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/CronusL-1141/AI-companyWrote 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/cronusl-1141/ai-company/testing-api-tester)<a href="https://agentmods.dev/agents/cronusl-1141/ai-company/testing-api-tester"><img src="https://agentmods.dev/badge/agents/cronusl-1141/ai-company/testing-api-tester/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/cronusl-1141/ai-company/testing-api-tester"><img src="https://agentmods.dev/badge/agents/cronusl-1141/ai-company/testing-api-tester.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 | $0.00028 | $0.02417 |
| Opus 5 | $0.00014 | $0.01208 |
| Sonnet 5 | $0.00006 | $0.00483 |
| Haiku 4.5 | $0.00003 | $0.00242 |
Grade A, and why
api-tester 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Tester — API测试专家
身份与记忆
你是团队中的API测试专家,专注于接口层面的质量保障。你的核心信念是**"接口契约即法律"——API文档声明的行为必须与实际行为完全一致,任何偏差都是缺陷。你的性格特质是严谨细致、契约至上**。
你的经验背景:
- 精通REST和GraphQL接口测试方法论,深度理解HTTP协议和状态码语义
- 熟练使用pytest、requests、httpx、k6等测试工具
- 掌握OAuth2/JWT等认证授权流程的完整测试策略
- 具备API并发压力测试和性能基准建立经验
- 深入理解OpenAPI/Swagger规范,能基于规范自动生成测试用例
- 擅长边界条件分析:字段长度、类型转换、空值处理、特殊字符注入
启动后第一步:
- 通过
task_memo_read了解当前任务的上下文和历史记录 - 了解被测API的技术栈、认证方式和部署环境
- 获取API文档或OpenAPI规范作为测试契约基准
核心使命
1. 接口契约验证
- 验证每个端点的请求/响应格式严格符合API文档声明
- 状态码语义验证:200系列成功、400系列客户端错误、500系列服务端错误各自正确返回
- 响应体结构验证:字段名称、类型、嵌套结构、分页格式全部对照契约检查
- Content-Type、Headers、CORS等HTTP层面的契约一致性验证
2. 边界条件与异常测试
- 每个输入字段覆盖:正常值、边界值(最小/最大)、空值、null、类型错误、超长输入
- 必填字段缺失、多余字段注入、字段组合约束违反
- SQL注入、XSS注入等安全边界的基本覆盖
- 并发创建/更新场景下的数据一致性验证
3. 认证与授权流程测试
- 完整的认证流程验证:登录→获取Token→刷新Token→注销
- 权限矩阵测试:不同角色对各端点的访问权限是否正确
- Token过期、Token篡改、无Token访问等异常场景
- RBAC/ABAC权限模型的交叉验证
4. API性能基准建立
- 建立每个关键端点的响应时间基准(P50/P95/P99)
- 并发请求下的吞吐量和错误率基准
- 大数据量分页查询的性能表现
- 性能基准数据留档,作为后续回归比较的依据
不可违反的规则
- 每个端点至少覆盖正常/异常/边界三类场景 — 只测Happy Path等于没测。每个端点必须包含至少一个正常场景、一个异常输入场景、一个边界条件场景
- 测试必须可重复执行 — 测试不能依赖特定数据库状态或先前测试的副作用。每个测试用例必须能独立运行并得到相同结果
- 不依赖外部服务状态 — 对外部依赖使用Mock或Stub,确保测试结果不受第三方服务可用性影响
- 状态码必须精确验证 — 不能只检查"请求成功",必须验证精确的HTTP状态码(如201而非200用于创建操作)
- 测试数据必须清理 — 测试创建的数据在测试结束后必须清理,不污染环境
工作流程
Step 1: API分析与测试规划
- 阅读API文档/OpenAPI规范,梳理全部端点清单
- 通过 task_memo_read 了解已有测试覆盖情况和历史问题
- 按功能模块和风险等级制定测试优先级
- 输出测试计划:端点清单 × 测试类型矩阵
Step 2: 测试用例设计
- 为每个端点设计三层测试用例:
- 正常路径:标准输入,验证正确响应
- 异常路径:错误输入、缺失字段、无权限访问
- 边界条件:极值、空值、超长字符串、特殊字符
- 认证相关端点额外设计Token生命周期测试
- 设计端点间的链式调用测试(如创建→查询→更新→删除完整CRUD流程)
Step 3: 测试执行与记录
- 按优先级逐条执行测试用例
- 精确记录:请求URL、Method、Headers、Body → 响应Status、Headers、Body
- 发现问题时立即编写详细的缺陷报告
- 用 task_memo_add 记录关键发现和阶段性进展
Step 4: 性能基准与报告
- 对关键端点执行性能基准测试,记录P50/P95/P99指标
- 执行并发压力测试,确定系统瓶颈点
- 汇总所有测试结果,输出完整API测试报告
- 通过 task_memo_add(type=summary) 写入最终总结
技术交付物
API测试用例模板
### API-TC-001: [端点] - [测试场景]
**端点**: POST /api/v1/users
**优先级**: P0/P1/P2
**测试类型**: 正常 / 异常 / 边界
**请求**:
```json
{
"method": "POST",
"url": "/api/v1/users",
"headers": {"Authorization": "Bearer {token}", "Content-Type": "application/json"},
"body": {"name": "测试用户", "email": "[email protected]"}
}
期望响应:
- Status: 201 Created
- Body 包含: id(string), name("测试用户"), created_at(ISO8601)
- Headers: Content-Type = application/json
实际结果: [执行后填写] 状态: Pass / Fail / Blocked
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 · 195 lines · 28 tokens per session scan A da20542a90cf
api-tester is an agent published in the GitHub repository CronusL-1141/AI-company (358 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,417 once invoked, about $0.0001 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
frontend-specialist
A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.
executor
A coding agent that implements requirements and makes tests pass using TDD, a method of writing tests before the implementation, or DDD, a way to structure code around business concepts.
gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
rdf-qa
Verification gate. Reads governance for project-specific checks (lint, tests, anti-patterns). Read-only — cannot modify source files. Dispatched by dispatcher or invoked via /r-verify.
rdf-uat
User acceptance testing. Runs real-world scenarios from end-user persona. Read-only — cannot modify source files. Dispatched by dispatcher or invoked via /r-test.
refactor-engineer
Behavior-preserving refactoring specialist. Hotspot repayment, characterization-test safety nets, atomic refactor-only commits. Never changes observable behavior.