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 instructions/buer2233/ai-api-test-skill/agents-mdgit clone --depth 1 https://github.com/buer2233/ai-api-test-skillWrote 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/instructions/buer2233/ai-api-test-skill/agents-md)<a href="https://agentmods.dev/instructions/buer2233/ai-api-test-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/buer2233/ai-api-test-skill/agents-md.svg" alt="Measured on agentmods" 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 | $0.03947 | $0.03947 |
| Opus 5 | $0.01973 | $0.01973 |
| Sonnet 5 | $0.00789 | $0.00789 |
| Haiku 4.5 | $0.00395 | $0.00395 |
Grade A, and why
ai-api-test-skill AGENTS.md 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 4d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
沟通语言
与用户沟通时一律使用简体中文。包括但不限于：解释方案、复述需求、报告执行结果、追问澄清、insight 注释中的解释文字。代码、命令、文件名、英文专有名词保持原样不翻译。
仓库性质
本目录是一个 Claude Code / Codex Skill(api-test-E10)，项目级，固定安装在 test-automation 仓库的 .claude/skills/api-test-E10/ 路径下，随仓库一起分发。它的工作是驱动同一仓库内 E10自动化/接口自动化测试/ 的接口测试编写。绝大多数"源代码"是 Markdown 规范，只有 tools/、capture/、skill_utils/、hooks/ 目录里有 Python。
用户触发本 skill 时，期望你把 SKILL.md 当作执行手册严格遵循，而不是去重构它。本仓库内的"代码改动"主要形式是文档编辑。
文档层级（加载顺序很重要）
文档刻意拆分，并非每次激活都全部加载：
SKILL.md—— 每次会话必加载。保留前置门禁的新增 / 维护分流读取要求、方式分流、核心原则纲领。AI 行为的入口权威来源；详细执行手册按任务类型 Readdoc/preflight_gates_new.md或doc/preflight_gates_maintenance.md，核心原则按需 Readdoc/core_principles.md，方式细则按需 Readdoc/mode_*.md。README.md—— 面向用户的快速指南。与SKILL.md部分内容重叠。修改策略时先改SKILL.md，再把用户可见的部分同步到README.md。python tools/scan_page_api.py：刷新tools/page_api_index.sqlite3接口索引。doc/preflight_gates_new.md—— 新增任务按需加载，新增用例/接口方法的前置门禁详细执行手册（5 项必填、四选一菜单等）。doc/preflight_gates_maintenance.md—— 维护任务按需加载，维护已有用例/接口方法的前置门禁详细执行手册（2 项必填、四选一菜单等）。doc/core_principles.md—— 按需加载，核心原则 1-5 的详细规则（查重流程、索引维护、pytest 闭环细节等）。SKILL.md 触发对应原则时按需 Read。doc/mode_capture_driven.md/doc/mode_reference_case.md/doc/mode_curl_manual.md/doc/mode_java_controller_source.md—— 新增任务的四种接口自动化编写方案，选定方式后必须按需读取对应文件。doc/maintenance_prompt_context.md+doc/mode_maintenance_*.md—— 维护任务专用上下文与四种维护方案，其中方式4为 pytest 报错驱动维护。doc/coding_style_guide.md—— 按需加载，仅在编写接口方法 / 用例代码前 Read。doc/high_frequency_experience.md—— 仅在踩到对应坑（Codex apply_patch、show_list、参数化与断言同步等）时加载。flow_chart/flow.md与同目录 PNG —— Mermaid 源码与导出图。当前导出图覆盖前置 hook、主流程、前置门禁、新增总览、新增四方式、维护总览、维护四方式、pytest 闭环。flow.md实质变化时才更新 PNG。- 第三方依赖 Skill：维护方式4默认优先使用
/test-fixing；只有/test-fixing无法解决、维护遇到困难或前后接口/调用栈信息不明确时，才使用/Debugging断点调试辅助定位。 - 若当前环境没有
/test-fixing，直接按doc/mode_maintenance_pytest_driven.md的失败分类、最小补丁和循环验证步骤执行，不得因依赖缺失而停止维护。
避免在多个文档间复制策略。这种拆分的目的就是让 SKILL.md 保持每次会话固定加载、其余按需拉取。
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.
- 4d ago First seen · 178 lines · 3,947 tokens per session scan A 2d0065784bf6
ai-api-test-skill AGENTS.md is an instructions file published in the GitHub repository buer2233/ai-api-test-skill (142 stars, last pushed 27d ago), licensed MIT. It adds 3,947 tokens to every session, about $0.0197 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 instructions, from other repositories
WHartTest copilot-instructions.md
Copilot instructions for MGdaasLab/WHartTest, covering copilot instructions — wharttest, 项目概述, 运行环境, 后端规范（wharttestdjango） and 视图与路由.
qaskills AGENTS.md
AGENTS.md instructions for PramodDutta/qaskills, covering agents.md, project overview, common commands, run a single package and run tests in watch mode.
agentic-playwright common-tasks.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai prompt templates for agentic playwright, critical, instructions, phase 1: identify the task category and resolve paths and phase 2: select and customize the matching prompt template.
agentic-playwright debugging.instructions.md
Instructions for idavidov13/agentic-playwright, covering debugging, critical, capture defaults (this scaffold), built-in npm scripts for debugging and instructions.
agentic-playwright data-strategy.instructions.md
Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.
agentic-playwright config.instructions.md
Instructions for idavidov13/agentic-playwright, covering configuration, critical, file locations, instructions and phase 1: understand how env files are loaded.