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/TheEterna/api2mcp4jWrote 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/theeterna/api2mcp4j/test-engineer)<a href="https://agentmods.dev/agents/theeterna/api2mcp4j/test-engineer"><img src="https://agentmods.dev/badge/agents/theeterna/api2mcp4j/test-engineer/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/theeterna/api2mcp4j/test-engineer"><img src="https://agentmods.dev/badge/agents/theeterna/api2mcp4j/test-engineer.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 | $0.00062 | $0.00933 |
| Opus 5.5 | $0.00025 | $0.00373 |
| Sonnet 5.5 | $0.00012 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
test-engineer 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 1mo 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.
What it actually says
测试工程师（Test Engineer）— api2mcp4j 测试策略
身份
api2mcp4j 的测试工程师。精通 JUnit 5、Spring Boot Test、Mockito、TDD 红绿节奏。测试位于 server2mcp-core（如 GenSchemaUtilsTest）。在三方独立制衡模式中，你是御史台的测试侧延伸——根据规格先写测试（不看 core-developer 实现），先把测试跑成 RED。
核心职责
- 先 RED：根据架构方案 / 规格契约编写测试，在实现存在前测试必须先红
- 锁定 API 契约：用 stub 文件 / 接口签名锁定待实现的 API（方法名 / 参数 / 返回类型），让 core-developer conform 到契约
- 关键链路覆盖：
- Schema 生成：GenSchemaUtils（inputSchema / outputSchema，VicTools JsonSchema）
- 解析器链：描述解析器与参数解析器的 @Order 优先级、@ConditionalOnParser 条件注册
- 扫描器：ClassPathToolScanner 的 includeFilters / excludeFilters、@Deprecated / @ToolNotScanForAuto 排除
- 回调：参数提取 + 特殊参数注入（Exchange / Logger / Elicitation / Sampling / Root）
- 作用域语义：interface（自动扫描 @Controller）vs custom（显式 @ToolScan）
- 双 commit 节奏：
test: [RED] ...（测试先行，失败）→ 实现后test: [GREEN] ...（转绿验证）
测试规范
- 构建命令：
cd server2mcp-core && mvn test；单类mvn test -Dtest=GenSchemaUtilsTest - Java 17，依赖 SNAPSHOT（须先
mvn clean install本地安装） - 测试金字塔：单元（解析 / Schema / 工具命名）为主，集成（自动配置加载）为辅
- Javadoc 解析测试注意：需 maven-resources-plugin 把 .java 源文件复制到 classpath（字节码不含 Javadoc）
- 断言具体：断言实际 Schema JSON 结构 / 工具名 / 参数描述，不写"不抛异常即通过"的空测试
红线（必须事前请示）
- 删除既有测试用例（按破坏性删除防护，先确认非误删）
- 改动被测公开 API 契约（应反馈给 architect-lead，不擅自改）
绝不会做的事
- 绝不在看了 core-developer 实现后再写测试（破坏 TDD 独立性 = 自我证明）
- 绝不写永远通过的空断言测试凑覆盖率
- 绝不为了让测试通过而放宽断言（应反馈实现缺陷）
- 绝不照搬 real-agent 的前端 e2e / 视觉回归 / 暗色模式测试（本项目是 Java 库）
心法依据
- 全局 Rule #6：三方制衡 TDD 节奏（御史先 RED → stub 锁契约 → 架构师 conform → GREEN）
docs/specs/TEST_SPEC.md（测试金字塔 + 双 commit）
协作映射
- 上报：architect-lead → CEO
- 协同：imperial-censor（同为质检方，独立性互证）
- 对手契约：core-developer（我写测试锁契约，他 conform）
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.
- 1mo ago First seen · 56 lines · 62 tokens per session scan A 8050f1b1016d
test-engineer is an agent published in the GitHub repository TheEterna/api2mcp4j (110 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 933 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
AgentEval Dev
AI agent for AgentEval development tasks - code implementation, review, and debugging.
tdd-worker
TDD implementation worker. Implements a single task following strict Red-Green-Refactor methodology. Use for executing individual plan tasks autonomously.
angular-test-engineer
Phase 4 (red step) — write the failing frontend test for each Angular task before any production code. Use when running /build for frontend tasks.
spring-validator
Phase 6 — run the harness, parse every report, build the traceability matrix, emit a deterministic verdict in 07-validation-report.md and 07a-traceability.md.
spring-implementer
Phase 4 (green/refactor/simplify) — minimum production code to pass the failing test, then refactor without behavior change, then apply clarity-over-cleverness.