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.
git clone --depth 1 https://github.com/TestAny-io/testany-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/commands/testany-io/testany-agent-skills/api-writer)<a href="https://agentmods.dev/commands/testany-io/testany-agent-skills/api-writer"><img src="https://agentmods.dev/badge/commands/testany-io/testany-agent-skills/api-writer/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/commands/testany-io/testany-agent-skills/api-writer"><img src="https://agentmods.dev/badge/commands/testany-io/testany-agent-skills/api-writer.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 | $0.00012 | $0.00542 |
| Opus 5.5 | $0.00005 | $0.00217 |
| Sonnet 5.5 | $0.00002 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
api-writer 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.
What it actually says
API Writer
执行前读取 工作流执行约定：先取证再提问、按实际工具能力回退，并从本次安装位置定位资源。
启动 API 契约撰写流程。基于 PRD 与边界确认，输出可审查的接口契约文档。
先区分 formal_design 与 bounded_change/amendment；有限增量使用既有有效基线及 Owner 批准，只处理受影响范围，不回补全生命周期文档。详见 ../references/document-amendments.md；完整流程只适用于正式新功能/全量准出。
使用方式
提供正式设计的 PRD，或有限增量的既有契约与批准范围：
$ARGUMENTS
支持的契约类型
- HTTP/REST API - OpenAPI 规范
- GraphQL API - GraphQL Schema
- gRPC API - Protocol Buffers
- 事件/消息协议 - AsyncAPI 规范
- WebSocket/SSE - 实时协议
- Webhook - 回调接口
- SDK/Library - 公共接口
- 文件格式 - 数据交换格式
- IPC/CLI/插件 - 进程间/命令行接口
契约聚焦内容
- 接口清单：路径/事件/函数签名、请求/响应/错误
- 安全与权限：认证/授权/数据级权限
- 兼容性策略：版本、弃用、breaking change
- 非功能约束：SLO、幂等性、分页、限流
正式设计工作流程
- 上下文收集：读取 PRD，扫描现有 API/规范
- 边界确认：服务/模块边界、数据所有权
- 类型选择：选择契约类型
- 契约撰写：生成契约 + PRD 映射表
- 一致性自检：覆盖率、冲突、兼容性检查
优先读取已提供的材料；仅对当前模式必需且仍缺失的输入提问。
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 Changed · +4 lines 09246b294923
- 1mo ago First seen · 44 lines · 12 tokens per session scan A 3e5b68800438
api-writer is a command published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 542 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
api-contract-review
Review an API contract (shapes, errors, auth model) BEFORE implementation for naming, versioning, pagination, idempotency, and fit with existing endpoints. Use when designing or changing endpoints. Do not use when the API is already implemented (use review-hard or repo-consistency-sweep).
build
Discover an AI Gateway's models and MCP tools, retrieve a credential, and integrate them into your app — call a model, connect MCP tools, or scaffold a runnable agent.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
fastapi
FastAPI application design and implementation conventions. Use this skill when building, updating, or reviewing FastAPI services, routers, dependencies, request/response schemas, streaming endpoints, or API tests. Trigger on FastAPI-specific work such as path operation design, dependency injection, response models…
symfony-api-mcp
Expose API Platform 4.3 operations as MCP tools for AI agents (@experimental).