agentmods.dev

test

A testing workflow for writing and running unit and integration tests, then recording the results in a structured test report. TDD, or test-driven development, is not required by the description.

In plain words
What is it for?
Use it to test planned features, normal and edge cases, error handling, and end-to-end scenarios while changing only test-related files.
Why use it?
It separates checking behavior from changing business code, so failures are documented instead of being silently hidden by unapproved fixes.

Skill for Claude CodeCodex

33 5mo ago A scan 77 tokens original MIT
View the source file SimpleEve/development-skills
Install

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.

agentmods
npx agentmods add skills/simpleeve/development-skills/test
Any agent
npx skills add SimpleEve/development-skills --skill test
Clone the repo
git clone --depth 1 https://github.com/SimpleEve/development-skills

Made for: Claude Code, Codex.

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00077 $0.01282
Opus 5 $0.00039 $0.00641
Sonnet 5 $0.00015 $0.00256
Haiku 4.5 $0.00008 $0.00128

Measured 2d ago against content hash 4c53d14bd57c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test 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 2d 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.

test/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test - 测试技能

根据 plan 文档编写并执行单元测试与集成测试，产出结构化测试报告。该技能的核心目标是验证而非修复。

职能边界

  1. 绝对禁令：禁止修改任何非测试相关的业务源码。即便发现 bug，也只能在测试报告中记录并建议修复，不得自行调用 /implement 或手动修改源码。
  2. 操作范围：仅允许修改、新增测试文件、测试目录内容，或项目明确归类为测试资产的文件。
  3. 输出目标：高质量的测试代码覆盖及详尽的 test.md 测试报告。

核心原则

  1. 以 Plan 为准：测试用例严格基于 plan.md 中的验收标准与测试规范。
  2. 验证驱动：所有职能围绕“证明代码是否符合预期”展开。
  3. 独立报告：测试结果必须固定产出到对应的 test.md 文档中。
  4. 可调用外部 Skill/工具：需要环境观测、运行验证、引擎执行或自动化操作时可调用相应工具。

工作流程

阶段一：单元测试

  1. 阅读 Plan 的测试标准

    • 阅读对应功能 plan.md 中的"单元测试标准"。
    • 提取每个 TODO 的验收标准。

  2. 编写/优化单元测试

    • 仅在测试目录或项目既有测试命名约定下编写代码。
    • 覆盖正常路径、边界条件、异常场景。

  3. 执行单元测试

    • 运行项目测试命令或测试入口（如 vitest、npm test、pnpm test、dotnet test、Unity Test Runner）收集结果。

  4. 失败分析与记录

    • 如果测试失败： a. 分析是测试代码本身的逻辑错误，还是业务代码的 bug。 b. 如果是测试代码写错了，直接在测试文件中修正。 c. 如果是业务代码 bug，停止修改行为，将失败原因、错误日志及重现步骤记录到测试报告中。

阶段二：集成 / 场景验证

  1. 阅读 Plan 的集成测试标准

    • 阅读对应功能 plan.md 中的"集成 / 场景验证标准"。

  2. 编写并执行集成 / 场景验证

    • 根据场景编写独立的测试脚本、测试用例或自动化验证流程。
    • 捕获命令输出、退出码、运行结果、日志或截图作为执行证据。

阶段三：产出测试报告

按照下方固定模板撰写，写入对应功能的 test.md。

固定模板

# <功能名称> 测试报告

> 关联 Spec：<spec 文档路径>
> 关联 Plan：<plan 文档路径>
> 测试日期：YYYY-MM-DD
> 测试环境：运行时 / OS / 版本 / 其他相关信息

## 测试总结

| 指标           | 数值 |
| -------------- | ---- |
| 单元测试总数   | N    |
| 单元测试通过   | N    |
| 单元测试失败   | N    |
| 集成测试总数   | N    |
| 集成测试通过   | N    |
| 集成测试失败   | N    |
| 总体通过率     | N%   |

## 单元测试详情

### ✅ 通过的测试

| 测试文件        | 测试用例 | 对应 TODO |
| --------------- | -------- | --------- |
| `path/to/test`  | 测试描述 | TODO-S1   |

### ❌ 失败的测试

#### [FAIL-1] <测试用例名称>

- **测试文件**：`path/to/test`
- **对应 TODO**：TODO-XX
- **失败原因**：详细描述（明确区分是测试错误还是业务 bug）
- **修复建议**：针对业务 bug 提出修改建议
- **错误日志**：

相关的错误输出


## 集成 / 场景验证详情

### 场景 1：<场景名称>
- **操作步骤**：...
- **期望结果**：...
- **实际结果**：✅ 符合预期 / ❌ 与预期不符
- **证据**：命令输出 / 日志 / 截图路径 / 运行结果

## 未覆盖的测试场景

列出 Plan 中要求但本次未覆盖的测试场景及原因。

## 遗留问题

列出需要人工关注的问题（如环境限制、业务代码存在的风险点等）。

关键约束

  • 禁止跨权：严禁调用 /implement 技能或者直接去尝试修复业务逻辑。
  • 测试独立性：每个测试用例应独立运行，不依赖其他测试的执行顺序。
  • 不修改 spec/plan：测试过程中发现 spec 或 plan 的问题，记录到报告中，不自行修改。
  • 证据完整：每个关键测试场景必须有可验证的执行证据。

Read the full file on GitHub · 123 lines

Changes

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.

  1. 2d ago First seen · 123 lines · 77 tokens per session scan A 4c53d14bd57c

Subscribe to this mod's changes

test is a skill published in the GitHub repository SimpleEve/development-skills (33 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 1,282 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.

TestingUnit testingagent-skillsai-agentsclaude-codecodexdeveloper-toolssoftware-engineering
Related

Other skills, from other repositories

coverage-enhancer

Analyze existing test suites and source code to suggest additional unit tests that improve test coverage. Use this skill when working with test files and source code to identify untested code paths, missing edge cases, uncovered branches, untested error conditions, and gaps in test coverage. Supports major testing…

ArabelaTso/Skills-4-SE · 84 tokens

assertion-synthesizer

Generate test assertions from existing code implementation. Use when the user has implementation code without tests or incomplete test coverage, and needs assertions synthesized by analyzing the code's behavior, inputs, outputs, and state changes. Supports Python (pytest/unittest), Java (JUnit/AssertJ), and…

ArabelaTso/Skills-4-SE · 87 tokens

directed-test-input-generator

Generate targeted test inputs to reach specific code paths and hard-to-reach behaviors in Python code. Use when: (1) Targeting uncovered branches or specific execution paths, (2) Need coverage-guided test generation, (3) Want to leverage LLM understanding of code semantics for meaningful test inputs, (4) Testing…

ArabelaTso/Skills-4-SE · 112 tokens

code-repair-generation-combo

Automatically repair buggy code and generate comprehensive tests for Python, Java, and C++ programs. Use when users need to fix logic errors or runtime errors in functions, modules, or repositories. Accepts specifications via natural language descriptions, existing test cases, or input/output examples. Generates…

ArabelaTso/Skills-4-SE · 119 tokens

enterprise-test-suites

Comprehensive testing matrix spanning Unit, Integration, E2E (Playwright), Contract (Pact), Chaos/Fault-Injection, Mutation, Load/Stress (k6), and Security Fuzz testing.

saitarrun/Devforge-ai · 47 tokens

eo-test

根据 change.md 编写并执行单元/集成测试，产出 test.md 报告。严禁修改业务代码。触发：写测试 / 跑测试 / test / /eo-test。.

SimpleEve/eo-skills · 47 tokens