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 skills add zhinkgit/embeddedskills --skill jlinkgit clone --depth 1 https://github.com/zhinkgit/embeddedskillsWrote 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/skills/zhinkgit/embeddedskills/jlink)<a href="https://agentmods.dev/skills/zhinkgit/embeddedskills/jlink"><img src="https://agentmods.dev/badge/skills/zhinkgit/embeddedskills/jlink/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/skills/zhinkgit/embeddedskills/jlink"><img src="https://agentmods.dev/badge/skills/zhinkgit/embeddedskills/jlink.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00176 | $0.03479 |
| Opus 5.5 | $0.00070 | $0.01392 |
| Sonnet 5.5 | $0.00035 | $0.00696 |
| Haiku 4.5 | $0.00018 | $0.00348 |
Grade A, and why
jlink 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 1mo 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
J-Link 下载与在线调试
本 skill 提供 J-Link 探针的设备探测、固件烧录、内存读写、寄存器查看、目标复位、RTT 日志读取，以及轻量在线调试和 GDB 源码级调试能力。
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": "C:\\Program Files\\SEGGER\\JLink\\JLink.exe",
"gdbserver_exe": "C:\\Program Files\\SEGGER\\JLink\\JLinkGDBServerCL.exe",
"rtt_exe": "C:\\Program Files\\SEGGER\\JLink\\JLinkRTTClient.exe",
"gdb_exe": "C:\\Program Files\\Arm\\GNU Toolchain mingw-w64-x86_64-arm-none-eabi\\bin\\arm-none-eabi-gdb.exe",
"serial_no": "",
"rtt_telnet_port": 0,
"swo_command": [],
"operation_mode": 1
}
exe：JLink.exe 完整路径（必填）gdbserver_exe：JLinkGDBServerCL.exe 路径，RTT 和 GDB 调试需要rtt_exe：JLinkRTTClient.exe 路径gdb_exe：arm-none-eabi-gdb 路径，GDB 源码级调试需要serial_no：默认探针序列号，多探针场景下使用rtt_telnet_port：RTT 端口，0 表示使用工具默认值swo_command：可选，完整 SWO viewer 命令数组，供jlink_swo.py包装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）
设备参数（device/interface/speed）统一在工作区的 .embeddedskills/config.json 中管理：
{
"jlink": {
"device": "STM32F407VG",
"interface": "SWD",
"speed": "4000"
}
}
device：芯片型号（如 STM32F407VG、GD32F470ZG）interface：调试接口，SWD 或 JTAG，默认 SWDspeed：调试速率 kHz，默认 4000
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 device/interface/speed 会自动写回工程配置。
子命令
基础操作
| 子命令 | 用途 | 风险 |
|---|---|---|
info |
探测探针与目标连通性 | 低 |
flash |
烧录固件（.hex / .bin / .elf） | 高 |
read-mem |
读取内存区域 | 低 |
write-mem |
写入内存 | 高 |
regs |
查看 CPU 寄存器 | 低 |
reset |
复位目标芯片 | 高 |
rtt |
读取 RTT 日志输出 | 低 |
swo |
包装外部 SWO viewer 为统一事件流 | 低 |
在线调试（JLink Commander）
| 子命令 | 用途 | 风险 |
|---|---|---|
halt |
暂停 CPU，返回寄存器状态 | 低 |
go |
恢复 CPU 运行 | 低 |
step |
单步执行（支持指定步数），返回执行的指令和寄存器 | 低 |
run-to |
设置断点并运行，等待命中后返回状态 | 低 |
GDB 源码级调试
| 子命令 | 用途 | 依赖 |
|---|---|---|
gdb backtrace/locals |
查看调用栈和局部变量 | arm-none-eabi-gdb |
gdb break/continue/next/step/finish/until |
one-shot 控制执行流 | arm-none-eabi-gdb |
gdb frame/print/watch/disassemble/threads/crash-report |
one-shot 源码级诊断 | arm-none-eabi-gdb |
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 405 B
- README.md 2.4 KB
- references/common_devices.md 1.8 KB
- scripts/jlink_exec.py 22 KB runs code
- scripts/jlink_gdb_common.py 8.4 KB runs code
- scripts/jlink_gdb.py 20 KB runs code
- scripts/jlink_rtt.py 15 KB runs code
- scripts/jlink_runtime.py 10 KB runs code
- scripts/jlink_swo.py 6.4 KB runs code
- templates/flash.jlink 62 B
- templates/read_mem.jlink 67 B
- templates/reset.jlink 46 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.
- 1mo ago First seen · 287 lines · 176 tokens per session scan A 3208ac2f971b
jlink is a skill published in the GitHub repository zhinkgit/embeddedskills (765 stars, last pushed 6d ago), licensed MIT. It adds 176 tokens to every session and 3,479 once invoked, about $0.0007 per session on Opus 5.5. 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
mastra-api
Interact with Mastra development server API for debugging agents, viewing conversation threads, listing/inspecting tools and workflows, accessing observability data, and managing Mastra resources. Use when working with Mastra agents and need to inspect runtime state, debug agent errors, view thread history, see…
d3k
Run and debug a local web app with a managed browser and a shared server/browser evidence timeline. Use when asked to develop, test, or reproduce a browser issue with d3k.
devtools-bidirectional
Two-way event patterns between devtools panel and application. App-to-devtools observation, devtools-to-app commands, time-travel debugging with snapshots and revert. structuredClone for snapshot safety, distinct event suffixes for observation vs commands, serializable payloads only.
devtools-instrumentation
Analyze library codebase for critical architecture and debugging points, add strategic event emissions. Identify middleware boundaries, state transitions, lifecycle hooks. Consolidate events (1 not 15), debounce high-frequency updates, DRY shared payload fields, guard emit() for production. Transparent server/client…
michel-monitor-pull-request-github-actions
Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment. Invoke whenever Michel's CI monitor loop triggers with anyfailure, stuck, or nottriggered — the bash loop already handles pending and allgreen silently, so…
review-agent-harness
Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a…