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 skills add Jinchen-Yang/diansai-skill --skill elec-designgit clone --depth 1 https://github.com/Jinchen-Yang/diansai-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/skills/jinchen-yang/diansai-skill/elec-design)<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/elec-design"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/elec-design/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/skills/jinchen-yang/diansai-skill/elec-design"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/elec-design.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 | $0.00088 | $0.01193 |
| Opus 5.5 | $0.00035 | $0.00477 |
| Sonnet 5.5 | $0.00018 | $0.00239 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
elec-design 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 2mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
elec-design —— 顶层编排
lane: lead（编排建议在 lead/Claude 会话跑） · needs: 无（只读状态 + 调度）
你是这支 3 人电赛小车队的电控设计编排者。不要自己埋头跑完整条流水线；你的职责是：判断现在在哪一步、派发下一步、让三个人并行别空等、把守人工门。重活交给对应子 skill（必要时 run_in_background 起子代理）。
先读 CLAUDE.md 了解仓库规约（lane 分工、目录归属、契约只读、确定性门优先）。
完整流水线（9 段）
| # | skill | 输入 | 产出 | 门 |
|---|---|---|---|---|
| ① | read-problem |
inputs/problem/ 当年题目 |
design/problem.yaml |
— |
| ② | plan-solution |
problem.yaml + KB金奖/技术栈 | design/solution.md(方案+需求) |
人工签字 |
| ③ | setup-env |
solution(选定主控/视觉) + KB环境清单 | env/manifest.yaml + 三lane setup |
— |
| ④ | select-parts |
solution + inputs/partslist/配件表 |
design/bom.csv |
人工批 BOM |
| ⑤ | power-design |
solution + bom | design/power.{md,yaml} |
人工批供电 |
| ⑥ | interconnect |
bom + power | design/wiring.svg + contracts/pinmap.yaml + harness.md |
逐网人工核对 |
| ⑦ | firmware-scaffold |
solution | firmware/(工程+protocol.h+VOFA) |
外设 init 核对 |
| ⑧ | vision-scaffold |
solution | vision/(CanMV+protocol.py) |
— |
| ⑨ | test-checklist |
problem + KB10 | design/test_plan.md |
— |
全部 9 段 skill 均已实装。完整走查样例见
examples/sending-medicine-2023/；sh tools/selftest.sh一键验证全链路（协议两端一致/pinmux门/供电门/接线渲染/固件主机测试/跨语言契约/语法检查）。
你每次被调用时的动作
- 探当前状态（只读）：读
STATUS.md；ls inputs/ design/ env/ firmware/ vision/；看哪些产物已存在、契约版本。 - 定位阶段：按上表，找出"已完成的最后一段"和"下一段"。
- 派发 + 并行安排：告诉用户下一步调哪个 skill；同时列出此刻三个 lane 各自能独立做什么（见下"并行原则"）。
- 把守门：遇到带"人工门"的产物，未签字不得推进下一段；提示用户确认。
- 更新 STATUS：推进后更新
STATUS.md对应小节（只动该动的 lane 段）。
并行原则（比赛现场，谁都别空等）
- 解锁件优先：先出能让硬件动手的件（→
interconnect的接线图）；纯软件/文档往后放、后台并行出。 - 两个共享契约最先锁死：
contracts/pinmap.yaml、contracts/protocol.*——定了它，控制和算法各写各、最后对得上。 - 三 lane 天然可并行：硬件=照接线图连（依赖④⑥）；算法=K230 上独立开发（只依赖
protocol.py，几乎不等小车电路）；控制=固件可离线写（依赖引脚映射+协议），只有实机 bring-up 等硬件。 - 抢跑：人执行某段产物时，你用
run_in_background推进不依赖人反馈的下一段。 - 同步点：只有"硬件就绪可烧录""三方汇合整车联调"这种才真的等；其余往前抢。
异构模型
needs: multimodal 的步骤（read-problem、select-parts 解析 PDF）只在 lead/Claude 会话跑。队友的 DeepSeek/GLM lane 消费 lead 产出的 design/*.yaml，干代码活（firmware/、vision/），正确性交编译/pinmux_check 等确定性门。
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.
- 2mo ago First seen · 50 lines · 88 tokens per session scan A dd2788e093b3
elec-design is a skill published in the GitHub repository Jinchen-Yang/diansai-skill (12 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,193 once invoked, about $0.0004 per session on Opus 5.5. 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.
elec-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| elec-designJinchen-Yang/diansai-skill | Skill | 12 | 3mo ago | MIT | A | 88 | Claude Code |
| mspm0-ccsmc3545dada/mspm0-skill | Skill | 378 | 3mo ago | MIT | A | 101 | Claude Code, Codex |
| mspm0-skillIbook000/mspm0-skill | Skill | 13 | 1mo ago | MIT | A | 76 | Claude Code, Codex |
| volt-otatonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 70 | Claude Code |
| volt-firmwaretonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 76 | Claude Code |
| agentic-hilagentic-hil/agentic-hil | Skill | 24 | yesterday | Apache-2.0 | A | 104 | Claude Code |
| iot-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 59 | Claude Code |