plan-solution

plan-solution is a skill for Claude Code from Jinchen-Yang/diansai-skill. It costs 83 tokens per session (1,065 once invoked), scanned A, original, MIT.

A skill for choosing electronic components from an event’s approved parts list based on a robot’s documented technical requirements and producing a bill of materials, or BOM.

In plain words
What is it for?
Use it to parse parts lists, match components to subsystems, identify missing items for extra purchase, and create a unified procurement list for review.
Why use it?
It prevents components from being selected without checking voltage, current, interfaces, quantities, or compatibility with the planned design.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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 skills/jinchen-yang/diansai-skill/plan-solution
Any agent
npx skills add Jinchen-Yang/diansai-skill --skill plan-solution
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 plan-solution

README.md
[![agentmods](https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/plan-solution.svg)](https://agentmods.dev/skills/jinchen-yang/diansai-skill/plan-solution)
Your own site
<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/plan-solution"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/plan-solution.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,065 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.01065
Opus 5 $0.00042 $0.00532
Sonnet 5 $0.00017 $0.00213
Haiku 4.5 $0.00008 $0.00106

Measured 6d ago against content hash 5320b9f09e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

plan-solution 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 6d 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/plan-solution/SKILL.md · 62 lines

What it actually says

plan-solution —— 方案 + 需求(流水线 ②)

lane: lead(推理重,建议 Claude) · needs: 无 · : 人工签字需求表

把题目变成"怎么做 + 要满足哪些硬指标"。借鉴金奖经验,别凭空设计。

前置

design/problem.yaml(没有就先跑 /read-problem)。重点看 restrictions.camera_allowed —— 决定视觉路线。

步骤

  1. 查金奖经验/技术栈(Read,不复制):
    • kb/10-典型赛题实战Playbook与Checklist.md —— "典型赛题技术栈组合"表,找与本题 category 最近的一行作起点。
    • kb/09-开源资源与备赛经验.md —— 金奖做法/避坑。
    • kb/06-PID及衍生控制算法.mdkb/08-软件架构与调试工程化.md —— 控制结构。
  2. 定方案(逐子系统):
    • 主控:默认 MSPM0G3507(KB03),需更强算力/FPU 再议 STM32G431。
    • 视觉:camera_allowed=true → K230 做识别/巡线;=false → 纯灰度/电磁,显著标注本届不上 K230
    • 传感:循迹(灰度阵列/电磁/K230)、定位(编码器/IMU/TOF)按题目功能选。
    • 执行:电机+驱动(默认 TB6612+编码电机)、舵机(如需转向/云台)。
    • 控制结构:嵌套 PID(外环位置/航向 ← 视觉/IMU/灰度;内环速度 ← 编码器)+ FSM 跑流程。
  3. 推导需求(硬数字,给后续选材/供电/接线用):
    • 电源轨与电压、每轨最坏电流(电机用堵转)、逻辑电平。
    • 接口清单与数量:要几路 PWM/UART/I2C/SPI/ADC/QEI(对照 MCU 能力表 contracts/mcu/)。
    • 每个外设及其接口、对端连接器。
  4. design/solution.md(模板见下)。
  5. 人工门:把"签字需求表"摊给用户逐项确认;用户没确认的硬指标不要默认,标 TODO。确认后更新 STATUS.md → ③/④,并提示可并行:lead 跑 /setup-env,随后 /select-parts

design/solution.md 模板

# 方案与需求 —— <题目名>
来源: design/problem.yaml  | 类别: <category> | 摄像头: <允许/禁止>

## 技术方案
- 主控: MSPM0G3507(理由…)
- 视觉: K230 / 无(依据 camera_allowed)
- 传感: …  执行: …  控制结构: 嵌套PID + FSM
- 参考金奖技术栈: KB10 <哪一行>

## 子系统清单
| 子系统 | 方案 | 接口 | 备注 |

## 签字需求表(★用户逐项确认)
| # | 需求 | 指标 | 确认 |
|---|------|------|------|
| 电源 | 轨/电压/最坏电流 | … | ☐ |
| 接口数量 | PWMx? UARTx? I2C? ADCx? QEIx? | … | ☐ |
| 每外设接口+电平 | … | … | ☐ |
| 连接器 | … | … | ☐ |

## 待确认/风险(不擅自默认)
- …(源自 problem.yaml.ambiguities)

注意

  • 需求表是后面 select-parts/power-design/interconnect 的输入契约,数字要硬
  • camera_allowed=false 时整条视觉链改纯灰度/电磁,务必在方案顶部红字提示。
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. 6d ago First seen · 62 lines · 83 tokens per session scan A 5320b9f09e5d

Subscribe to this mod's changes

plan-solution is a skill published in the GitHub repository Jinchen-Yang/diansai-skill (9 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,065 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

mspm0-ccs

Tool-neutral CLI agent rules for TI MSPM0 development with Code Composer Studio, Keil/uVision, CMake/GCC/OpenOCD, SysConfig, and DriverLib. Use when an agent needs to inspect or modify MSPM0 projects, edit .syscfg configuration, avoid generated SysConfig/build files, use DriverLib APIs, validate SysConfig output…

mc3545dada/mspm0-skill · 101 tokens

mspm0-skill

Tool-neutral CLI agent rules for TI MSPM0 development with SysConfig, DriverLib, CCS, Keil/uVision, CMake/GCC/OpenOCD, and supported board references. Use when an agent needs to inspect or modify MSPM0 projects, validate SysConfig output, package examples, or work on NUEDC embedded firmware.

Ibook000/mspm0-skill · 76 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

iot-expert

Expert-level IoT systems, embedded devices, edge computing, and IoT protocols. Use when the user mentions embedded, edge computing, MQTT, sensors, or firmware, or when the task involves IoT Architecture, IoT Protocols, Embedded Systems, or Device Design.

personamanagmentlayer/pcl · 59 tokens

embedded-debugging

Debug embedded firmware on real hardware through the jlink-mcp server — crashes, hangs, peripheral misconfiguration, silent devices. Covers loading ELF symbols for source-level backtraces, supplying an SVD for named peripheral fields, and the halt/read/resume discipline. Use whenever debugging a microcontroller over a…

Klievan/jlink-mcp · 77 tokens

agentic-hil

Use when a request operates this project's connected target board through the configured bench (flashing, resetting, probing, debugging, UART and CAN stimulus and feedback, firmware artifacts, test reports) or configures Agentic HIL, the safe local MCP bridge that performs them. Use it instead of invoking a debugger…

agentic-hil/agentic-hil · 104 tokens