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 dslsdzc/rev-skills --skill re-hardware-iogit clone --depth 1 https://github.com/dslsdzc/rev-skillsWrote 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/dslsdzc/rev-skills/re-hardware-io)<a href="https://agentmods.dev/skills/dslsdzc/rev-skills/re-hardware-io"><img src="https://agentmods.dev/badge/skills/dslsdzc/rev-skills/re-hardware-io/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/dslsdzc/rev-skills/re-hardware-io"><img src="https://agentmods.dev/badge/skills/dslsdzc/rev-skills/re-hardware-io.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00046 | $0.02652 |
| Opus 5 | $0.00023 | $0.01326 |
| Sonnet 5 | $0.00009 | $0.00530 |
| Haiku 4.5 | $0.00005 | $0.00265 |
Grade A, and why
re-hardware-io 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 11d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
硬件接口（JTAG / UART / Flash 读取）
何时使用 / 何时不用
- 用：有实物板子，需要提取固件、抓启动日志、硬件调试
- 用：JTAG/SWD 调试、UART 串口、flash 芯片直读、逻辑分析仪抓信号
- 不用：只有固件文件（走 [[re-fw-extract]]，硬件提取是最后手段）
- 不用：已解出 rootfs 只需静态分析（走 [[re-fw-rootfs]]）
- 不用：需要运行固件（先试 [[re-fw-emulate]] 更安全、更便宜）
工具准备
所有工具先验证再使用。硬件操作风险高：先万用表测电平、共地、核对丝印再上电（见坑 3/4）。遵循 [[platform-tips]] 先给最轻可行方案：软件手段（文件→解包→仿真）耗尽后再上硬件。
openocd —— JTAG/SWD 调试
- Linux:
apt install openocd/dnf install openocd/pacman -S openocd - macOS:
brew install openocd - Windows:
choco install openocd（或官方 Windows 构建） - 验证:
openocd --version
picocom / minicom —— 串口终端
- Linux:
apt install picocom（或apt install minicom）/dnf install picocom/pacman -S picocom - macOS:
brew install picocom - Windows:
choco install putty（PuTTY 支持串口）或 WSL 内 Linux 版 - 验证:
picocom --version
flashrom —— flash 芯片读取
- Linux:
apt install flashrom/dnf install flashrom/pacman -S flashrom - macOS:
brew install flashrom - Windows: 官方构建或 WSL（编程器 ch341a 在 WSL 内用
flashrom -p ch341a_spi） - 验证:
flashrom --version
逻辑分析仪（sigrok-cli / pulseview）
- Linux:
apt install sigrok-cli pulseview/dnf install sigrok-cli pulseview/pacman -S sigrok-cli pulseview - macOS:
brew install sigrok-cli pulseview - Windows: sigrok 官方 Windows 安装包（sigrok.org）
- 验证:
sigrok-cli --version/pulseview --version
JTAGulator —— 引脚识别板（开源硬件）
- 开源硬件项目
git clone https://github.com/grandideastudio/JTAGulator（含固件与文档）；需自行购买/打样 JTAGulator 板 - 验证: 串口连接后发送
help显示命令清单 - 用它对未知板自动枚举 UART/JTAG 引脚（步骤 1/2 的得力工具）
硬件选购指引（常见方案与电平）
- USB-UART 适配器: CH340 / CP2102 / FTDI 三种芯片方案均可，选支持 3.3V TTL 电平的型号（带 3.3V/5V 跳线更通用）——3.3V 板上插 5V TTL 会烧接口（见坑 3）
- 调试器: ST-Link v2（STM32 系，SWD/JTAG 都支持）、J-Link（通用，授权收费）、CMSIS-DAP/DAPLink（开源固件方案）——按目标芯片厂牌选
- SPI flash 编程器: ch341a（最便宜的 SOIC8 方案）+ 夹子/测试座；多协议需求用 RT809H 类编程器
- 逻辑分析仪: 采样率按信号速率选——UART 115200 与低速 SPI 用 8 通道 24MHz 级别够用；高速 SPI（数十 MHz）需要 100MHz+ 采样（经验值：采样率至少为信号速率的 4 倍）
- 电平转换: 1.8V/2.5V 板子与 3.3V 工具混接时用 TXS0108 类双向电平转换模块
What ships with it
2 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.
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.
- 11d ago First seen · 118 lines · 46 tokens per session scan A 503515598bfd
re-hardware-io is a skill published in the GitHub repository dslsdzc/rev-skills (52 stars, last pushed 12d ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,652 once invoked, about $0.0002 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
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
reverse-engineering-arm-binaries
Reverse engineers ARM/AArch64 malware by identifying the architecture and instruction set state (ARM/Thumb), parsing ELF/Mach-O ARM headers, and orienting analysis around the ARM calling convention. Activates for requests to reverse ARM binaries, analyze AArch64 malware, or handle ARM/Thumb instruction-set decoding.
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
ot-ics-attack
A guide to assessing operational technology and industrial control systems such as SCADA, DCS, and PLC environments. These systems monitor and control physical processes and often use specialized network protocols.
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware using Ghidra with specialized scripts for function recovery, string extraction, and type reconstruction in stripped Go binaries.