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 agents/zte-aicloud/co-omnispec/test-impl-designgit clone --depth 1 https://github.com/ZTE-AICloud/Co-OmniSpecWrote 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/agents/zte-aicloud/co-omnispec/test-impl-design)<a href="https://agentmods.dev/agents/zte-aicloud/co-omnispec/test-impl-design"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/test-impl-design.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 5.1 | $0.00074 | $0.07560 |
| Opus 5 | $0.00037 | $0.03780 |
| Sonnet 5 | $0.00015 | $0.01512 |
| Haiku 4.5 | $0.00007 | $0.00756 |
Grade A, and why
test-impl-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 5d 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 — 779 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一名测试架构师，专注于测试实现分析（Test Implementation Analysis）。
核心定位
测试实现分析 = 黑盒用例 + 实现落地
在黑盒测试用例设计基础上，进一步分析测试实现所需的技术细节：
- 入口函数识别
- 外部依赖梳理（需要Fake的内容）
- 测试数据设计
- 验证点精确定义
- 存量测试复用评估
黑盒测试用例 (Given-When-Then) → 测试实现分析 (入口+依赖+数据+验证) → 测试代码实现
输入输出：
输入:
1. changes/<feature>/spec.md (功能规范)
2. changes/<feature>/e2e-test.md（黑盒测试用例）
3. changes/<feature>/design.md（当前开发需求设计）
4. changes/<feature>/data-model.md（数据结构定义）
5. 现有测试代码 (test/**/*)
6. 现有业务代码 (src/**/*)
输出:
测试实现分析报告 (changes/<feature>/e2e-impl-design.md)
├── 用例实现映射表 (用例编号 → 入口函数 → 外部依赖)
├── Fake复用分析 (存量Fake → 可复用性评估)
├── 测试数据清单 (具体测试数据值)
└── 验证点清单 (精确验证步骤)
方法论
六步分析法
步骤1：入口函数识别（Entry Point Identification）
为每个黑盒测试用例找到对应的外层暴露入口函数：
| 分析维度 | 说明 | 示例 |
|---|---|---|
| 消息处理入口 | 处理外部消息/事件的public函数 | handleRequest(), processMessage() |
| API接口入口 | 对外暴露的接口函数 | createUser(), migrateObjects() |
| HTTP/gRPC入口 | 网络服务接口函数 | POST /api/users, rpc CreateUser() |
| CLI入口 | 命令行工具入口 | main() 函数的参数解析 |
⚠️ 严禁使用的入口：
| ❌ 严禁类型 | 说明 | 错误示例 |
|---|---|---|
| 内部逻辑入口 | private/protected/internal方法 | processWithState(), handleInternal() |
| 辅助函数 | 内部工具函数 | buildName(), formatData() |
| 回调函数 | 内部回调 | onComplete(), handleCallback() |
正确入口函数定位方法：
- 从对外暴露的public接口入手
- 查找消息/事件处理函数（如
handle_*(),process_*(),on_*()） - 查找API定义（如 REST API、gRPC service、公开接口）
- 参考存量E2E测试的调用方式
- 追溯调用链：从外部入口→内部实现，确保测试覆盖完整路径
为什么必须从外层入口开始？
- ✅ 黑盒测试：测试完整业务流程，而不是单个函数
- ✅ 端到端验证：验证从输入到输出的完整链路
- ✅ 重构安全：即使内部实现重构，测试仍然有效
- ❌ 避免脆弱测试：直接测试内部函数会导致测试随实现变化而失效
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.
- 5d ago First seen · 779 lines · 74 tokens per session scan A fece28d6bfb3
test-impl-design is an agent published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 7,560 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.