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 skills/zhinkgit/embeddedskills/openocdnpx skills add zhinkgit/embeddedskills --skill openocdgit clone --depth 1 https://github.com/zhinkgit/embeddedskillsWhat 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 | $0.00247 | $0.04417 |
| Opus 5 | $0.00123 | $0.02209 |
| Sonnet 5 | $0.00049 | $0.00883 |
| Haiku 4.5 | $0.00025 | $0.00442 |
Grade A, and why
openocd 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 2d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenOCD 下载与调试
本 skill 提供 OpenOCD 的探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位、 Telnet 在线调试、GDB 源码级调试和 Semihosting 输出捕获能力。
配置
环境级配置（skill/config.json）
skill 目录下的 config.json 包含环境级配置（工具路径、端口号等），首次使用前确认 exe 路径正确：
{
"exe": "openocd",
"scripts_dir": "",
"gdb_port": 3333,
"telnet_port": 4444,
"gdb_exe": "",
"operation_mode": 1
}
exe：openocd.exe 路径或命令名（必填）scripts_dir：OpenOCD 配置脚本目录，为空时使用 OpenOCD 内置路径gdb_port：GDB Server 端口，默认 3333telnet_port：Telnet 端口，默认 4444gdb_exe：arm-none-eabi-gdb 路径，GDB 调试子命令（run/backtrace/locals）需要operation_mode：1直接执行 /2输出风险摘要但不阻塞 /3执行前确认
工程级配置（.embeddedskills/config.json）
board/interface/target 等工程参数统一在工作区的 .embeddedskills/config.json 中管理：
{
"openocd": {
"board": "",
"interface": "interface/stlink.cfg",
"target": "target/stm32f4x.cfg",
"adapter_speed": "4000",
"transport": "swd",
"tpiu_name": "stm32f4x.tpiu",
"traceclk": "168000000",
"pin_freq": "2000000"
}
}
board：board 配置（如board/stm32f4discovery.cfg），优先级高于 interface+targetinterface：interface 配置（如interface/stlink.cfg）target：target 配置（如target/stm32f4x.cfg）adapter_speed：调试速率 kHztransport：传输协议（swd/jtag）tpiu_name/traceclk/pin_freq：ITM/SWO 观测所需的 TPIU 参数
参数解析优先级：CLI 显式参数 > .embeddedskills/config.json（工程级）> skill/config.json（环境级）> .embeddedskills/state.json > 默认值/报错
成功执行后，确认过的参数会自动写回工程配置。
子命令
基础操作
| 子命令 | 用途 | 风险 |
|---|---|---|
probe |
验证 board 或 interface+target 组合，探测目标连通性 | 低 |
flash |
烧录固件（.elf / .hex / .bin） | 高 |
erase |
擦除目标 Flash | 高 |
reset / reset-init |
复位目标芯片 | 高 |
targets / flash-banks / adapter-info |
查询底层 target / flash / adapter 信息 | 低 |
raw |
执行受控 OpenOCD 原生命令 | 高 |
GDB Server
| 子命令 | 用途 | 风险 |
|---|---|---|
gdb-server |
启动 GDB Server，保持运行等待 GDB 连接 | 低 |
gdb backtrace/locals |
快捷获取调用栈和局部变量 | 低 |
gdb break/continue/next/step/finish/until |
one-shot 执行流控制 | 低 |
gdb frame/print/watch/disassemble/threads/crash-report |
one-shot 源码级诊断 | 低 |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- config.example.json 127 B
- README.md 3.0 KB
- references/common_targets.md 2.7 KB
- scripts/openocd_gdb_common.py 8.1 KB runs code
- scripts/openocd_gdb.py 26 KB runs code
- scripts/openocd_itm.py 18 KB runs code
- scripts/openocd_run.py 25 KB runs code
- scripts/openocd_runtime.py 9.4 KB runs code
- scripts/openocd_semihosting.py 19 KB runs code
- scripts/openocd_telnet.py 28 KB runs code
- templates/flash.cfg 200 B
- templates/gdb_server.cfg 150 B
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.
- 2d ago First seen · 347 lines · 247 tokens per session scan A 3fac6ece22de
openocd is a skill published in the GitHub repository zhinkgit/embeddedskills (610 stars, last pushed 13d ago), licensed MIT. It adds 247 tokens to every session and 4,417 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
robot-perception
Comprehensive best practices for robot perception systems covering cameras, LiDARs, depth sensors, IMUs, and multi-sensor setups. Use this skill when working with RGB image processing, depth maps, point clouds, sensor calibration (intrinsic, extrinsic, hand-eye), object detection, semantic segmentation, 3D…
gpu-use
查看远程服务器 GPU 使用情况。SSH 连接服务器，展示每张卡的显存占用、运行进程、所属容器。当用户说查看 GPU、显卡占用、显存使用时使用.
robotics-software-principles
Foundational software design principles applied specifically to robotics module development. Use this skill when designing robot software modules, structuring codebases, making architecture decisions, reviewing robotics code, or building reusable robotics libraries. Trigger whenever the user mentions SOLID principles…
robotics-design-patterns
Architecture patterns, design principles, and proven recipes for building robust robotics software. Use this skill when designing robot software architectures, choosing between behavioral frameworks, structuring perception-planning-control pipelines, implementing state machines, designing safety systems, or…
robotics-testing
Testing strategies, patterns, and tools for robotics software. Use this skill when writing unit tests, integration tests, simulation tests, or hardware-in-the-loop tests for robot systems. Trigger whenever the user mentions testing ROS nodes, pytest with ROS, launchtesting, simulation testing, CI/CD for robotics, test…
robot-bringup
Bringing up a complete ROS2 system on a robot's onboard computer: systemd services, launch file composition, ordered startup, and production monitoring. Use this skill when configuring a robot to start ROS2 nodes on boot, writing systemd unit files for ROS2 launch, composing layered launch files for full robot stacks…