Borrowing it
Nothing to install: this file belongs to Jinchen-Yang/diansai-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jinchen-Yang/diansai-skill/main/CLAUDE.mdgit 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/instructions/jinchen-yang/diansai-skill/claude-md)<a href="https://agentmods.dev/instructions/jinchen-yang/diansai-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/jinchen-yang/diansai-skill/claude-md/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/instructions/jinchen-yang/diansai-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/jinchen-yang/diansai-skill/claude-md.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 | $0.01361 | $0.01361 |
| Opus 5 | $0.00681 | $0.00681 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
diansai-skill CLAUDE.md 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 9d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
elec_race — 电控设计智能体（仓库操作规约）
本仓库 = NUEDC 小车队的"设计指挥部"：既是知识库，也是一套 Claude Code 驱动的 skill 流水线。
推理由 Claude Code 完成（Claude Code 是运行时，背后接大模型：lead 用 Claude，队友可接 DeepSeek / GLM 等 API）。我们不在 skill / 工具代码里直接写大模型 API 调用——脏活交给 tools/ 下的纯 Python 脚本（无 LLM 依赖），推理交给 Claude Code 背后的模型。
完整流水线：读题 → 方案+需求 → 环境 → 选材 → 供电 → 接线图 → 固件/视觉骨架 → 测试标定。
团队与 lane（重要）
3 人，各一台电脑、各一个 Claude Code 会话，只通过本 git 仓库 + 文件 + 契约协同（不靠模型对话）：
- lead（控制+软件负责人，Claude Max）：控制 lane + 顶层编排；独占维护
contracts/、env/；负责所有"读 PDF/数据手册"等多模态任务。 - 硬件 lane（队友，可能用 DeepSeek/GLM）：照
design/wiring.svg连线/焊接/供电；只写design/。 - 算法 lane（队友，可能用 DeepSeek/GLM）：K230 视觉；只写
vision/。
目录归属（防 git 冲突，铁律）
| 目录 | 谁可写 |
|---|---|
contracts/、env/、.claude/、tools/、lib/ |
只 lead |
design/ |
硬件 lane（+ lead 跑设计 skill 时） |
firmware/ |
控制 lane |
vision/ |
算法 lane |
kb/（知识库 00~10 + 资源链接总表）、README.md |
人工维护，skill 只读不改 |
- 全员在
main，小步频繁提交；干活前先git pull。 STATUS.md各 lane 只编辑自己那一节。
两个神圣契约（只 lead 改，其余 lane 只读）
contracts/protocol.*— K230↔MCU UART 帧协议。改protocol.yaml后必须python tools/gen_protocol.py重新生成.h/.py，三 lane 再 pull。contracts/pinmap.yaml— 引脚映射。改完必须python tools/pinmux_check.py <file>通过才提交。
契约尽量早冻结、少改：改一次，控制和算法都要 pull 重对。
确定性门优先（不靠模型"觉得对"）
- 引脚正确性 →
tools/pinmux_check.py；协议一致性 →gen_protocol.py自检；固件 → 编译。 - "检查通过" ≠ "设计对"：原理图连接、封装/引脚这类静默错误必须人工逐网核对（见各 skill 的"人工门"）。
- 电源按电机堵转电流算，不是标称。
KB 只作"参考语料"
知识库都在 kb/ 下（kb/00~10 与 kb/资源链接总表.md），是参考知识（引脚说明 / 赛事章程 / 开发流程分工 / 金奖经验），skill 用 Read 查阅（路径如 kb/03-...），不复制进库、不当需求来源、不当器件库存。下文及各 skill 里的 "KBxx"/"第xx篇" 简写均指 kb/ 内对应文件。候选器件来自主办方当年配件表（用户丢进 inputs/partslist/）。常用对照：
01 赛事章程/限制条款 · 02 历年赛题 · 03 主控引脚事实 · 04 电机驱动 · 05 传感器 · 06 PID · 07 K230 帧协议 · 08 软件架构(4层/时间片/FSM/VOFA) · 09 备赛+金奖经验 · 10 实战 Playbook + 现场 checklist + 环境清单
工作流入口
/elec-design— 看全流程编排、当前该做哪一步、3-lane 怎么并行。- 各阶段 skill：
/read-problem/setup-env/select-parts/power-design/interconnect/firmware-scaffold/vision-scaffold/test-checklist（部分在后续 Build Pass 实装）。 - 用户每年把当年题目与主办方配件表（PDF/文本）丢进
inputs/problem/、inputs/partslist/。
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.
- 9d ago First seen · 64 lines · 1,361 tokens per session scan A b186e37f1a38
diansai-skill CLAUDE.md is an instructions file published in the GitHub repository Jinchen-Yang/diansai-skill (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,361 tokens to every session, about $0.0068 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.