An embedded-device verification workflow that checks a development step through building, flashing firmware, debugging with J-Link, and reading serial logs. Firmware is software that runs directly on a microcontroller or other device.

Use it to verify a numbered development step, confirm the firmware reaches its main function, capture startup logs, audit protected files, record results, and prepare a commit suggestion.

It brings the main hardware checks into one recorded process and can block verification when protected files changed without approval.

verify — Command by jzl-maker

Install

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.

agentmods

npx agentmods add commands/jzl-maker/ea-skill/verify

Clone the repo

git clone --depth 1 https://github.com/jzl-maker/EA-SKILL

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 896 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00896
Opus 5	$0.00000	$0.00448
Sonnet 5	$0.00000	$0.00179
Haiku 4.5	$0.00000	$0.00090

Measured 2d ago against content hash ada7132980ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify 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.

commands/verify.md · 66 lines

What it actually says

命令: /ea verify (步骤验证)

功能

对某个开发步骤做验证：编译 → 烧录 → J-Link 运行验证 → 串口日志 四连 + HVR 记录 + 保护区/增量审计 + commit 提议。

触发

/ea verify s<编号>    # 如 /ea verify s7

步骤参数使用 /ea new 分配的 S 编号。

执行流程

【状态目录】 get_state_dir() → <STATE_DIR>
【读 context】 读取 <STATE_DIR>/context.md（芯片/外设/构建入口/保护区基线）
【更新状态】 state.md: 当前步骤 → S<N> 🔄 验证中；project-spec.md 步骤表同步
【四连执行】 加载 workflows/verify-flow.md：
- 编译 build-keil → 成功自动进烧录；失败分析编译日志请求修复
- 烧录 flash-openocd（含校验）→ 成功自动进 J-Link 验证
- J-Link 运行验证 jlink-debug：--regs 读 PC/SP 确认固件进入 main；--rtt 抓启动日志；必要时 --mem 读固件区内存
- 串口 serial-monitor 抓业务启动日志
- 结果记入 HVR 的「执行记录」区段
【保护区/增量审计】 python ~/.claude/skills/ea-skill/tools/shared/project_guard.py --check
- 与 context.md 基线比对：保护区文件有改动且无 approve 记录 → 告警并阻塞验证
- 输出改动清单（供用户确认 diff）
【生成 HVR】 <STATE_DIR>/checkpoints/HVR-<步骤>-<序号>.md（模板 templates/hvr-template.md，嵌入式四连字段内嵌）
【输出验证清单】 待用户口述物理现象的检查点（LED/按键/波形等）
【提议 commit】 见下

commit 提议

━━━━━━━━━━━━━━━━━━━━━━━━━━
💡 提议 commit
建议 commit message:
  [S<step>] feat: verify <步骤描述> with HVR-<序号>

待提交文件:
  M  <STATE_DIR>/checkpoints/HVR-<步骤>-<序号>.md
  M  <STATE_DIR>/state.md
  M  <STATE_DIR>/project-spec.md
  M  <本次实际改动的源文件，来自 diff>

确认提交？[y/n/edit]
━━━━━━━━━━━━━━━━━━━━━━━━━━

输入	行为
`y` / `确认`	`git add` + `git commit -m "..."`
`n` / `取消`	跳过
`edit` / `修改为: ...`	用新 message 重提议

执行约束

✅ 允许 git status / git add / git commit -m "..."
❌ 禁止 git push（必须拒绝并提示手动 push）
❌ 禁止 --no-verify / --force / --amend 等破坏性选项

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 · 66 lines · 0 tokens per session scan A ada7132980ed

Subscribe to this mod's changes

verify is a command published in the GitHub repository jzl-maker/EA-SKILL (6 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 896 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.

Debugging Git and workflow Productivity ai-coding claude-code claude-skills embedded embedded-systems jlink

verify

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

命令: /ea verify (步骤验证)

功能

触发

执行流程

commit 提议

执行约束

相关文件

What this file has done since we first saw it

Other commands, from other repositories

icpg-bootstrap

version

go-review

review-branch

execute

dispatcher