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/cyj0920/jlink_mcp/agents-mdgit clone --depth 1 https://github.com/cyj0920/jlink_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/cyj0920/jlink_mcp/agents-md)<a href="https://agentmods.dev/instructions/cyj0920/jlink_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cyj0920/jlink_mcp/agents-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 | $0.02567 | $0.02567 |
| Opus 5 | $0.01283 | $0.01283 |
| Sonnet 5 | $0.00513 | $0.00513 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
jlink_mcp 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 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JLink MCP - AI Agent 开发指南
项目概述 / Project Overview
JLink MCP 是一个基于 Model Context Protocol (MCP) 的 J-Link 调试器服务器，允许 AI 助手通过标准化接口与 J-Link 硬件调试器交互。
核心功能：
- 设备连接管理（SWD/JTAG）
- 内存读写操作
- Flash 编程（擦除/烧录/校验）
- 调试控制（暂停/运行/单步/断点）
- SVD 寄存器解析
- RTT 实时数据传输
- GDB Server 支持
项目结构 / Project Structure
jlink_mcp/
├── src/jlink_mcp/ # 源代码
│ ├── server.py # MCP 服务器主入口
│ ├── jlink_manager.py # JLink 设备管理器（单例）
│ ├── svd_manager.py # SVD 文件管理器（单例）
│ ├── config_manager.py # 配置管理器（单例）
│ ├── device_patch_manager.py # 设备补丁管理器
│ ├── gdb_server.py # GDB Server 管理
│ ├── exceptions.py # 自定义异常和错误码
│ ├── utils.py # 工具函数
│ ├── models/ # Pydantic 数据模型
│ │ ├── base.py # 基础响应模型
│ │ ├── device.py # 设备相关模型
│ │ ├── operations.py # 操作相关模型
│ │ └── svd.py # SVD 解析模型
│ ├── plugins/ # 设备补丁插件
│ │ └── flagchip_patch.py # Flagchip 设备补丁
│ └── tools/ # MCP 工具函数
│ ├── connection.py # 连接管理
│ ├── device_info.py # 设备信息
│ ├── memory.py # 内存操作
│ ├── flash.py # Flash 操作
│ ├── debug.py # 调试控制
│ ├── rtt.py # RTT 日志
│ ├── svd.py # SVD 寄存器
│ └── guidance.py # 使用指南
├── tests/ # 测试目录
│ ├── unit/ # 单元测试
│ ├── mock/ # Mock 测试
│ └── performance/ # 性能测试
├── docs/ # 文档
├── pyproject.toml # 项目配置
└── pytest.ini # 测试配置
技术栈 / Tech Stack
- Python: 3.10+
- MCP SDK: mcp>=1.26.0
- JLink 库: pylink-square>=2.0.0
- 数据验证: Pydantic>=2.12.0
- 测试: pytest>=8.0.0, pytest-asyncio, pytest-benchmark
开发命令 / Development Commands
安装
# 开发模式安装
pip install -e .
# 使用 UV 安装（推荐）
pip install uv
uv pip install -e .
# 安装开发依赖
pip install -e ".[dev]"
运行
# 启动 MCP 服务器
python -m jlink_mcp
# 或直接运行
jlink-mcp
测试
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 · 341 lines · 2,567 tokens per session scan A bb9f7f880d7f
jlink_mcp AGENTS.md is an instructions file published in the GitHub repository cyj0920/jlink_mcp (33 stars, last pushed 4mo ago), licensed MIT. It adds 2,567 tokens to every session, about $0.0128 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 2026-09-01.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.