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/liuqihonggit/mcp-cli-bridge/claude-mdgit clone --depth 1 https://github.com/liuqihonggit/mcp-cli-bridgeWrote 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/liuqihonggit/mcp-cli-bridge/claude-md)<a href="https://agentmods.dev/instructions/liuqihonggit/mcp-cli-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/liuqihonggit/mcp-cli-bridge/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 | $0.04391 | $0.04391 |
| Opus 5 | $0.02195 | $0.02195 |
| Sonnet 5 | $0.00878 | $0.00878 |
| Haiku 4.5 | $0.00439 | $0.00439 |
Grade A, and why
mcp-cli-bridge 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - AI行为红线手册
📎 定位: 本文档专注于文件操作、系统命令、工作流程层面的约束
📚 文档分工说明
| 文档 | 定位 | 适用场景 |
|---|---|---|
| CLAUDE.md(本文) | 操作层面红线 | 文件操作、Git命令、工作流程、安全规范 |
| CLAUDE.local.md | 平台本地规则 | Windows/macOS/Linux 平台特定约束(不入Git) |
| 代码规范.md | 编程语法红线 | C#编写禁令、异步编程、代码质量要求 |
| 渐进式执行模式.md | 任务执行手册 | 错误分级处理、渐进式修改流程、回滚机制 |
| 任务并行化.md | /spec模式规范 | 并行任务分解、依赖关系管理 |
| AGENTS.md | 项目架构规则 | 架构依赖、构建发布、环境变量 |
🔴 绝对禁止(触碰即错)
操作禁令
-
⛔ 禁止删除文件(不可协商的安全红线)
这是神圣不可侵犯的规则。违反将导致任务立即失败。
🚫 绝对禁用的工具和命令:
DeleteFile工具(Trae IDE 内置)— 永远不要调用此工具Remove-Item/del/rm命令- 任何形式的文件删除操作
为什么?
- 删除 = 无法回滚 = 灾难性后果
- 丢失审计追踪,无法追溯历史
- 违反渐进式安全原则
✅ 唯一正确做法:移动到
.x/目录- 格式:
.x/{原文件名}.{原后缀}.{时间戳}.del - 平台命令参见
CLAUDE.local.md
-
❌ 禁止使用命令行文本工具直接修改源码文件
- 原因: 可能导致文件损坏或编码问题
- 正确: 使用 IDE 提供的
SearchReplace工具修改文件内容 - 平台细节参见
CLAUDE.local.md2.5. ❌ 禁止删除函数注释(XML 文档注释) - 🚫 禁止: 删除或清空函数/方法上的
/// <summary>等 XML 文档注释 - 原因: 函数注释是代码契约的一部分,删除会导致 IntelliSense 信息丢失、调用方无法理解意图
- 原因: AI 生成代码时容易"顺手"删掉注释,这是不可逆的信息损失
- ✅ 正确做法:
- 函数签名变更时,同步更新注释内容,而非删除
- 注释内容过时时,更新为正确描述,而非清空
- 新增函数时,必须编写 XML 文档注释
-
❌ 禁止使用会卡住交互的命令
- 禁止:
more,less等分页命令 - 禁止:
git commit不带-m参数(会打开编辑器) - 禁止:
npm init等交互式命令(使用-y跳过)
- 禁止:
-
❌ 禁止猜测用户意图/背景/业务场景(规划任务期间)
- 任务规划首先阅读:
AI交互文档/任务并行化.md - 禁止假设用户的具体业务需求、行业背景或隐含意图
- 一旦信息存在模糊地带,基于行业最佳实践自主选择技术方案
- 优先选择保守、安全的实现方式
- 记录决策依据到工作文件末尾(遵循第3条对话偏好)
- 此时推荐使用
AskUserQuestion工具,询问用户是否确认,或者建议其他实现方式
- 任务规划首先阅读:
-
⚠️ 分级交互控制(执行任务期间)
- Level 1-2 禁止交互: 自主决策技术方案,基于上下文选择最合理的实现方式
- Level 3 允许交互: 穷尽所有手段(MCP记忆 → 项目代码 → 可用技能 → 互联网搜索)后仍无法解决时,使用
AskUserQuestion工具请求用户决策 - 📎 详细分级标准见 渐进式执行模式.md > 阶段3
-
⛔ 禁止并行子智能体期间提交 Git
- 每次指派子智能体时,必须告知子智能体当前处于并行期间,禁止执行
git commit/git push - 原因: 并行子智能体操作同一仓库,提交会导致冲突或覆盖他人工作
- ✅ 正确做法: 并行任务全部完成后,由主智能体统一提交
- 每次指派子智能体时,必须告知子智能体当前处于并行期间,禁止执行
-
⚠️ Git 提交前遇到错误时禁止强行提交
- 提交前若遇到错误(如文件锁定、合并冲突),可能是并行子智能体正在操作同一仓库
- 此时禁止执行
git commit,应等待并行任务完成后再统一处理 - 若持续失败,使用
AskUserQuestion工具请求用户决策
-
⛔ 禁止因时间/长度关系中断任务
- 禁止因为输出过长、执行时间过长而中途停止
- 禁止主动询问用户"是否继续"——用户可以随时中断,不需要AI提醒
- 长任务应持续执行直到完成或穷尽所有手段后请求用户决策
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 · 261 lines · 4,391 tokens per session scan A 7ec9ae532d5e
mcp-cli-bridge CLAUDE.md is an instructions file published in the GitHub repository liuqihonggit/mcp-cli-bridge (0 stars, last pushed 3mo ago), licensed MIT. It adds 4,391 tokens to every session, about $0.0220 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
langchain AGENTS.md
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.
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).
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.