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 vignesh2027/AI-AGENT-SKILLS --skill api-and-interface-designgit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-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/vignesh2027/ai-agent-skills/api-and-interface-design)<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/api-and-interface-design"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/api-and-interface-design/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/vignesh2027/ai-agent-skills/api-and-interface-design"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/api-and-interface-design.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 | $0.00017 | $0.00560 |
| Opus 5.5 | $0.00007 | $0.00224 |
| Sonnet 5.5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
api-and-interface-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 2mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
APIs are promises. Once published, they are hard to break without breaking callers. This skill designs APIs that are easy to use correctly, hard to use incorrectly, and evolvable without breaking changes.
When to Use
- Before designing a new API endpoint, SDK, or library interface
- Before publishing an API to external consumers
- When an existing API is causing confusion or misuse
Process
Step 1: Design the API for the caller, not the implementation
Your internal data model should not dictate your API shape. Design for the use case: what does the caller need to do? What information do they have? What do they want back?
Step 2: Consistency over cleverness
Naming, parameter order, error formats, and response shapes should be consistent across the entire API. Consistency is worth more than local elegance.
Step 3: Make the happy path obvious
A caller should be able to guess how to use the API without reading the documentation for the common cases. Reserve documentation for edge cases.
Step 4: Make errors informative
Every error must tell the caller: what went wrong, which field caused it (for validation errors), what they can do to fix it. "Bad request" is not an error message.
Step 5: Version from day one
Build versioning into the API from the first version: /v1/users, not /users. Retrofitting versioning is painful.
Step 6: Design for evolution
- Additive changes are backward compatible (add fields, add endpoints)
- Destructive changes break callers (remove fields, rename fields, change types)
- Use deprecation periods before removing anything
- Make optional fields optional, not required
Step 7: Define the contract
Document: authentication method, rate limits, request/response schema, error codes, pagination pattern, time formats, ID formats.
Step 8: Respect Hyrum's Law
"With a sufficient number of users of an API, it does not matter what you promise in the contract: all observable behaviors of your system will be depended on by somebody." Design carefully; change carefully.
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.
- 2mo ago First seen · 55 lines · 17 tokens per session scan A 79b93d3ddb98
api-and-interface-design is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 560 once invoked, about $0.0001 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 2026-08-31.
api-and-interface-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| api-and-interface-designvignesh2027/AI-AGENT-SKILLS | Skill | 2 | 2mo ago | MIT | A | 17 | Claude Code, Codex |
| mcp-builderHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 30 | Claude Code, Codex |
| build-teaql-appteaql/teaql-agent-kit | Skill | 2.8k | yesterday | MIT | A | 112 | Codex |
| firebase-authevanca/flutter-ai-rules | Skill | 668 | 2d ago | MIT | A | 29 | Claude Code |
| telegramrazzant/ouroboros | Skill | 1.6k | today | MIT | A | 19 | Claude Code |
| developing-genkit-dartevanca/flutter-ai-rules | Skill | 668 | 2d ago | MIT | A | 39 | Claude Code, Codex |
| firebase-cloud-functionsevanca/flutter-ai-rules | Skill | 668 | 2d ago | MIT | A | 36 | Claude Code |