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/debug)<a href="https://agentmods.dev/commands/jzl-maker/ea-skill/debug"><img src="https://agentmods.dev/badge/commands/jzl-maker/ea-skill/debug/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/debug"><img src="https://agentmods.dev/badge/commands/jzl-maker/ea-skill/debug.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 | $0.08484 |
| Opus 5.5 | $0.00000 | $0.03394 |
| Sonnet 5.5 | $0.00000 | $0.01697 |
| Haiku 4.5 | $0.00000 | $0.00848 |
Grade A, and why
debug 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命令: /ea debug (调试)
功能
自主调试五件套，用于「代码跑哪了 / 变量值对不对 / 日志说了什么 / 根因是什么」。双后端：--backend jlink（默认）或 --backend openocd（ST-Link/DAP 用，无停机监控）。
| 能力 | 命令 | 底层工具 | 是否 halt 目标 | 后端 |
|---|---|---|---|---|
| RTT 日志（含历史/取证） | --rtt snapshot |
JLink savebin 直读 RAM |
不 halt | jlink |
| RTT 日志（只能抓新数据） | --rtt start/stop/show |
JLinkRTTLogger.exe | 不 halt | jlink |
| 断点定位 | --bp <函数名/地址> |
JLink Commander SetBP + halt | halt | jlink |
| 内存监视 | --mem <变量名/地址> |
JLink mem32/mem8 | halt（--no-halt 可免） |
jlink |
| 内存监视（免停机） | --mem --no-halt |
JLink savebin 后台读 |
不 halt | jlink |
| 内存监视（免停机） | --mem/--regs |
OpenOCD TCL mdw/reg |
不 halt | openocd |
| 寄存器 | --regs |
JLink regs / OpenOCD reg |
halt（ocd 免） | 两者 |
| 复位+放行 | --reset-run |
JLink Commander r+g |
复位后自由运行 | jlink |
| 源码级调试（可选） | --gdb |
JLinkGDBServerCL + arm-none-eabi-gdb | 由 gdb 控制 | jlink |
零第三方 Python 依赖：只调用 J-Link / OpenOCD 自带可执行文件。
py 是 Windows Python launcher（python 可能是 Store 假别名，勿用）。
后端选择：有 J-Link 用默认 jlink（支持全功能）；只有 ST-Link/DAP 用
--backend openocd（内存/寄存器免断点实时监控，TCLmdw运行中直读不 halt CPU；--rtt/--bp/--gdb/--reset-run仅 jlink 后端支持）。
调用方式
BJ="py <SKILL>/tools/jlink-debug/scripts/jlink_debug.py"
# ① 探测工具链（确认 JLink/RTTLogger/GDBServer 是否可用）
$BJ --detect
# ② RTT 取证：直读 RAM，拿回「已经发生」的历史日志（推荐）
$BJ --rtt snapshot # 控制块地址自动从 .map 的 _SEGGER_RTT 解析
$BJ --rtt snapshot --cb-addr 0x200014DC # .map 里没有时手工指定
$BJ --rtt snapshot --out .ea/logs/rtt.log # 原始字节落盘
$BJ --rtt snapshot --json # 结构化输出
# ③ RTT 轮询：目标跑人工交互测试，过程中反复采样
$BJ --rtt snapshot --duration 420 --interval 5 --out .ea/logs/rtt.log
$BJ --rtt snapshot --poll 20 --interval 5
# ④ 复位 + 放行（配合人工按压测试；也可加在 ② 前面先复位）
$BJ --reset-run
$BJ --rtt snapshot --reset-run --duration 420 --interval 5
# ⑤ RTT 实时日志（只能抓 attach 之后的新数据，须先 start 再复位）
$BJ --rtt start --log .ea/logs/rtt.log
$BJ --rtt stop
$BJ --rtt show --log .ea/logs/rtt.log --tail 50
$BJ --rtt show --log .ea/logs/rtt.log --encoding gbk
# ⑥ 断点定位：函数跑哪了？（.map 符号 → SetBP → go → halt → 报告 PC/寄存器）
# ⚠️ 符号名**必须来自本工程**的 .map —— 先用 --list-symbols <关键字> 查（见「符号解析」）
$BJ --bp <本工程函数名> --run-ms 2000
$BJ --bp 0x08001d28 # 也可直接给地址（Thumb bit 可带可不带）
# ⑦ 内存监视：变量值是多少？
$BJ --mem <本工程变量名> # 默认 4×32bit，halt→读→go
$BJ --mem <本工程变量名> --no-halt --watch 10 # 不打断正在跑的目标
$BJ --mem <本工程变量名> --watch 5
$BJ --mem 0x20020228 --count 8 --width 1
# ⑧ 读寄存器
$BJ --regs
# ⑨ 源码级调试（可选，需 arm-none-eabi-gdb）
$BJ --gdb --elf build/app.axf --gdb-script debug.gdb
# ⑩ ST-Link/DAP 后端：内存/寄存器免断点实时监控（OpenOCD，不 halt CPU）
$BJ --backend openocd --mem <本工程变量名> --watch 10 --interval 0.5
$BJ --backend openocd --regs
# --ocd-if stlink（默认）| cmsis-dap；--ocd-target 指定 target（默认 target/stm32f4x.cfg 通用 Cortex-M4）
# OpenOCD 自动拉起/复用（先查 6666 端口，已开则复用不打扰用户进程）
# 辅助：符号表 / 地址解析（AI 先核对映射再下断点）
$BJ --list-symbols <关键字> # 如 --list-symbols Timer / --list-symbols OM
$BJ --resolve <本工程符号名>
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 9ccf415e33ef
- 1mo ago Changed · +27 lines 92bc0428d150
- 1mo ago Changed · +174 lines af6eb6992c79
- 1mo ago First seen · 151 lines · 0 tokens per session scan A 6d4709a15238
debug 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 8,484 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.