api-designer

api-designer is a skill for Claude Code from rtazima/claude-proj-blueprint. It costs 54 tokens per session (1,109 once invoked), scanned A, original, MIT.

A workflow for designing API contracts, the agreed shape of endpoints, data, errors, and conventions, before implementation.

In plain words
What is it for?
Use it to design REST or GraphQL APIs, inspect existing endpoint patterns, define schemas and error codes, check project specifications, and record new conventions in an ADR.
Why use it?
It gives the implementation a clear source of truth and catches missing decisions about resources, authentication, rate limits, pagination, and errors early.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to design REST or GraphQL APIs, inspect existing endpoint patterns, define schemas and error codes, check project specifications, and record new conventions in an ADR.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rtazima/claude-proj-blueprint/api-designer
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.

Any agent
npx skills add rtazima/claude-proj-blueprint --skill api-designer
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

Made for: Claude Code.

Wrote 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.

agentmods badge for api-designer

README.md
[![agentmods](https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/api-designer.svg)](https://agentmods.dev/skills/rtazima/claude-proj-blueprint/api-designer)
Your own site
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/api-designer"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/api-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.01109
Opus 5 $0.00027 $0.00554
Sonnet 5 $0.00011 $0.00222
Haiku 4.5 $0.00005 $0.00111

Measured 7d ago against content hash 07acdb8ba5da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

.claude/skills/api-designer/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Designer

Design API contracts before implementation. Define endpoints, schemas, error codes, and conventions. The contract is the source of truth — implementation follows it.

Rules

  1. Contract first — design the API before writing handler code
  2. Consistency — follow existing API patterns in the project (scan src/ first)
  3. Check specs — read versioning spec (API strategy) and security spec (auth, rate limiting)
  4. Resource-oriented — REST: nouns, not verbs. GraphQL: types and fields, not endpoints
  5. Error handling is part of the design — define error codes and response format upfront
  6. Pagination for lists — never return unbounded collections
  7. ADR for new patterns — if introducing a new API convention, create an ADR

Workflow

Phase 1: Context

  1. Read the PRD requirements for the API
  2. Scan existing endpoints: grep -r "router\|app\.\(get\|post\|put\|delete\|patch\)" src/ (or [SPEC] equivalent)
  3. Read docs/specs/versioning/ for API versioning strategy
  4. Read docs/specs/security/ for auth and rate limiting patterns
  5. Read docs/specs/api/ for API conventions (if exists)
  6. Check memory for past API design decisions

Phase 2: Design

For each endpoint, define:

[METHOD] /api/v{N}/{resource}

Description: What this endpoint does (one line)
Auth: [required | public | specific role]
Rate limit: [requests/window]

Request:
  Headers: [required headers]
  Params: [path and query params with types]
  Body: [schema with required/optional fields]

Response 200:
  {schema}

Response 4xx/5xx:
  {
    "error": {
      "code": "SPECIFIC_ERROR_CODE",
      "message": "Human-readable description"
    }
  }

Phase 3: Conventions checklist

  • Naming: plural nouns for resources (/users, not /user)
  • HTTP methods: GET (read), POST (create), PUT (full update), PATCH (partial), DELETE (remove)
  • Status codes: 200 (ok), 201 (created), 204 (no content), 400 (bad request), 401 (unauthorized), 403 (forbidden), 404 (not found), 409 (conflict), 422 (validation), 429 (rate limited), 500 (server error)
  • Pagination: ?page=1&limit=20 or cursor-based, with total, hasMore in response
  • Filtering: ?status=active&sort=created_at&order=desc
  • Versioning: follows strategy from versioning spec (URL prefix, header, or query)
  • Error format: consistent across all endpoints
  • Dates: ISO 8601 (2026-04-01T12:00:00Z)
  • IDs: consistent format (UUID, nanoid, auto-increment — pick one)

Read the full file on GitHub · 105 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. 7d ago First seen · 105 lines · 54 tokens per session scan A 07acdb8ba5da

Subscribe to this mod's changes

api-designer is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 1,109 once invoked, about $0.0003 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.