What is beidou-cli CLAUDE.md?

Repository instructions for BeiDouMS's command-line tool, which uses HTTP requests to operate a server console and can compile into a native executable.

Building the Java command-line tool, producing a JAR or GraalVM native executable, and updating reflection settings when commands or data models change.

They collect the project's build commands, technology choices, architecture, and rules for keeping native compilation working.

beidou-cli CLAUDE.md — Instructions file by BeiDouMS

Install

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.

agentmods

npx agentmods add instructions/beidoums/beidou-cli/claude-md

Clone the repo

git clone --depth 1 https://github.com/BeiDouMS/beidou-cli

Per session 2,041 This file is loaded in full into every session.

When invoked 2,041 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02041	$0.02041
Opus 5	$0.01020	$0.01020
Sonnet 5	$0.00408	$0.00408
Haiku 4.5	$0.00204	$0.00204

Measured 3d ago against content hash 6b75fc80cd0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

beidou-cli 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 3d 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.

CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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

beidou-cli 是 BeiDou-Server 的命令行工具，供 AI agent 通过 HTTP API 操作服务端控制台。编译目标为 GraalVM Native Image 原生二进制。

构建

mvn package -DskipTests          # fat JAR（shade 插件自动打包依赖）
mvn package -DskipTests -Pnative # GraalVM 原生二进制（需要 GraalVM JDK 21）

输出：target/beidou-1.0-SNAPSHOT.jar 或 target/beidou（原生二进制）。

原生构建也可用脚本：./build-native.sh（macOS/Linux）、build-native.bat（Windows，需 Visual Studio 2022+ C++ 桌面开发）。

技术栈

CLI: picocli 4.7.6（子命令模式）
HTTP: java.net.http.HttpClient（JDK 内置，native-image 兼容）
JSON: Jackson 3.1.3（tools.jackson 命名空间），annotation 混用 com.fasterxml.jackson（来自传递依赖），两者需同时在 reflect-config.json 中注册
构建: Maven shade 插件打 fat jar，org.graalvm.buildtools:native-maven-plugin 按 -Pnative profile 进行原生编译
反射配置: src/main/resources/META-INF/native-image/reflect-config.json（picocli 命令类、model 类、Jackson 节点类），新增 model 或命令类需同步更新该文件。注意 tools.jackson.databind.node.ObjectNode 和 com.fasterxml.jackson.databind.node.ArrayNode 两个包名混用，都需要注册

架构

Main.java  ──>  ConfigCommand   (beidou config / beidou config --show)
           ──>  LoginCommand    (beidou login)
           ──>  CallCommand     (beidou call <METHOD> <path> [body] [--force])
           ──>  BatchCommand    (beidou batch — 从 stdin 逐行读取，格式: METHOD /path [body])
           ──>  VersionCommand  (beidou version)
           ──>  ApiListCommand  (beidou apis [keyword])
           ──>  UpdateCommand   (beidou update — 从 GitHub Releases 下载覆盖当前二进制)
           ──>  UninstallCommand(beidou uninstall — 删除二进制 + 清理 PATH)
                     │
         CallCommand ─┴──> ApiClient ──> AuthManager ──> CliConfig
         BatchCommand ─┘        │              │
                                  │   login ─────┘ POST /auth/v1/login
                                  │   parseJwtExpiry ─  Base64 解码 payload.exp
                                  │
                                  └──> sendRequest ──> java.net.http.HttpClient

Read the full file on GitHub · 89 lines

Changes

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.

3d ago First seen · 89 lines · 2,041 tokens per session scan A 6b75fc80cd0a

Subscribe to this mod's changes

beidou-cli CLAUDE.md is an instructions file published in the GitHub repository BeiDouMS/beidou-cli (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,041 tokens to every session, about $0.0102 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.

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).

microsoft/vscode · 6,785 tokens

beidou-cli CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

项目概述

构建

技术栈

架构

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

codex AGENTS.md

langchain AGENTS.md

vscode oss-third-party-notices.instructions.md

next.js AGENTS.md