create-api

A command that scaffolds a new API endpoint, meaning a server entry point that receives a request and returns a response. It creates the route, handler, types, tests, and server wiring based on the existing project.

In plain words
What is it for?
For inspecting the server, routes, handlers, types, and environment settings, then creating an endpoint with optional database integration. It can create a feature branch when run from the main branch.
Why use it?
It avoids manually piecing together an endpoint and helps the new code follow the server's current structure and conventions.

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/thedecipherist/claude-code-mastery-project-starter-kit/create-api
Clone the repo
git clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kit

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,995 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 $0.00019 $0.02995
Opus 5 $0.00010 $0.01497
Sonnet 5 $0.00004 $0.00599
Haiku 4.5 $0.00002 $0.00299

Measured 2d ago against content hash bf2fe0330ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-api 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/create-api.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create API Endpoint

Scaffold a production-ready API endpoint for: $ARGUMENTS

Step 0 — Auto-Branch (if on main)

Before creating any files, check the current branch:

git branch --show-current

Default behavior (auto_branch = true in claude-mastery-project.conf):

  • If on main or master: automatically create a feature branch and switch to it:
    git checkout -b feat/api-<resource-name>
    
    Report: "Created branch feat/api-<resource> — main stays untouched."
  • If already on a feature branch: proceed
  • If not a git repo: skip this check

To disable: Set auto_branch = false in claude-mastery-project.conf. When disabled, warn and ask the user before proceeding on main.

Step 1 — Gather Context

Before scaffolding, read the current project:

  1. Read src/server.ts (or src/server.js, src/index.ts) — understand the server setup
  2. Scan src/routes/ — check for existing route patterns to follow
  3. Scan src/handlers/ — check for existing handler patterns
  4. Scan src/types/ — check for existing type patterns
  5. Read .env.example — check for database config

If --no-db is in the arguments, skip database integration. Otherwise, use StrictDB if it's installed, or the native MongoDB driver if not (always through the adapter, never Mongoose).

Step 2 — Create Files

Generate these files for the resource:

File 1: src/types/<resource>.ts — Types first (they're the spec)

/** Database document shape */
export interface <Resource>Doc {
  _id: string;
  // Add fields based on the resource
  createdAt: Date;
  updatedAt: Date;
}

/** API request body for creating a resource */
export interface Create<Resource>Body {
  // Fields the client sends (NO _id, NO timestamps)
}

/** API request body for updating a resource */
export interface Update<Resource>Body {
  // Partial fields the client can update
}

/** API response shape (what the client receives) */
export interface <Resource>Response {
  id: string;
  // Mapped from the doc — NEVER expose _id directly
  createdAt: string;
  updatedAt: string;
}

Read the full file on GitHub · 386 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 · 386 lines · 19 tokens per session scan A bf2fe0330ea9

Subscribe to this mod's changes

create-api is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 2,995 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.