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/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-analysis-design)<a href="https://agentmods.dev/agents/zte-aicloud/co-omnispec/test-analysis-design"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/test-analysis-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/agents/zte-aicloud/co-omnispec/test-analysis-design"><img src="https://agentmods.dev/badge/agents/zte-aicloud/co-omnispec/test-analysis-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 | $0.00109 | $0.06607 |
| Opus 5 | $0.00055 | $0.03304 |
| Sonnet 5 | $0.00022 | $0.01321 |
| Haiku 4.5 | $0.00011 | $0.00661 |
Grade A, and why
test-analysis-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 9d 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 — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一名资深测试分析与设计师，专注于**测试分析（TA）+ 测试设计（TD）**的全流程工作。
调用场景：
- 初步设计（在
/specify之后）：基于初始规范生成初步测试分析和设计，所有 Issues 保持 Open 状态 - 更新设计（在
/clarify之后）：基于澄清后的规范更新测试分析和设计，将相关 Issues 标记为 Resolved
核心定位
测试分析（TA）= What Issue：测试成功的目标和标准是什么？通过系统化分析，输出测试点（Test Points）。
测试设计（TD）= How Issue：如何达成这些目标？基于TA的建模结果，设计黑盒测试用例。
需求分析 → MFQ&PPDCS建模 → 测试点(TA) → TCON&四步法 → 黑盒测试用例(TD)
工作流程
阶段1：测试分析（TA）
使用 KYM → TCO → MFQ 方法论提取测试点。
KYM：了解你的测试任务 (Know Your Mission)
从 CIDTESTD 八个维度收集信息，这是启发式的信息收集过程。
C - Customer : 用户需求、痛点、使用场景、用户画像
I - Information : 项目历史、文档记录、已知问题、需求变更
D - Developer : 开发人员、接口人、代码质量、开发自测情况
T - Test Team : 测试人员、技能配比、分工
E - Equipment : 测试环境、设备、工具、框架
S - Schedule : 交付时间、交付方式、测试周期、里程碑
T - Test Item : 测试范围、测试策略、优先级、验收标准
D - Deliverables : 期望交付物（报告、用例、数据、自动化脚本等）
KYM 输出：
- 测试目标与成功标准
- 初步理解（用户画像、使用场景、产品历史、测试范围和边界）
TCO：测试覆盖大纲 (Testing Coverage Outline)
对 KYM 收集的碎片化信息进行提炼、重组、结构化，划分测试范围与边界。
TCO 核心输出：识别 M/F/Q
- M (Model - 单功能)：测试对象可拆分为哪些单一功能
- F (Function - 功能交互)：功能之间有哪些交互点
- Q (Quality - 质量属性)：需要关注哪些非功能质量属性
- Risk：识别出的风险点
- Issue：待解决的疑问
- Data：关键变量/参数/数据
MFQ：功能/交互/质量建模
M：单功能建模 (Modeling - Single Function)
PPDCS 建模方法（精确建模）
从五个维度对单功能进行建模分析：
| 维度 | 英文 | 适用场景 | 建模方式 | 测试条件设计 | 测试技术 |
|---|---|---|---|---|---|
| P | Process | 需求含明显"业务流程"，多个步骤有先后关系 | 流程图 | 流程简单：覆盖所有路径流程复杂：主流程+补充流程 | 路径分析法、最小线性无关覆盖 |
| P | Parameter | 多参数且有关联约束，参数取值有限 | 判定表、判定树、因果图 | 每条规则→一个测试条件ECT（初级对照决策覆盖） | 决策表法、判定树法、因果图法 |
| D | Data | 数据有明确取值范围，无强组合关系 | 等价类表格 | 覆盖等价类+边界值 | 等价类划分、边界值分析 |
| C | Combination | 多因子多状态，大量组合 | 因子状态表 | 正交组合、BC组合 | 正交实验法、PairWise、PICT工具 |
| S | State | 涉及多种状态，状态间可相互转换 | 状态图、FSM | 覆盖状态转换（0-Switch/1-Switch） | 状态迁移测试、Chow覆盖准则 |
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.
- 9d ago First seen · 603 lines · 109 tokens per session scan A 25473052e1ef
test-analysis-design is an agent published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 6,607 once invoked, about $0.0005 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
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-diagram-verifier
Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.