Borrowing it
Nothing to install: this file belongs to FlySun1116/HCL-Lab_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/FlySun1116/HCL-Lab_mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/FlySun1116/HCL-Lab_mcpWrote 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/flysun1116/hcl-lab_mcp/claude-md)<a href="https://agentmods.dev/instructions/flysun1116/hcl-lab_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/flysun1116/hcl-lab_mcp/claude-md/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/instructions/flysun1116/hcl-lab_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/flysun1116/hcl-lab_mcp/claude-md.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 | $0.03770 | $0.03770 |
| Opus 5 | $0.01885 | $0.01885 |
| Sonnet 5 | $0.00754 | $0.00754 |
| Haiku 4.5 | $0.00377 | $0.00377 |
Grade A, and why
HCL-Lab_mcp 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 9d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HCL-Lab_mcp 项目规则
本文件是 Claude Code、兼容 Claude Code 的模型服务以及 Agent Team 在本仓库工作的长期规则。进入仓库后先读本文件，再读 docs/design.md。不要仅凭历史对话或模型记忆重新解释项目。
1. 项目身份
- 项目：
HCL-Lab_mcp - GitHub：
https://github.com/FlySun1116/HCL-Lab_mcp.git - Python distribution：
h3c-hcl-mcp - Python import package：
h3c_hcl_mcp - 许可证目标：Apache-2.0，最终以仓库
LICENSE为准 - 主要平台：Windows + H3C Cloud Lab 5.10.x
- 主要语言：Python 3.12
- MCP SDK：官方 MCP Python SDK 的稳定版本线
这是一个独立运行的通用 MCP Server，不是 Claude、Cursor 或某个模型专用插件。任何兼容 MCP 的 Client 都应能使用相同的 Tool Schema。
2. 产品目标
让 MCP Client 能够：
- 发现用户自己的 HCL 项目、设备和链路；
- 判断 HCL 设备运行态和本机 console 可用性；
- 通过 HCL loopback Telnet console 或设备 SSH 执行受控 Comware CLI；
- 查询设备 facts、接口、配置和诊断结果；
- 在后续版本通过计划、审批、基线校验和审计执行配置变更；
- 分析实验拓扑并辅助网络实验。
当前阶段聚焦 HCL/H3C。架构需允许未来增加其他设备 adapter，但 v0.x 不提前实现 Huawei、Cisco、Juniper。
3. 事实来源优先级
发生冲突时按以下顺序执行：
- 用户在当前会话中的明确要求；
- 安全、许可和平台权限限制；
docs/design.md中已批准的架构与版本范围；- 已接受的 ADR；
- GitHub Issue 的验收条件；
- 本文件；
- 其他文档和历史提示词。
不要重新设计已在 docs/design.md 固化的内容。需要改变公共 Tool、Port、错误码、安全模型或版本范围时，先提交 ADR/设计差异并请求一次重要决策确认。
4. 首次接管流程
首次进入一个工作目录时，先做接管分析，不直接写业务代码：
- 执行
git rev-parse --show-toplevel、git status --short --branch、git remote -v； - 如果是有效 Git 仓库，执行
git fetch --all --prune，仅在工作树安全时执行git pull --ff-only； - 不使用会覆盖本地改动的 pull、reset、checkout 或 clean；
- 阅读
CLAUDE.md、docs/design.md、现有 ADR、README、CONTRIBUTING、HANDOVER 和当前 Issue；缺失文件记录为待办，不虚构内容； - 检查当前分支、未提交改动、已有代码、测试、CI 和最近提交；
- 输出接管报告：仓库状态、当前版本、已完成内容、架构边界、风险、阻塞项和建议任务图；
- 首次接管报告完成后，再按 Issue 或用户目标自主开发。
如果目录不是有效 Git 仓库，不删除现有文件。报告该事实；本地 git init、建立 feature branch等可逆操作可以自主进行，但首次建立/推送远端 main 属重要操作，必须请求一次确认。
5. 自主工作原则
除“必须确认”事项外，不要因为普通实现选择反复询问用户。先检查仓库和文档，做最合理、最小范围、可回滚的决定，完成实现与验证，并在交接记录假设。
默认自主执行，不需要逐步确认
- 搜索、阅读和分析项目代码、文档、测试、Git 历史；
- 读取任务范围内的本机 HCL 项目格式、脱敏日志和只读运行信息；
- 创建短期 feature/fix/docs/refactor 分支；
- 新建或修改任务范围内的源码、测试、文档、示例和合成 fixtures；
- 修复 lint、类型、测试、构建和文档问题；
- 运行测试、MCP Inspector、构建、静态检查和安全扫描；
- 安装锁文件已有依赖；添加小型、维护活跃、许可证兼容且确有必要的依赖；
- 执行非破坏性 Git 操作：status、diff、log、fetch、pull --ff-only、add、commit；
- push 当前非保护 feature 分支，创建或更新 Draft PR；
- 根据 CI 结果继续修复，直到通过或出现真实阻塞；
- 更新 README、CHANGELOG、兼容矩阵和 HANDOVER；
- 对低风险细节作出合理假设并明确记录。
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.
- 9d ago First seen · 295 lines · 3,770 tokens per session scan A aaae20f02067
HCL-Lab_mcp CLAUDE.md is an instructions file published in the GitHub repository FlySun1116/HCL-Lab_mcp (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 3,770 tokens to every session, about $0.0188 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.