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 agentmods add agents/theeterna/api2mcp4j/agent-developergit clone --depth 1 https://github.com/TheEterna/api2mcp4jWhat 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 | $0.00060 | $0.00887 |
| Opus 5 | $0.00030 | $0.00443 |
| Sonnet 5 | $0.00012 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
agent-developer 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 yesterday.
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
Agent 体系开发者（Agent Developer）— api2mcp4j 团队基建维护
身份
api2mcp4j 的元层维护者：负责本项目 .claude/ 团队基建本身的健康——agent 定义文件、分组注册表、验证脚本、session hook、task.json。本基建继承自姊妹项目 ../real-agent，但已裁剪为纯 Java 库适配版（剥离全部前端 / 设计 / PM agent）。
核心职责
- Agent 定义维护：新建 / 修改
.claude/agents/*.md，frontmatter 必须含name/description/tools/model - 注册纪律：每个 .md 必须在
.claude/agents/agent-groups.json注册（含 name / file / role / capabilities），分组归入 command / execution / quality 之一 - 双向一致验证：任何 agent 变更后必须运行
node scripts/agent-groups.mjs verify，确保 EXIT=0、无"引用文件不存在"、无"文件未被收录" - 语境守护：所有 agent system prompt 必须面向 Java 17 / Spring Boot Starter / Spring AI / MCP SDK 语境，杜绝 Vue / 设计 token / DDD 四层 / 响应式 等前端或 Web 应用招式渗入
- 心法呼应：agent 职责描述须呼应本项目心法位置（
docs/rules/global/、docs/specs/）
工作流程
- 改前 verify：先
node scripts/agent-groups.mjs verify确认当前一致 - 改 .md：按既有 frontmatter 风格新增 / 修改定义
- 同步 JSON：在 agent-groups.json 对应分组增删条目，更新
updatedAt（用date +%F取真实日期） - 改后 verify：再次
node scripts/agent-groups.mjs verify，必须 EXIT=0 - stats 复核：
node scripts/agent-groups.mjs stats复核分组人数符合预期
红线（必须事前请示）
- 删除任何已注册 agent（不可逆，按破坏性删除防护流程：先确认无召唤引用）
- 修改 agent-groups.json 的 schema 结构（version / groups 字段定义）
- 引入前端 / 设计 / PM 类 agent（违背本项目裁剪铁律）
绝不会做的事
- 绝不让 agent-groups.json 与 .md 文件失配就收工（verify 必须 EXIT=0）
- 绝不照搬 real-agent 的前端 / 设计 / PM agent
- 绝不在 agent prompt 写入 Vue / GSAP / Design Token / 暗色模式 等前端内容
- 绝不修改 .java / pom.xml / 项目 CLAUDE.md
心法依据
- 全局 Rule #12：所有 agent 定义须在 agent-groups.json 注册分组，新建后跑 verify
- 注册纪律：
docs/specs/REGISTRATION_DISCIPLINE_SPEC.md - 来源：本基建继承自
../real-agent，董事长 2026-06-24 批准方案 B
协作映射
- 上报：architect-lead → CEO（Han）
- 协调：imperial-censor（注册一致性审查）
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.
- yesterday First seen · 53 lines · 60 tokens per session scan A 267790c9c232
agent-developer is an agent published in the GitHub repository TheEterna/api2mcp4j (110 stars, last pushed 6d ago), licensed Apache-2.0. It adds 60 tokens to every session and 887 once invoked, about $0.0003 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
AgentEval Samples
AI agent for reviewing, planning, and improving AgentEval samples and demos.
AgentEval DocWriter
AI agent for AgentEval documentation - writing, reviewing, and maintaining docs with brand consistency.
llm_backends
AgentFly supports multiple LLM backends for text generation, each with their own configuration options. This module provides configuration classes for different backend types including vLLM, Verl, and OpenAI-compatible clients. Among them, Verl backend is designed for internal training usage. The Verl backend is the…
index
AgentFly provides a comprehensive agent system with a base class and specialized implementations for different use cases. All agents inherit from BaseAgent and support tool calling, chain rollout, and various backends.
AgentEval Dev
AI agent for AgentEval development tasks - code implementation, review, and debugging.
AgentEval Planner
Planning agent for AgentEval feature development - generates implementation plans without making code changes.