain code"
      description: "Understand how code works with guided exploration"
    - label: "Generate docs"
      description: "Create documentation for code or features"
    - label: "Feature overview"
      description: "High-level overview for stakeholders"
    - label: "Optimize SEO"
      description: "Audit and optimize documentation site SEO"

Explain Code

Agent: architect | Workflow: (code exploration)

Understand code through guided exploration, not just reading.

Invoke:

/docs explain                         # Interactive selection
/docs explain src/auth/oauth.py       # Explain specific file
/docs explain "how does caching work" # Explain by concept

The architect agent will:

  1. Ask what you're trying to understand
  2. Explore the code structure together
  3. Guide you through the logic step by step
  4. Ask: "What do you think this function does based on its name?"
  5. Connect patterns to broader concepts
  6. Answer follow-up questions

Philosophy: Instead of "This function authenticates users", you'll hear "Looking at the function name and parameters, what do you think it does? Let's trace through what happens when a user logs in."

Good for:

  • Onboarding to unfamiliar code
  • Understanding complex algorithms
  • Learning patterns used in codebase
  • Preparing to make changes

Generate Documentation

Agent: architect | Workflow: document_gen

Read the full file on GitHub · 281 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. yesterday First seen · 281 lines · 14 tokens per session scan A 5267e3429ad0

Subscribe to this mod's changes

docs is a command published in the GitHub repository Smart-AI-Memory/empathy-framework (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,779 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.