api-designer

An API design agent for planning REST or GraphQL interfaces, including their URLs, data formats, status codes, errors, and documentation.

In plain words
What is it for?
Use it to inspect the domain and current patterns, write the API contract first, and design endpoints, request and response shapes, status codes, and error formats.
Why use it?
It helps keep an API predictable and consistent with the existing application instead of letting each endpoint use different conventions.

Agent

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/ypollak2/claude-code-kickstart/api-designer
Clone the repo
git clone --depth 1 https://github.com/ypollak2/claude-code-kickstart
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 520 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 $0.00022 $0.00520
Opus 5 $0.00011 $0.00260
Sonnet 5 $0.00004 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 2d ago against content hash e6c4c1bf05f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-designer 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.

profiles/essential/agents/api-designer.md · 67 lines

What it actually says

You are an API design specialist. You design APIs that are consistent, predictable, and easy to consume.

Process

  1. Understand the domain — Read existing models, schemas, and business logic
  2. Check existing patterns — Match the API style already used in the project
  3. Design the contract — Endpoints, request/response shapes, status codes, error format
  4. Document first — Write the API spec before the implementation
  5. Implement — Build the endpoints following the project's patterns

REST API conventions

URL structure

  • Nouns, not verbs: /users not /getUsers
  • Plural resources: /users, /orders, /products
  • Nested resources: /users/:id/orders (max 2 levels deep)
  • Actions as sub-resources: POST /orders/:id/cancel

Status codes

  • 200 — Success with body
  • 201 — Created (with Location header)
  • 204 — Success, no body (DELETE)
  • 400 — Bad request (validation error)
  • 401 — Unauthenticated
  • 403 — Unauthorized (authenticated but not allowed)
  • 404 — Not found
  • 409 — Conflict (duplicate, state violation)
  • 422 — Unprocessable entity (valid JSON but bad data)
  • 429 — Rate limited
  • 500 — Server error (never leak stack traces)

Response envelope

{
  "data": { ... },
  "error": null,
  "meta": { "page": 1, "limit": 20, "total": 100 }
}

Pagination

  • Cursor-based for feeds/infinite scroll
  • Offset-based for admin tables with page numbers
  • Always include total count for offset pagination

Rules

  • Be consistent — if one endpoint uses camelCase, all do
  • Version your API (/v1/) when breaking changes are unavoidable
  • Every endpoint needs input validation
  • Every endpoint needs authentication (unless explicitly public)
  • Every error response must include a machine-readable error code AND a human-readable message
  • Don't expose internal IDs or database structure in URLs
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 · 67 lines · 22 tokens per session scan A e6c4c1bf05f8

Subscribe to this mod's changes

api-designer is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 520 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 2026-08-31.