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.
git clone --depth 1 https://github.com/jzl-maker/EA-SKILLWrote 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/commands/jzl-maker/ea-skill/la)<a href="https://agentmods.dev/commands/jzl-maker/ea-skill/la"><img src="https://agentmods.dev/badge/commands/jzl-maker/ea-skill/la/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/commands/jzl-maker/ea-skill/la"><img src="https://agentmods.dev/badge/commands/jzl-maker/ea-skill/la.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.05232 |
| Opus 5.5 | $0.00000 | $0.02093 |
| Sonnet 5.5 | $0.00000 | $0.01046 |
| Haiku 4.5 | $0.00000 | $0.00523 |
Grade A, and why
la 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命令: /ea la (逻辑分析仪)
功能
Saleae 逻辑分析仪（Logic 8 / Logic 16 / Pro 8 / Pro 16）抓取 + 协议解码，用于排查 UART/SPI/I2C 等总线时序。
| 能力 | 参数 | 底层 | 依赖 |
|---|---|---|---|
| 数字/模拟抓取 | --capture |
Logic 2 Automation API | Logic 2 软件 + logic2-automation |
| 边沿触发抓取 | --trigger-channel / --trigger-edge |
DigitalTriggerCaptureMode |
同上 |
| 协议解码（看帧结构） | --decoder |
add_analyzer + export_data_table |
同上 |
| 软件解码（取字节值） | --decode-uart / --decode-spi / --decode-i2c |
waveform.py 直接解 digital.csv |
仅标准库 |
| 通道素描 | --export-raw 自动 |
waveform.py 统计每通道 |
仅标准库 |
| 原始数据导出 | --export-raw |
export_raw_data_csv（写目录） |
同上 |
| 捕获保存/复用 | --save / --load |
save_capture / load_capture |
同上 |
| 波形图 | --plot |
numpy + matplotlib | + numpy/matplotlib |
| 无硬件自测 | --simulate |
Logic 2 内置模拟设备 | Logic 2 软件即可 |
与 jlink-debug 不同：这是唯一依赖第三方 pip 包 + 后台 GUI 软件的工具。Logic 2 软件需单独安装（winget install Saleae.Logic2 或官网下载），且抓取前需开启「脚本服务器」。
调用方式
py <SKILL>/tools/instrument/scripts/logic_analyzer.py --detect
# ✅ 确认依赖 / Logic 2 软件 / 脚本端口 10430
# 无硬件自测：模拟设备抓 0.5s + I2C 解码 + 出图
py .../logic_analyzer.py --simulate --capture --duration 0.5 \
--decoder "i2c:SCL=0,SDA=1" --export-raw --save sim.sal --plot la.png
# 真实抓取：4 通道 10M 采样 2s + UART 解码
py .../logic_analyzer.py --capture --channels 0,1,2,3 --sample-rate 10000000 \
--duration 2 --decoder "uart:TX=0,RX=1,Bit Rate (Bits/s)=115200" --export-raw
# 复用已有 .sal 重新解码
py .../logic_analyzer.py --load trace.sal --decoder "spi:CLK=0,MOSI=1,MISO=2"
# 拿精确字节（不经 Logic 2 解码器，自动开 --export-raw）
py .../logic_analyzer.py --capture --channels 7 --duration 2 \
--decode-uart "ch=7,baud=auto"
# SPI：按片选切帧，mode 明给（给定 mode 不靠猜）
py .../logic_analyzer.py --capture --channels 0,1,2,3 --sample-rate 10000000 \
--duration 1 --decode-spi "clk=0,mosi=1,miso=2,cs=3,mode=0,bits=8"
# I2C：直接解出 START/地址/读写位/ACK/NACK
py .../logic_analyzer.py --capture --channels 4,5 --duration 2 \
--decode-i2c "scl=4,sda=5"
# 抓偶发事件：只录 ch7 下降沿之后 0.2s，不必硬录满全程
py .../logic_analyzer.py --capture --channels 7,15 --sample-rate 10000000 \
--trigger-channel 7 --trigger-edge falling --duration 0.2 --export-raw
# 纯逻辑核对（不碰设备，打印将执行的 API 序列）
py .../logic_analyzer.py --dry-run --capture --decoder "spi:CLK=0,MOSI=1,MISO=2,Enable=3"
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 Changed · +1 lines 753f64cfbc64
- 1mo ago Changed · +74 lines 6541358e2898
- 1mo ago First seen · 109 lines · 0 tokens per session scan A abc536b846e1
la is a command published in the GitHub repository jzl-maker/EA-SKILL (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,232 tokens. 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.
Other commands, from other repositories
cortex-m
Generate Cortex-M startup code or a linker script, configure a core subsystem, decode a fault, or add DWT timing.
debug-embedded
Attach a debugger, halt and inspect a target, decode fault registers, or configure ITM, SWO, or ETM trace.
esp-debug
Help debug ESP32 crashes, hangs, and peripheral issues.
hw-bringup
Drive the hardware bring-up checkpoint ladder when something won't come up.
debug
Start GDB debug session with OpenOCD or probe-rs.
fix
Command "fix" from mantacron/manta, covering usage, instructions, step 1: choose the report, step 2: extract findings and step 3: run remediation-agent.