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 ngocsangyem/MeowKit --skill api-design-principlesgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/api-design-principles)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/api-design-principles"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/api-design-principles/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/ngocsangyem/meowkit/api-design-principles"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/api-design-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.01845 |
| Opus 5.5 | $0.00024 | $0.00738 |
| Sonnet 5.5 | $0.00012 | $0.00369 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
mk:api-design-principles 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 1mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Design Principles
Durable interface contracts. Discover the existing contract before proposing a new one.
Ownership
| Owner | Owns | Does NOT own |
|---|---|---|
mk:api-design-principles |
Interface contract: resource/type/message shape, error and authorization requirements, compatibility and deprecation, consumer discovery | Implementation, persistence, security verdict, release |
mk:backend-development |
End-to-end backend change: discovery, classification, service/handler/integration work | Contract authorship, schema/SQL, security verdict, deploy |
mk:database |
Data invariants, schema, migration and recovery, query/index evidence, ORM boundary | API contract, authorization verdict, infrastructure execution |
mk:devops |
Infrastructure-as-code, containers, CI, runtime config, deployment safety design, rollback, incident diagnosis | Deploy approval and execution, security verdict, code root-cause, schema semantics |
Routing rules — identical in all four skills:
- Contract-only API question →
mk:api-design-principles, even in the middle of a task owned by another skill. "Contract" means what a consumer can observe: field set, error shape, status semantics, pagination, versioning. Extending an endpoint without changing any of those is not a contract change. - End-to-end backend change →
mk:backend-development, which invokes the API skill only when a new, public, or breaking contract is in scope. - A message-based change (event, webhook, RPC) splits: the message contract belongs to
mk:api-design-principles; the producer or consumer implementation belongs tomk:backend-development. - Schema, migration, query, index, or ORM work →
mk:database. No other skill writes a migration or generic SQL. - Infrastructure, containers, delivery, or deployment safety →
mk:devops. - An unscoped performance request is triaged by evidence, never by guess:
mk:backend-developmentlocates where the time actually goes, then hands a query or index question tomk:databaseand a capacity or runtime question tomk:devops. No skill invents the target. - Code root cause →
mk:investigate.mk:devopsowns the operational picture — what changed, where it fails, which signal proves it — and hands the defect over. - An auth-sensitive change: the owning skill states the requirement; the security workflow owns the verdict.
- Any production effect →
mk:shipor a human.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 152 lines · 59 tokens per session scan A cb8ebbf3b8c6
mk:api-design-principles is a skill published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,845 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
api-connector-builder
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-jitter on transient failures only, rate-limit-aware throttling. NOT inbound callbacks (that is webhooks), NOT chaining services (that is automation-flows), NOT designing your own…
api-design
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
api-testing-patterns
Comprehensive API testing patterns including contract testing, REST/GraphQL testing, and integration testing. Use when testing APIs or designing API test strategies.
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
conducting-api-security-testing
Conducts security testing of REST, GraphQL, and gRPC APIs to identify vulnerabilities in authentication, authorization, rate limiting, input validation, and business logic. The tester uses the OWASP API Security Top 10 as the testing framework, combining Burp Suite interception with Postman collections and custom…