agentmods.dev

vision-scaffold

vision-scaffold is a skill for Claude Code from Jinchen-Yang/diansai-skill. It costs 99 tokens per session (782 once invoked), scanned A, original, MIT.

A starter code structure for visual software running on a K230 camera board with CanMV, a Python-based camera platform. It processes camera images and sends results to a main controller.

In plain words
What is it for?
Use it to build line following, colored-object tracking, and digit recognition, while grouping camera settings and sending results over the defined serial connection.
Why use it?
It gives vision code a consistent structure and keeps messages between the camera board and controller aligned.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is protocol.py # 从 ../contracts/ 复制(勿手改).

not rated 12repo 3mo ago A scan 99 tokens original MIT

Good fit Use it to build line following, colored-object tracking, and digit recognition, while grouping camera settings and sending results over the defined serial connection.

Compare 6 skills from other repositories ↓
View source ↗ Jinchen-Yang/diansai-skill
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Jinchen-Yang/diansai-skill
agentmods
npx agentmods add skills/jinchen-yang/diansai-skill/vision-scaffold

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 vision-scaffold

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/vision-scaffold"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/vision-scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 782 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 $0.00099 $0.00782
Opus 5.5 $0.00040 $0.00313
Sonnet 5.5 $0.00020 $0.00156
Haiku 4.5 $0.00010 $0.00078

Measured 2mo ago against content hash 491aa7717bfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vision-scaffold 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/vision-scaffold/SKILL.md · 39 lines

What it actually says

vision-scaffold —— K230 视觉骨架（流水线 ⑧，算法 lane）

lane: 算法（DeepSeek/GLM 擅长代码） · 门: 语法检查 + 现场标阈值

K230 是独立板，可桌面独立开发。发帧只用 contracts/protocol.py（与主控 protocol.h 同源同签名，杜绝漂移）。

前置

design/solution.md（视觉要做什么）、contracts/protocol.py（已生成）。

生成结构（写到 vision/）

vision/
  README.md          # CanMV 烧录/运行(指向 env/vision.md), 镜像版本锁定提醒
  main.py            # 主循环: 取流 → 处理 → 用 protocol.py 发帧
  line_follow.py     # 巡线: 取一行/多行, 求中线偏差 error(int16)
  blob_track.py      # 色块/光点: find_blobs → cx,cy
  digit_recog.py     # 门牌数字: KPU/模板, 出 class_id+confidence
  protocol.py        # 从 ../contracts/ 复制(勿手改)
  config.py          # ★ 阈值/ROI/曝光 占位, 现场标定

步骤

  1. main.py：CanMV 初始化（sensor/lcd），主循环里按当前任务调 line_follow/blob_track/digit_recog，把结果用 protocol.line_error()/blob_xy()/target_class() 经 UART 发出。硬件相关 import（sensor/image/lib）放运行时，保证主机 py_compile 语法可过。
  2. line_follow.py：灰度/二值化取中线，输出 error（中线相对画面中心的偏差，int16）。阈值放 config.py。
  3. blob_track.py：find_blobs 取最大色块 cx,cy。
  4. digit_recog.py：KPU 模型或模板匹配，出 class_id+confidence；连续 N 帧一致才采信（防误识，呼应 KB08 FSM）。
  5. config.py：所有阈值/ROI/曝光/串口波特(115200)集中放，标"现场标定"。
  6. 复制 contracts/protocol.py 到 vision/。
  7. 门：README 写运行步骤 + 镜像版本须与队伍锁定一致；阈值现场标（见 test-checklist）。

与主控对接

  • 帧格式由 contracts/protocol.py 决定；改协议找 lead 改 protocol.yaml 重生成，不要在 K230 端硬编。
  • 联调：K230 发 → 主控 k230_uart.c 的 proto_parse_byte 收，串口助手可旁观 AA 55 .. 0D。
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 · 39 lines · 99 tokens per session scan A 491aa7717bfe

Subscribe to this mod's changes

vision-scaffold is a skill published in the GitHub repository Jinchen-Yang/diansai-skill (12 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 782 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.

Claude CodeHardware and IoTagent-skillsembeddedk230mspm0nuedc
Related

vision-scaffold compared with skills from other repositories

vision-scaffold next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vision-scaffoldJinchen-Yang/diansai-skillSkill123mo agoMITA99Claude 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