AAS Core is a local control plane for coding agents that lets them search a large catalogue of skills, choose a stack, validate it, and create a reproducible plan. It is used to assemble and review agent workflows through its CLI, local MCP server, catalogue, plugins, and Workbench. The catalogue add-ons provide the skills, plugins, bundles, and workflows that AAS Core helps agents select and validate.
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.
npx skills add sickn33/agentic-awesome-skills --skill api-designergit clone --depth 1 https://github.com/sickn33/agentic-awesome-skillsWrote 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/skills/sickn33/agentic-awesome-skills/api-designer)<a href="https://agentmods.dev/skills/sickn33/agentic-awesome-skills/api-designer"><img src="https://agentmods.dev/badge/skills/sickn33/agentic-awesome-skills/api-designer/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.
<a href="https://agentmods.dev/skills/sickn33/agentic-awesome-skills/api-designer"><img src="https://agentmods.dev/badge/skills/sickn33/agentic-awesome-skills/api-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00023 | $0.01438 |
| Opus 5 | $0.00012 | $0.00719 |
| Sonnet 5 | $0.00005 | $0.00288 |
| Haiku 4.5 | $0.00002 | $0.00144 |
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.
Copies of this mod
4 near-identical copies found in the catalogue:
- api-designer — 100% identical, 4 lines differ
- api-designer — 100% identical, 4 lines differ
- api-designer — 100% identical, 2 lines differ
- api-designer — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Designer Skill
When to Use
Use this skill when you need generates complete, production-ready REST API endpoint specifications for any system or domain the user describes. Use this skill whenever the user asks about API design, API endpoints, REST APIs, API URLs, or says things like "what endpoints do I need for...", "design an API for...",...
You are an expert API architect.
Ask the user if they want just the endpoints or complete detailed response (Enpoints Only/Detail Design). Do not ask these options if the user has specified the details of his requirement in the input already. If the user says Endpoints Only:
- Output only the endpoints If the user says Detail Design:
- Output complete design as the structure described in this skill.
Output Format
First list down all the endpoints one after another as output then expand each in this exact structure for each endpoint group (resource):
RESOURCE NAME
METHOD /path/to/endpoint
Short description of what this endpoint does. Not more than two lines.
Headers
| Header | Value | Required |
|---|---|---|
Content-Type |
application/json |
Yes |
Authorization |
Bearer <token> |
Yes/No |
X-Api-Key |
<api-key> |
Yes/No |
| (add others as relevant) |
Request Body (omit for GET/DELETE if no body)
{
"field": "type — description",
"field2": "type — description"
}
Success Response — STATUS_CODE Description
{
"field": "value or type"
}
Error Codes
| Code | Meaning |
|---|---|
400 |
Bad Request — invalid or missing fields |
401 |
Unauthorized — missing or invalid token |
403 |
Forbidden — insufficient permissions |
404 |
Not Found |
409 |
Conflict — e.g. duplicate resource |
422 |
Unprocessable Entity — validation failed |
500 |
Internal Server Error |
Rules for Output
- Cover all major resources for the described system. Infer resources if the user doesn't list them.
- Always include CRUD (Create, Read, Update, Delete) where applicable, plus domain-specific actions.
- Use RESTful conventions: plural nouns for collections, nested paths for relationships (e.g.
/hotels/{id}/rooms). - Auth: Default to Bearer token (JWT) for protected routes. Add API key header where relevant (e.g. third-party integrations). Mark public endpoints clearly.
- Request body: Show realistic JSON with field names, types, and brief descriptions. Mark required vs optional fields in comments.
- Responses: Show the success response shape with realistic fields. Always include the HTTP status code.
- Error codes: List the relevant subset per endpoint — don't always paste all 7. Use judgement.
- Pagination: For list endpoints, include query params (
page,limit,sort,filter) and wrap responses in a paginated envelope. - Versioning: Prefix all paths with
/api/v1/unless the user specifies otherwise. - Group endpoints by resource (e.g. "Authentication", "Hotels", "Rooms", "Bookings", "Payments", "Reviews").
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.
- 2d ago Changed · -39 tokens per session ba65d90c01ee
- 4d ago First seen · 168 lines · 62 tokens per session scan A 61d04dca68e2
api-designer is a skill published in the GitHub repository sickn33/agentic-awesome-skills (46,133 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,438 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 2026-09-05.
Other skills, from other repositories
websocket-architect
Design and implement real-time features using WebSockets. Covers Laravel Reverb, Pusher, Socket.io, broadcasting, and live update patterns.
openapi-designer
Design complete OpenAPI 3.1 specifications for RESTful APIs. Covers schemas, security, examples, webhooks, and documentation generation.
codeigniter-builder
Build clean, efficient CodeIgniter 4 applications. Covers MVC structure, database queries, validation, services, and RESTful API development.
laravel-api
Build production-ready RESTful APIs with Laravel. Covers authentication (Sanctum/Passport), versioning, resources, rate limiting, and API testing.
laravel-architect
Design and build robust Laravel applications using best practices, proper architecture patterns, Eloquent ORM, service containers, and Laravel ecosystem tools.
laravel-queues
Implement robust background job processing with Laravel Queues. Covers job design, Redis queues, Laravel Horizon, retry logic, and job monitoring.