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/hotic/protools/agents-mdgit clone --depth 1 https://github.com/hotic/protoolsWhat 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 | $0.00671 | $0.00671 |
| Opus 5 | $0.00336 | $0.00336 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
protools AGENTS.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 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
AGENTS.md
ProTools MCP Server 项目指南,供 AI 代理参考。
项目概述
这是一个 MCP (Model Context Protocol) Server,提供代码合并和 AI 代码审查功能。
技术栈:TypeScript, Node.js, Zod, MCP SDK
核心模块
LLM Provider (src/core/llm/)
支持两个 Provider:
- OpenAI: GPT-5.2,使用 Responses API,支持 JSON 格式约束
- Gemini: Gemini 3 Flash,支持 thinking_level 配置
两者都实现了:
- 超时控制(AbortController)
- 指数退避重试(429/5xx)
- JSON 格式强制输出
代码审查 (src/tools/code-review.ts)
主要功能:
- 同步审查:
executeCodeReview - 异步任务:
startCodeReviewTask/getCodeReviewTaskStatus - 支持 Git diff 模式和文件路径模式
- 多模型并发审查,使用
Promise.allSettled容错
审查子模块 (src/tools/review/)
拆分的子模块:
task-store.ts: 任务存储、状态管理、LRU 清理report-generator.ts: Markdown 报告生成result-processor.ts: 结果验证(Zod)和多模型合并
开发规范
代码风格
- 使用 ESM 模块(
import,不用require) - 类型定义使用 Zod Schema
- 异步操作使用
async/await - 文件操作优先使用
fs.promises
错误处理
- LLM 调用需要超时和重试
- 使用
Promise.allSettled处理并发,允许部分失败 - Zod
safeParse校验外部输入,失败时尝试修复
Prompt 设计
- 模板在
src/prompts/templates/review.ts - 代码内容放在 Prompt 最后
- 强调务实审查,避免过度工程化建议
常见任务
添加新工具
- 在
src/types/创建输入 Schema - 在
src/tools/实现工具逻辑 - 在
src/index.ts注册server.tool()
添加新 LLM Provider
- 继承
BaseLLMProvider - 实现
doChat方法 - 在
src/core/llm/index.ts注册
修改审查 Prompt
编辑 src/prompts/templates/review.ts 中的模板常量。
测试
# 编译
npm run build
# 重启 MCP Server(在 IDE 中)后测试
注意事项
- 审查结果需要批判性分析,不是所有问题都需要修复
- 环境变量配置在 MCP 配置文件中,不在
.env - 异步任务存储在内存中,服务重启后丢失
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 · 92 lines · 671 tokens per session scan A 12439b884859
protools AGENTS.md is an instructions file published in the GitHub repository hotic/protools (1 stars, last pushed 7mo ago), licensed MIT. It adds 671 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.