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/helpgit 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 | $0.00795 |
| Opus 5 | $0.00000 | $0.00398 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
help 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 2d 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.
What it actually says
命令: /ea help (帮助)
功能
显示命令列表或指定命令的详细帮助。
触发
/ea help [命令]
无参数时
显示命令表（19 个）：
嵌入式 AI 开发管家 — /ea 命令
环境/项目:
setup 环境工具初始化（权限 / 工具路径 / CLAUDE.md 触发器）
init <name> 新项目初始化（建 context + 基线快照）
si [path] 存量项目接入（代码审计 + context + 基线快照）
rec [name] 恢复项目（state + context 摘要）
stat [-v/steps/next] 状态查看
开发流程:
new <描述> 新功能开发（轻档 quick-plan / 标准档 brainstorm+milestones）
test unit <文件|函数> 生成并运行纯函数 host 单测（用例 .md + 代码 .c）
test board <功能> 生成板级工装验收用例（用例 .md + 板载测试固件/驱动脚本）
嵌入式工具:
build 编译（Keil UV4）
flash 烧录（OpenOCD）
serial 串口监控（CLI/MCP）
debug 调试（J-Link RTT/断点/内存/寄存器；OpenOCD ST-Link/DAP 免断点监控）
svd SVD 寄存器地图（外设 / 位域 / 枚举 + 免断点读值）
la Saleae 逻辑分析仪（抓取 / 协议解码）
scope Rigol 示波器（波形抓取 / 测量）
size 固件资源分析（Flash/RAM/栈 + 超限预警）
map Map 文件解析（对象排行 / 分段分布 / 符号映射）
验证/记录:
verify s<N> 步骤验证（HVR + 编译→烧录→J-Link 验证→串口 + 保护区审计）
record s<N> 输出修改记录（文件清单 + diff + 测试证据）
help [命令] 查看帮助
有参数时
显示指定命令的详细帮助：
/ea help setup # 环境初始化
/ea help init # 新项目初始化
/ea help si # 存量接入
/ea help new # 新功能开发两档
/ea help test # 测试生成（unit / board）
/ea help verify # 验证流程 + 保护区审计
/ea help debug # 调试（J-Link / OpenOCD 双后端）
/ea help svd # SVD 寄存器地图
/ea help la # 逻辑分析仪
/ea help scope # 示波器
/ea help size # 固件资源分析
/ea help map # Map 文件解析
/ea help record # 修改记录
红线提醒
任何命令执行中都需遵守 SKILL.md 红线：保护区文件禁随意改、老工程增量修改、所有修改给 diff、GBK 编码。
相关文件
commands/<cmd>.md— 各命令完整定义workflows/— 工作流细则SKILL.md— 总览 + 红线规则
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.
- 2d ago First seen · 72 lines · 0 tokens per session scan A dd7e71e21ff5
help is a command published in the GitHub repository jzl-maker/EA-SKILL (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 795 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
analyze-repo
Analyze an existing repository's structure, conventions, and guardrails.
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.
doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
example-only
This command documents how to dispatch. Example only.
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.