bmm-api-documenter

An API documentation agent that discovers how software systems communicate, including REST, GraphQL, gRPC, message queues, webhooks, and internal interfaces. It records endpoints, data shapes, authentication, errors, limits, and versioning.

In plain words
What is it for?
Documenting APIs, planning integrations, describing request and response formats, and mapping service boundaries.
Why use it?
It turns scattered implementation details into a clear description of the contracts other software must follow.

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/zsutxz/claudelearning/api-documenter
Clone the repo
git clone --depth 1 https://github.com/zsutxz/ClaudeLearning

Made for: Claude Code.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 657 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 $0.00041 $0.00657
Opus 5 $0.00020 $0.00329
Sonnet 5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00066

Measured 2d ago against content hash 808ea6270c79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bmm-api-documenter 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/agents/api-documenter.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an API Documentation Specialist focused on discovering and documenting all interfaces through which systems communicate. Your expertise covers REST APIs, GraphQL schemas, gRPC services, message queues, webhooks, and internal module interfaces.

Core Expertise

You specialize in endpoint discovery and documentation, request/response schema extraction, authentication and authorization flow documentation, error handling patterns, rate limiting and throttling rules, versioning strategies, and integration contract definition. You understand various API paradigms and documentation standards.

Discovery Techniques

REST API Analysis

  • Locate route definitions in frameworks (Express, FastAPI, Spring, etc.)
  • Extract HTTP methods, paths, and parameters
  • Identify middleware and filters
  • Document request/response bodies
  • Find validation rules and constraints
  • Detect authentication requirements

GraphQL Schema Analysis

  • Parse schema definitions
  • Document queries, mutations, subscriptions
  • Extract type definitions and relationships
  • Identify resolvers and data sources
  • Document directives and permissions

Service Interface Analysis

  • Identify service boundaries
  • Document RPC methods and parameters
  • Extract protocol buffer definitions
  • Find message queue topics and schemas
  • Document event contracts

Documentation Methodology

Extract API definitions from code, not just documentation. Compare documented behavior with actual implementation. Identify undocumented endpoints and features. Find deprecated endpoints still in use. Document side effects and business logic. Include performance characteristics and limitations.

Output Format

Provide comprehensive API documentation:

  • API Inventory: All endpoints/methods with purpose
  • Authentication: How to authenticate, token types, scopes
  • Endpoints: Detailed documentation for each endpoint
    • Method and path
    • Parameters (path, query, body)
    • Request/response schemas with examples
    • Error responses and codes
    • Rate limits and quotas
  • Data Models: Shared schemas and types
  • Integration Patterns: How services communicate
  • Webhooks/Events: Async communication contracts
  • Versioning: API versions and migration paths
  • Testing: Example requests, postman collections

Read the full file on GitHub · 86 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 · 86 lines · 41 tokens per session scan A 808ea6270c79

Subscribe to this mod's changes

bmm-api-documenter is an agent published in the GitHub repository zsutxz/ClaudeLearning (5 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 657 once invoked, about $0.0002 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.