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 agentmods add skills/ashtonian/llm-init/api-designnpx skills add ashtonian/llm-init --skill api-designgit clone --depth 1 https://github.com/ashtonian/llm-initWhat 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 | $0.00010 | $0.00963 |
| Opus 5 | $0.00005 | $0.00481 |
| Sonnet 5 | $0.00002 | $0.00193 |
| Haiku 4.5 | $0.00001 | $0.00096 |
Grade A, and why
api-design 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Contract Design Skill
Interactive workflow for designing API contracts. Produces OpenAPI 3.1 specifications and optionally generates typed client code.
Workflow
Step 1: Identify Resources and Relationships
Analyze the feature requirements to identify:
- Resources: Core entities that need API endpoints (e.g., Users, Projects, Invoices)
- Relationships: How resources relate to each other (e.g., Users belong to Organizations, Projects have Members)
- Actions: Non-CRUD operations that need endpoints (e.g., activate, archive, export)
Output: Resource inventory table with relationships.
Step 2: Design URL Structure
For each resource, design the URL following .claude/rules/api-design.md:
GET /api/v1/{resources} # List (paginated)
POST /api/v1/{resources} # Create
GET /api/v1/{resources}/{id} # Get by ID
PUT /api/v1/{resources}/{id} # Full update
PATCH /api/v1/{resources}/{id} # Partial update
DELETE /api/v1/{resources}/{id} # Delete
For nested resources: /api/v1/{parent}/{parentId}/{children}
For actions: POST /api/v1/{resources}/{id}/{action}
Output: Complete URL structure table with HTTP methods and descriptions.
Step 3: Define Request/Response Schemas
For each endpoint, define:
- Request body (POST, PUT, PATCH): Field names, types, required/optional, constraints
- Response body: Data envelope structure, field names, types
- Query parameters (GET list): Pagination, filtering, sorting options
Rules:
- Field names:
snake_casein JSON - IDs: UUIDs
- Dates: ISO 8601 (
2024-01-15T10:30:00Z) - Enums: lowercase strings
- Include
tenant_idin response (from server context, never from request)
Output: Schema definitions for all request/response types.
Step 4: Specify Error Responses
For each endpoint, define error responses using RFC 7807 Problem Details:
- 400: What constitutes a bad request?
- 401: How is authentication checked?
- 403: What permissions are required?
- 404: When is the resource not found?
- 409: What conflicts can occur?
- 422: What business rule validations exist?
- 429: What rate limits apply?
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 First seen · 131 lines · 10 tokens per session scan A 6034cea9f5a9
api-design is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 963 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…