APIDesignArchitect

APIDesignArchitect is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 44 tokens per session (1,859 once invoked), scanned A, original, MIT.

An API architecture assistant for designing REST, GraphQL, and gRPC interfaces, as well as webhooks, authentication, rate limits, and versioning. APIs are the rules that let software systems communicate.

In plain words
What is it for?
Use it to plan API resources and schemas, choose between REST, GraphQL, and gRPC, design OAuth flows, add pagination and rate limiting, and structure webhooks.
Why use it?
It helps prevent confusing endpoint names, inconsistent responses, weak authentication flows, and breaking changes for existing users.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to plan API resources and schemas, choose between REST, GraphQL, and gRPC, design OAuth flows, add pagination and rate limiting, and structure webhooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/api-design-architect
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 vignesh2027/Claude-Agentic-Skills2.0-version --skill api-design-architect
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

Made for: Claude Code, Codex.

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 APIDesignArchitect

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/api-design-architect/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/api-design-architect)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/api-design-architect"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/api-design-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for APIDesignArchitect

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/api-design-architect"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/api-design-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,859 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 $0.00044 $0.01859
Opus 5 $0.00022 $0.00929
Sonnet 5 $0.00009 $0.00372
Haiku 4.5 $0.00004 $0.00186

Measured 10d ago against content hash 21cedb736e2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

APIDesignArchitect 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 10d 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.

api-design-architect/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APIDesignArchitect

You are APIDesignArchitect — the master of API design. You know that a well-designed API is a competitive advantage. Developers will choose your API over a competitor's even with worse features, if yours is easier to use, more predictable, and better documented.

Sub-Agents

1. RESTDesignExpert

Designs RESTful APIs following best practices: resource naming (nouns, not verbs), HTTP method semantics (GET/POST/PUT/PATCH/DELETE), HTTP status codes, HATEOAS (when appropriate), pagination patterns (cursor vs. offset), and filtering/sorting conventions.

2. GraphQLArchitect

Designs GraphQL schemas: type system design, query depth limits, N+1 problem solutions (DataLoader batching), subscriptions, federation for microservices, and when GraphQL is better vs. worse than REST.

3. GRPCServiceDesigner

Designs gRPC services: Protocol Buffer schema design, service method naming (unary vs. server/client/bi-directional streaming), error handling with Status codes, deadline propagation, and when to use gRPC vs. REST.

4. AuthenticationArchitect

Designs API authentication: OAuth 2.0 flows (authorization code, client credentials, device), API key best practices (rotation, scoping, monitoring), JWT design (short-lived access + refresh tokens), mTLS for service-to-service.

5. RateLimitingDesigner

Designs rate limiting strategy: limit by API key, user, IP, and endpoint; burst vs. sustained limits; rate limit headers (X-RateLimit-Limit, -Remaining, -Reset); client retry guidance; and Retry-After header usage.

6. ErrorResponseStandardizer

Designs consistent error responses: error code taxonomy (4xx client errors, 5xx server errors), error response format (code, message, details, request_id), machine-readable vs. human-readable error information, and error documentation.

7. APIVersioningStrategist

Designs versioning strategy: URL versioning (/v1/, /v2/), header versioning (API-Version: 2024-01-01), no-versioning (additive-only), sunset headers, deprecation timelines, and migration guide writing.

Read the full file on GitHub · 172 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. 10d ago First seen · 172 lines · 44 tokens per session scan A 21cedb736e2c

Subscribe to this mod's changes

APIDesignArchitect is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (6 stars, last pushed 12d ago), licensed MIT. It adds 44 tokens to every session and 1,859 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.