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/ocbunknown/fastapi-claude-template/api-clientnpx skills add ocbunknown/fastapi-claude-template --skill api-clientgit clone --depth 1 https://github.com/ocbunknown/fastapi-claude-templateWhat 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 | $0.00102 | $0.04217 |
| Opus 5 | $0.00051 | $0.02108 |
| Sonnet 5 | $0.00020 | $0.00843 |
| Haiku 4.5 | $0.00010 | $0.00422 |
Grade A, and why
api-client 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrating an external HTTP API
An external API integration is two objects, not one:
- Client (
infrastructure/http/clients/<vendor>/) — thin HTTP wrapper. Returns raw vendor-shaped Pydantic models that mirror the API's JSON 1:1. No business logic, no transformation, no domain types. - Service (
application/v1/services/<vendor>.py) — holds a Client via its port, calls it, and maps raw responses into applicationResulttypes. All business rules (enum mapping, filtering, multi-call orchestration) live here. The service never returnsCreate*Type/Update*Type— persistence shape is the use case's job.
Use cases depend on the Service. In rare cases (debug/proxy/admin) they can depend on the Client port directly. Examples below use a Stripe-shaped payment provider — substitute your vendor.
Layer split
The project's rule (CLAUDE.md): application/ cannot import from infrastructure/; infrastructure/ can import from application/. Every type application-code reads must live in application/.
src/
├── application/
│ ├── common/interfaces/<vendor>/
│ │ ├── port.py ← Protocol <Vendor>Client
│ │ ├── types.py ← VENDOR enums/literals
│ │ └── responses.py ← raw Pydantic DTOs (1:1 with API JSON)
│ ├── v1/results/<entity>.py ← application Result (PaymentResult, …)
│ └── v1/services/<vendor>.py ← <Vendor>Service: raw → Result
│
└── infrastructure/http/clients/<vendor>/
├── client.py ← <Vendor>API(Client) — implements port structurally
└── endpoints.py ← StrEnum of URL paths
Raw response DTOs and vendor enums live in application/ because the service in application reads them. They become part of the port contract — the same pattern as JWT/TokenType, Cache/CacheKey: the port owns its vocabulary.
The Client — raw and dumb
Jobs: know the vendor's URL/auth, send HTTP, parse JSON into application-defined DTOs, translate HTTP errors into application exceptions. Never contains business branching or domain types.
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 · 390 lines · 102 tokens per session scan A 8d86170be610
api-client is a skill published in the GitHub repository ocbunknown/fastapi-claude-template (32 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 4,217 once invoked, about $0.0005 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.