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/scope)<a href="https://agentmods.dev/commands/jzl-maker/ea-skill/scope"><img src="https://agentmods.dev/badge/commands/jzl-maker/ea-skill/scope/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/scope"><img src="https://agentmods.dev/badge/commands/jzl-maker/ea-skill/scope.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 | $0.13927 |
| Opus 5.5 | $0.00000 | $0.05571 |
| Sonnet 5.5 | $0.00000 | $0.02785 |
| Haiku 4.5 | $0.00000 | $0.01393 |
Grade A, and why
scope 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命令: /ea scope (示波器)
功能
两条路径：
A. Rigol 示波器实时 SCPI —— 抓取 + 测量，排查模拟波形/电压/频率。
真机验证状态（两族都已实测，脚本按机型自动适配）：
| 机型 | 固件 | 横向 | 屏幕点数 | 测量命令形式 | 深内存 |
|---|---|---|---|---|---|
| DS1074Z（DS1000Z 族） | 00.04.02.SP3 |
12 格 | 1200 | :MEAS:ITEM? <item>,<ch> |
不可用（:ACQ:MDEP 写不进） |
| DS2302A（DS2000A 族） | 00.03.06 |
14 格 | 1400 | :MEAS:<item>? <ch> |
可用（须先 :STOP） |
两族命令集不通用：DS2000A 上 :MEAS:ITEM 这个节点根本不存在（:SYST:ERR? 回 -113 Undefined header）。脚本用 *IDN? 给初步猜测 + 600ms 短超时实测确认，猜错自动换另一种形式——见注意事项 15。横向格数不写死，取 :WAV:POIN?/100（两族都是 100 点/格）。
下列结论均在这两台机上实测得出，标注了实测数字——换固件/机型需重新复核。
| 能力 | 参数 | 底层 | 依赖 |
|---|---|---|---|
| 波形抓取 | --capture |
:WAV:DATA? + TMC 解析 |
pyvisa + pyvisa-py |
| 电压/时间轴还原 | --capture |
(code-YREF-YOR)*YINC + :WAV:XINC? |
numpy |
| 采样域分析 | --capture |
整数周期内算频率/占空比 + 削顶/平线/噪声/不等周期判定 | numpy |
| 直接测量 | --measure vpp,freq,... |
命令形式按机型探测（可与 --capture 同用） |
pyvisa |
| 前端配置 | --coupling/--vdiv/--voffs/--timebase/--autoset |
:{ch}:COUP/SCAL/OFFS、:TIM:SCAL、:AUT |
pyvisa |
| CSV / PNG | --save / --plot |
numpy + matplotlib | + matplotlib |
| 设备识别 | --detect |
列资源 + 逐个 *IDN? |
pyvisa |
| 无硬件自测 | --parse-tmc <file> |
合成 TMC 块走解析链路（前导由 --yref/--yinc/--yor 给） |
numpy 即可 |
退出码：0=正常 / 1=失败（含参数错误、通道名写错、本机没这个通道、文件不存在、连不上）/ 2=取到数据但不可信（削顶、平线、噪声、不等周期、占空比在窗口内变化、窗口内周期数不足、某项测不出）。Rigol 实时、--parse-tmc、DS100 三条路径同一套语义——解析平线文件也回 2。按 rc 分支时不要把 2 当失败丢弃——数据在，只是需要看 warnings。
SCPI 基本通用，主流品牌（Siglent/鼎阳/泰克等）命令集大同小异，换设备只需调 --resource。
B. 正点原子 DS100 手持示波器（无 SCPI，U 盘导出 CSV） —— 手动导出波形后解析分析。
| 能力 | 参数 | 底层 | 依赖 |
|---|---|---|---|
| 导出 CSV 波形解析 | --parse-ds100 <file.csv> |
跳过 header/自动探测列 + numpy 测量 | numpy 即可 |
| 采样率自动提取 | --parse-ds100 |
正则解析 header sampling rate : N |
numpy |
| 频率/周期/占空比 | --parse-ds100 |
首末上升沿跨度法 + 整数周期占空比（与 Rigol 路径同源） | numpy |
| 波形出图 | --plot |
matplotlib | + matplotlib |
DS100 路径的 sample_domain 与实时路径是同一套判据（flat/irregular/period_cv/duty_irregular/duty_spread_pct/periods），退出码也同一套：平线 → rc=2，窗口内不足 2 个完整周期 → rc=2 并说明占空比不可信。不要只看 freq_hz 有没有值就下结论——平线时它同样是 null，但"测到 0 V"和"没测到"是两件事。
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 · +213 lines 01be04487add
- 1mo ago Changed 5cc711094f3f
- 1mo ago First seen · 165 lines · 0 tokens per session scan A eef7fb21de21
scope 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 13,927 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
embedded-linux
Generate a Yocto or Buildroot config, flashing commands, a kernel module skeleton, or on-target debug commands.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
debug
Start GDB debug session with OpenOCD or probe-rs.
hyperbolic-space
Install (if needed) and run the hyperbolic-space cog on the paired seed.
srs-sm
Draft and QC the Supplementary Materials: scope approval → SM writing → figure QC for SM figures.
checklist
Generate a custom checklist for the current feature based on user requirements.