agentmods.dev

interconnect

interconnect is a skill for Claude Code from Jinchen-Yang/diansai-skill. It costs 117 tokens per session (805 once invoked), scanned A, original, MIT.

A hardware wiring procedure that maps modules to microcontroller pins and produces a wiring diagram and connection table. A microcontroller is the small computer that controls embedded hardware.

In plain words
What is it for?
It is for assigning GPIO, PWM, UART, I2C, ADC, and encoder connections, running pin checks, rendering wiring files, and guiding manual verification of power and signal connections.
Why use it?
It reduces wiring mistakes by checking pin capabilities and conflicts before the hardware is connected.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

not rated 12repo 3mo ago A scan 117 tokens original MIT

Good fit It is for assigning GPIO, PWM, UART, I2C, ADC, and encoder connections, running pin checks, rendering wiring files, and guiding manual verification of power and signal connections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jinchen-yang/diansai-skill/interconnect
View source ↗ Jinchen-Yang/diansai-skill
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.

Any agent
npx skills add Jinchen-Yang/diansai-skill --skill interconnect
Clone the repo
git clone --depth 1 https://github.com/Jinchen-Yang/diansai-skill

Made for: Claude Code.

Wrote 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.

agentmods badge for interconnect

README.md
[![agentmods](https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/interconnect/github.svg)](https://agentmods.dev/skills/jinchen-yang/diansai-skill/interconnect)
Your own site
<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/interconnect"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/interconnect/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.

agentmods 80×15 button for interconnect

Your own site · 80×15
<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/interconnect"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/interconnect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.00805
Opus 5.5 $0.00047 $0.00322
Sonnet 5.5 $0.00023 $0.00161
Haiku 4.5 $0.00012 $0.00081

Measured 2mo ago against content hash a41a2461aa12, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

interconnect 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.

.claude/skills/interconnect/SKILL.md · 28 lines

What it actually says

interconnect —— 模块接线图（流水线 ⑥）

lane: 任何模型产 YAML（正确性交 pinmux_check.py） · 门: pinmux PASS + 逐网人工核对

这是 scope-A 的心脏：人照它连线。正确性靠确定性门 + 人工逐网核对，不靠模型"觉得对"。

前置

design/bom.csv（选了哪些模块）+ design/power.yaml（供电轨）+ lib/modules/（接法块）+ contracts/mcu/<MCU>.yaml（引脚能力）。

步骤

  1. 列对 MCU 网络：对 BOM 每个模块，读其 lib/modules/<block>.yaml，取 to_mcu: true 的脚（PWM/GPIO/UART/I2C/ADC/QEI…）。没有现成块就按 KB 03/04/05 引脚说明补一个最小块到 lib/modules/。
  2. 分配主控引脚：从 contracts/mcu/<MCU>.yaml 给每条网络挑一个支持该功能、且未被占的引脚；同类外设实例（UART/I2C/QEI…）注意不超数量上限。I2C/SPI 总线多模块共享同一对引脚（只占一次）。
  3. 写 contracts/pinmap.yaml（结构见 contracts/pinmap.schema.yaml，照 contracts/pinmap.example.yaml）。
  4. 跑确定性门：python tools/pinmux_check.py contracts/pinmap.yaml。FAIL（撞脚/非法功能/超限）就改分配，重跑直到 PASS。
  5. 渲染：python tools/render_wiring.py contracts/pinmap.yaml design/wiring → design/wiring.svg（接线图）+ design/harness.md（接线表）。
  6. 人工门（高危·必做）：让用户逐网核对 harness.md，重点：电源/GND、K230 串口 TX↔RX 交叉、I2C 上拉、舵机独立供电、SWD 没被占。核对打勾后才交硬件 lane。
  7. 更新 STATUS.md：硬件 lane 段贴 design/wiring.svg、阶段→可连线；契约版本记 pinmap vX。

注意

  • pinmap 是神圣契约（CLAUDE.md）：改完必过 pinmux_check 才提交，并通知控制 lane 重 pull（固件 SysConfig 据此生成）。
  • MCU 能力表 verified:false 时，pinmux PASS 只保证逻辑自洽；真实引脚复用要 lead 用 SysConfig 核（读手册=多模态）。
  • 接线图一出，硬件 lane 即可开工——这是解放人手的解锁件，优先最先交付。
Changes

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.

  1. 2mo ago First seen · 28 lines · 117 tokens per session scan A a41a2461aa12

Subscribe to this mod's changes

interconnect is a skill published in the GitHub repository Jinchen-Yang/diansai-skill (12 stars, last pushed 3mo ago), licensed MIT. It adds 117 tokens to every session and 805 once invoked, about $0.0005 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.

Claude CodeHardware and IoTagent-skillsembeddedk230mspm0nuedc
Related

interconnect compared with skills from other repositories

interconnect next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
interconnectJinchen-Yang/diansai-skillSkill123mo agoMITA117Claude Code
mspm0-ccsmc3545dada/mspm0-skillSkill3783mo agoMITA101Claude Code, Codex
mspm0-skillIbook000/mspm0-skillSkill131mo agoMITA76Claude Code, Codex
volt-otatonone-ai/tononeSkill7723d agoMITA70Claude Code
volt-firmwaretonone-ai/tononeSkill7723d agoMITA76Claude Code
agentic-hilagentic-hil/agentic-hilSkill24yesterdayApache-2.0A104Claude Code
iot-expertpersonamanagmentlayer/pclSkill4411d agoApache-2.0A59Claude Code