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 agentmods add commands/jzl-maker/ea-skill/debuggit clone --depth 1 https://github.com/jzl-maker/EA-SKILLWhat 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 | $0.00000 | $0.03077 |
| Opus 5 | $0.00000 | $0.01538 |
| Sonnet 5 | $0.00000 | $0.00615 |
| Haiku 4.5 | $0.00000 | $0.00308 |
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 yesterday.
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 — 151 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
自主调试四件套，用于「代码跑哪了 / 变量值对不对 / 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 | 依赖 |
|---|---|---|---|
| RTT 打印日志 | --rtt |
JLinkRTTLogger.exe（channel 0） | J-Link |
| 断点定位 | --bp <函数名/地址> |
JLink Commander SetBP + halt | J-Link |
| 内存监视 | --mem <变量名/地址> |
JLink mem32/mem8 或 OpenOCD TCL mdw/mdh/mdb | J-Link 或 OpenOCD |
| 寄存器 | --regs |
JLink regs 或 OpenOCD TCL reg |
J-Link 或 OpenOCD |
| 源码级调试（可选） | --gdb |
JLinkGDBServerCL + arm-none-eabi-gdb | + GNU 工具链 |
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，适合--watch持续采样看变量变化；--rtt/--bp/--gdb仅 jlink 后端支持）。
调用方式
# ① 探测工具链（确认 JLink/RTTLogger/GDBServer 是否可用）
py ~/.claude/skills/ea-skill/tools/jlink-debug/scripts/jlink_debug.py --detect
# ② 启动 RTT 日志抓取（先启动 logger，再触发复位，避免错过启动消息）
py .../jlink_debug.py --rtt start --log .em/logs/rtt.log
py .../jlink_debug.py --rtt stop
py .../jlink_debug.py --rtt show --log .em/logs/rtt.log --tail 50
# ③ 断点定位：函数跑哪了？（.map 符号 → SetBP → go → halt → 报告 PC/寄存器）
py .../jlink_debug.py --bp Display_BootDoraemon --run-ms 2000
py .../jlink_debug.py --bp 0x08001d28
# ④ 内存监视：变量值是多少？（符号名或地址）
py .../jlink_debug.py --mem _TimeCount_10ms # 默认 4×32bit
py .../jlink_debug.py --mem _TimeCount_10ms --watch 5 # 持续采样 5 次
py .../jlink_debug.py --mem 0x20020228 --count 8 --width 1
# ⑤ 读寄存器
py .../jlink_debug.py --regs
# ⑥ 源码级调试（可选，需 arm-none-eabi-gdb）
py .../jlink_debug.py --gdb --elf build/app.axf --gdb-script debug.gdb
# ⑦ ST-Link/DAP 后端：内存/寄存器免断点实时监控（OpenOCD，不 halt CPU）
py .../jlink_debug.py --backend openocd --mem _TimeCount_10ms --watch 10 --interval 0.5
py .../jlink_debug.py --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）
py .../jlink_debug.py --list-symbols Display
py .../jlink_debug.py --resolve Display_BootDoraemon
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.
- yesterday First seen · 151 lines · 0 tokens per session scan A 6d4709a15238
debug is a command published in the GitHub repository jzl-maker/EA-SKILL (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,077 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
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
version
Display current guide and Claude Code versions.
go-review
Go code review for idiomatic patterns.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
execute
Executa o plano aprovado em .first-plan/07-state/plans/. Segue o plano à risca, para se algo invalidar premissa, gera relatório ao final.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.