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 instructions/theeterna/api2mcp4j/claude-mdgit 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/instructions/theeterna/api2mcp4j/claude-md)<a href="https://agentmods.dev/instructions/theeterna/api2mcp4j/claude-md"><img src="https://agentmods.dev/badge/instructions/theeterna/api2mcp4j/claude-md.svg" alt="Measured on agentmods" 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 | $0.05501 | $0.05501 |
| Opus 5 | $0.02750 | $0.02750 |
| Sonnet 5 | $0.01100 | $0.01100 |
| Haiku 4.5 | $0.00550 | $0.00550 |
Grade A, and why
api2mcp4j CLAUDE.md 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 4d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
api2mcp4j（内部名称 server2mcp）是一个 Spring Boot Starter 框架，能自动将 Java Spring Controller 接口暴露为 MCP（Model Context Protocol）的 Tool、Resource、Prompt 和 Complete。设计理念是非侵入式、纯增强——类似 MyBatis-Plus 与 MyBatis 的关系。
核心思想：在 interface 作用域模式下，现有 @RestController 方法无需改动即可成为 MCP 工具。自定义 MCP 实体则使用专用注解（@McpTool、@McpResource、@McpPrompt、@McpComplete）。
顶层授权框架（必读）
本项目 2026-06-24 全面继承姊妹项目
../real-agent的「开发心法」（董事长批准·方案 B）。本节及下方红线、审查、导航均在「自决默认协议」框架下解读。 协议正本：~/.claude/CLAUDE.md顶部 · [ENFORCED] · 优先级高于本文件以下所有具体规范。
核心契约：
- 红线场景（不可逆操作 / 跨系统协议变更 / 全局规范修改 / 战役级启停 / 生产部署 / 删公开 API / 升级 SNAPSHOT 依赖的破坏性变更）→ 必须事前请示董事长，按下方「开发红线总表」执行多源验证等慢档流程。
- 红线之外 → AI 自决，不推送选项给董事长，事后简报（
[DONE] 做了 X · 因 Y · 风险 Z · 回滚成本 W）。
三方独立制衡（中等以上复杂度任务，全局 Rule #6）：架构师（开发，不自写测试）/ 御史台（独立测试 + Code Review，不参与开发）/ CEO（协调验证闭环）。本项目质检 agent 见 .claude/agents/（御史台 imperial-censor）。
Briefback 宣誓：所有 agent 执行前须输出工作协议宣誓六项（任务理解 / 红线清单 / 交付标准 / 绝不会做的事 / 偏离预案 / 环境能力自检），未宣誓 = 产出作废。
开发心法与规范导航
心法继承自
../real-agent，已剥离前端/设计招式、适配本 Java 库语境。单一权威源原则：下方「开发红线总表」是本项目红线的唯一权威源，各 spec 只引用不重复。
通用心法（docs/rules/global/，所有会话默认生效）
| 规则 | 路径 | 核心 |
|---|---|---|
| 搜索工具序位 | docs/rules/global/search-tool-parity.md |
grep（字面量）/ 结构层 / LSP（语义）/ 多模块（图谱）四维不互替 |
| 破坏性删除多源验证 | docs/rules/global/destructive-deletion.md |
[ENFORCED] 删公开 API 前 grep 多形式 + LSP + 跨模块/下游兼容性评估 |
| Session 续接铁律 | docs/rules/global/session-continuity.md |
[ENFORCED] 续接先 git log/status 验证，禁凭记忆断言状态 |
| 重构 commit 顺序 | docs/rules/global/refactor-ordering.md |
[ENFORCED] 契约提供者先行 / 原子 commit，避免契约真空期 |
| Agent 能力声明 | docs/rules/global/agent-capability-declaration.md |
[ENFORCED] 物理不可能性原则，Briefback 第六项环境自检 |
| 工作留痕 | docs/rules/global/work-log.md |
[ENFORCED] 报告类产出 / >30 行结构化产出落 docs/logs/ |
核心规范（docs/specs/）
| 规范 | 路径 | 核心 |
|---|---|---|
| 注册纪律宪法 | docs/specs/REGISTRATION_DISCIPLINE_SPEC.md |
[ENFORCED] 六维成熟度 Rubric + 三把利器（本框架灵魂：注册不遗漏） |
| 文件头规范 | docs/specs/FILE_HEADER_SPEC.md |
[ENFORCED] AI 可读性文件头 @header-start/@header-end 分级模板 |
| 测试规范 | docs/specs/TEST_SPEC.md |
[ENFORCED] 测试金字塔 + TDD 双 commit（[RED]/[GREEN]） |
| 工作留痕规范 | docs/specs/WORK_LOG_SPEC.md |
[ENFORCED] 落文件模板 + Agent 五要素总结 + MUST-WIN 三源验证 |
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.
- 4d ago First seen · 274 lines · 5,501 tokens per session scan A 25182ec25a8d
api2mcp4j CLAUDE.md is an instructions file published in the GitHub repository TheEterna/api2mcp4j (110 stars, last pushed 9d ago), licensed Apache-2.0. It adds 5,501 tokens to every session, about $0.0275 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 instructions, from other repositories
eve AGENTS.md
AGENTS.md instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
AgentEval memory-benchmarks.instructions.md
Guidelines for working with AgentEval Memory module — benchmarks, reporting, HTML reports, and LongMemEval integration.
AgentEval copilot-instructions.md
Copilot instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
AgentEval maf-updates.instructions.md
Instructions for detecting and adapting to Microsoft Agent Framework (MAF) breaking changes.
AgentEval maf-upgrade-preparation.instructions.md
Instructions for analyzing a new MAF version and producing an upgrade plan BEFORE updating the NuGet package.
AgentEval AGENTS.md
AGENTS.md instructions for AgentEvalHQ/AgentEval, covering agenteval development instructions, project overview, quick reference, build & test and key directories.