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.
git clone --depth 1 https://github.com/mertjane/awesome-claude-commandsWrote 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.
[](https://agentmods.dev/commands/mertjane/awesome-claude-commands/api-doc)<a href="https://agentmods.dev/commands/mertjane/awesome-claude-commands/api-doc"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/api-doc.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01076 |
| Opus 5 | $0.00020 | $0.00538 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
api-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate API Documentation
Analyze the project's backend source code to produce a complete OpenAPI 3.0.0 specification and save it to docs/openapi.yaml (or the path provided in $ARGUMENTS if specified).
Step 1 — Detect Framework and Project Info
Read package.json:
- Extract
name,version,descriptionfields - Detect the framework from
dependencies:express→ Express.jsfastify→ Fastifykoa→ Koa.js@hapi/hapi→ Hapi.js- None found → treat as Generic HTTP API
Step 2 — Read the Main Entry File
Search for and read the first match from (in order):
src/index.js, src/app.js, src/server.js, index.js, app.js, server.js
Detect:
- PORT value (e.g.
process.env.PORT || 3000) - Route prefixes (e.g.
app.use("/api/v1", ...)→ base path/api/v1) - Auth middleware usage (e.g.
verifyToken,authenticate,authMiddleware,passport) - All registered router prefixes
Step 3 — Discover Route Files
Use Glob to find route files:
**/routes/**/*.{js,ts}**/router/**/*.{js,ts}**/controllers/**/*.{js,ts}**/api/**/*.{js,ts}(exclude node_modules)
Read each route file and extract:
HTTP Methods and Paths:
router.get("/path", ...)→ GET /pathrouter.post("/path", ...)→ POST /pathrouter.put("/:id", ...)→ PUT /{id}router.patch("/:id", ...)→ PATCH /{id}router.delete("/:id", ...)→ DELETE /{id}
Path Parameters:
:id→{id}(integer, required):slug→{slug}(string, required):userId→{userId}(string, required)
Request Body:
- Look at
req.bodydestructuring:const { email, password } = req.body - If validation exists (joi, zod, yup), read the schema
- Extract field names and types
Response Structure:
- Look at
res.json({...})output shapes - Status codes:
res.status(201),res.status(404), etc. - Extract response object fields
Auth Protection:
- Does the route handler have middleware?
router.get("/", authMiddleware, handler) - If the middleware name relates to auth → this endpoint is protected
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.
- 7d ago First seen · 128 lines · 41 tokens per session scan A 93b117d2f121
api-doc is a command published in the GitHub repository mertjane/awesome-claude-commands (2 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,076 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.
Other commands, from other repositories
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
setup
Interactive auth setup wizard. Choose provider, configure OAuth, email, generate schema, create UI components — all in one command.
content-model
Generate Alfresco content model XML and Spring context file from requirements.
handoff
Thin wrapper (GETSITREP-10) — generating sitrep/HANDOFF.md (archiving the previous one first), tailoring to a human or AI audience, and committing all live in getsitrep handoff.
implement-graphql-api
Command "implement-graphql-api" from qdhenry/Claude-Command-Suite, covering implement graphql api and instructions.