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 BackToCimaCoppi/Praxis --skill test-execution-routergit clone --depth 1 https://github.com/BackToCimaCoppi/PraxisWrote 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/backtocimacoppi/praxis/test-execution-router)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/test-execution-router"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/test-execution-router/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/backtocimacoppi/praxis/test-execution-router"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/test-execution-router.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 | $0.00102 | $0.08219 |
| Opus 5.5 | $0.00041 | $0.03288 |
| Sonnet 5.5 | $0.00020 | $0.01644 |
| Haiku 4.5 | $0.00010 | $0.00822 |
Grade A, and why
test-execution-router 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 29d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测试执行路由
本 skill 只回答：冻结用例如何被准备、执行、路由和收口。不要在本层改用例口径；不要写项目凭据或平台专属细节。
0. 同一 goal 内的两种模式
| 模式 | 发生时点 | 可以做 | 禁止做 |
|---|---|---|---|
bootstrap M0 启动检查 |
goal 首个里程碑 | 实现/修复测试资产、runner、夹具、数据/环境适配与证据工具；每个命中面运行一个最小健康探针 | 改冻结用例语义、扩大用户授权、给逐 AC 提前签发 Ready |
verification 正式验证 |
goal 各施工切片内及候选交付前 | 跑冻结矩阵、封存 raw、派生证据状态；发现基础设施缺陷可就地修复并按影响面重跑 | 手填 VERIFIED、削弱断言、把产品现状反写测试 |
两种模式执行前都必须满足：
- 已读取冻结用例规格。
- 已确认
execution_ref或预定锚点。 - 已生成执行面矩阵：单元、接口、DB 预置、DB 终态、Web/admin UI、小程序 UI、视觉、手工；本任务命中面各一行，N/A 有可核理由。
- 已识别项目执行 skill；如果项目没有执行 skill，先报告缺口。
涉及真实动作时必须有上游用户授权锚点，逐项锁定目标环境、精确动作、目标对象、费用上限（含重试储备）与副作用范围。没有独立 readiness 门票；bootstrap 的失败先在 goal 内自愈。只有 goal-charter §4 白名单（真值矛盾 / 死亡线 / 未预授权动作，细则以彼处为真值）或计划内真实人工里程碑才交给用户；安全路径穷尽或达到限轮只交付 EXECUTION_BLOCKED，不前拉上游。
禁止行为：
- 边执行边修改断言。
- 用“环境不方便”跳过自动化。
- 把手工验证计作自动化覆盖。
- 把 AI 可控浏览器/开发者工具、DOM/data 断言、截图或 VLM 判读降级成手工。
- 失败后只写“测试失败”，不分类。
- 状态账本自证、派生聚合物冒充 raw、从账本反向改 raw、事后补绑候选版本或环境。
0.1 证据强度按影响面选择
执行载体的轻重不决定证据重量。先根据冻结规格与执行面矩阵选一种证据轮廓并记录理由，施工中发现影响面扩大时自动升档，禁止为了省事降档：
| 轮廓 | 适用判据 | 最低闭环 |
|---|---|---|
direct-native |
文案、样式、局部只读展示或单点行为；不改接口契约、持久化结构/写链路、状态机/并发/时钟语义，且已有稳定 runner 能直接给出原生结果 | 最终候选 + 目标环境 + run 绑定；AC 逐项直指原生报告、截图或终点实测；失败/错误/跳过/未执行完整可见；不为包装而新造证据框架 |
assertion-native |
新增/变更表、字段、索引、迁移、接口契约、持久化写链路、状态机/并发/时钟规则、跨前后端完整功能、死亡线、高失败代价，或需要新建/实质修改取证工具 | 细粒度逐 AC/证明部件的 raw → envelope → mapping → 账本；所需 fixture/harness、数据清理恢复和终态校验；项目原生检查器全绿 |
direct-native 不是口头验收：缺候选/环境/run 绑定、用聚合 PASS 代替原始结果、隐藏失败或无法逐 AC 定位时必须升为 assertion-native 或补齐原生观测。assertion-native 也不要求每个任务重造生成器；优先复用项目公共 producer/checker，只有实际观测适配缺口才建设新工具。标准总控有正式 L7 和独立冻结索引时默认 assertion-native；plan-goal 以批准后的 AC 表直接充当索引，是否采用细粒度证据仍只看上述影响面。
涉及真实动作时必须有上游用户授权锚点，逐项锁定目标环境、精确动作、目标对象、费用上限（含重试储备）与副作用范围。没有独立 readiness 门票；bootstrap 的失败先在 goal 内自愈。只有 goal-charter §4 白名单（真值矛盾 / 死亡线 / 未预授权动作，细则以彼处为真值）或计划内真实人工里程碑才交给用户；安全路径穷尽或达到限轮只交付 EXECUTION_BLOCKED，不前拉上游。
禁止行为：
- 边执行边修改断言。
- 用“环境不方便”跳过自动化。
- 把手工验证计作自动化覆盖。
- 把 AI 可控浏览器/开发者工具、DOM/data 断言、截图或 VLM 判读降级成手工。
- 失败后只写“测试失败”，不分类。
- 状态账本自证、派生聚合物冒充 raw、从账本反向改 raw、事后补绑候选版本或环境。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 29d ago Changed · +98 lines 2a46dc259ad4
- 1mo ago First seen · 178 lines · 102 tokens per session scan A aef1d3ad2c4e
test-execution-router is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 102 tokens to every session and 8,219 once invoked, about $0.0004 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.
Other skills, from other repositories
emulate-seed
Generate emulate seed configs for stateful API emulation. Wraps Vercel's emulate tool for GitHub, Vercel, Google OAuth, Slack, Apple Auth, Microsoft Entra, AWS, Okta, Clerk, Resend, Stripe, and MongoDB Atlas APIs — full state machines, not mocks. Use when setting up test environments, CI pipelines, integration tests…
architecture-patterns
Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right…
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
testing-e2e
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.
testing-integration
Integration and contract testing patterns — API endpoint tests, component integration, database testing, Pact contract verification, property-based testing, and Zod schema validation. Use when testing API boundaries, verifying contracts, or validating cross-service integration.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.