agentmods.dev

master-go-to-code

master-go-to-code is a skill for Claude Code from willnie9/agent-skills. It costs 94 tokens per session (5,670 once invoked), scanned A, original, MIT.

A tool that turns a MasterGo design file—a browser-based interface design—into structured files describing the page, vector shapes, and image resources.

In plain words
What is it for?
Use it when converting a MasterGo screen or layer into materials that another workflow can assemble into a Vue frontend.
Why use it?
It reduces the manual work of reading a design and collecting its visual assets before building the interface.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

not rated 2repo 2mo ago A scan 94 tokens original MIT

Good fit Use it when converting a MasterGo screen or layer into materials that…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/willnie9/agent-skills/master-go-to-code
View source ↗ willnie9/agent-skills
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 willnie9/agent-skills --skill master-go-to-code
Clone the repo
git clone --depth 1 https://github.com/willnie9/agent-skills

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 master-go-to-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/willnie9/agent-skills/master-go-to-code.svg)](https://agentmods.dev/skills/willnie9/agent-skills/master-go-to-code)
Your own site
<a href="https://agentmods.dev/skills/willnie9/agent-skills/master-go-to-code"><img src="https://agentmods.dev/badge/skills/willnie9/agent-skills/master-go-to-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,670 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 $0.00094 $0.05670
Opus 5 $0.00047 $0.02835
Sonnet 5 $0.00019 $0.01134
Haiku 4.5 $0.00009 $0.00567

Measured 6d ago against content hash 754726eb275b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

master-go-to-code 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.

The scan reads SKILL.md. This mod also ships 12 executable files (scripts/compare-pixel.mjs, scripts/compare-tokens.mjs, scripts/extract-image-names.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

master-go-to-code/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Master-Go-to-Code · 视觉还原流水线

Auto Mode(无确认模式)

触发:用户输入含任一关键词 → 全跑 / 一气呵成 / auto / yolo / 别问 / 自动,或被 module-flow 委托(auto 透传)。

行为:

  • 跳过所有"报告 + 等用户继续"检查点(Step 1 报告下载数 / Step 2 报告 dom-tree 大小)
  • compare-tokens.mjs 失败不阻断(verdict=fail 也继续,落 issues 给上层处理)

保留:

  • Step 2 validate-dom-tree.mjs 失败必停(schema 错下游全废)
  • 铁律 1-5 不变

决策

本 skill 专做"设计稿 → dom-tree.json + svg-paths.json + 图片资源"。永远委托给 module-flow / frontend-page-design 完成 Vue 组装(不在本 skill 直出)。

用户给 MasterGo URL
  │
  ├─ 含 auto 关键词 ──→ 直接进 Step 1,跳所有检查点
  └─ 默认           ──→ Step 0 自检后进 Step 1,Step 1-2 完后给报告等用户继续

工作流（3 个 Step + 1 个委托点 + 1 个回收验证)

Step 1 拉资源 + 切 chunk → Step 2 分块精修 + 合并 + 校验 → Step 3 渲染预览 + 自检 → Step 4 委托 → Step 5 token diff 回收。

Step 0 · Reconnaissance（自检）

启动前必须通过:

# 1. MCP 可用性
test -n "$(grep MASTERGO_TOKEN .env)"           # Token 存在(在项目根 .env 或 skill 父级)
# 2. skill 自带脚本齐全
test -f .claude/skills/master-go-to-code/scripts/fetch-and-parse.mjs
# 3. skill 依赖装好(首次使用前)
test -d .claude/skills/master-go-to-code/node_modules/sharp \
  || (cd .claude/skills/master-go-to-code && npm install)
# 4. 解析 URL → fileId + layerId(从 ?layer_id= 提取)

任一失败即停,告诉用户具体原因。

Step 1 · 提取资源 + 切分 chunk

1.1 拉 DSL + 资源
# 默认: 下载图片 + 提取 SVG path + SVG → PNG (2x 图,适合直接当图片用)
node .claude/skills/master-go-to-code/scripts/fetch-and-parse.mjs <fileId> <layerId> <imgDir>

# 选项: 项目要保留 SVG(轻量/缩放无损),加 --keep-svg 关闭 PNG 转换
node .claude/skills/master-go-to-code/scripts/fetch-and-parse.mjs <fileId> <layerId> <imgDir> --keep-svg

# 选项: 想要有意义的英文文件名(user-mgmt.png 而不是 716-294400.png)
node .claude/skills/master-go-to-code/scripts/fetch-and-parse.mjs <fileId> <layerId> <imgDir> --icon-names=<path/to/icon-names.json>

imgDir 推断规则见 references/imgdir-mapping.md。 SVG → PNG 详细说明 + icon-names 映射格式见 references/svg-to-png.md。

产物目录(下文统称 <outDir>):默认 .claude/skills/master-go-to-code/output/ —— 跨项目复用 skill 时,产物落在 skill 自身目录,不污染项目根。可被以下机制覆盖(优先级从高到低):

  1. 命令行参数(部分脚本支持)
  2. 环境变量 MASTERGO_OUT_DIR
  3. (历史)project.config.json.mastergoOutput.outDir 仍兼容

Read the full file on GitHub · 381 lines

Files

What ships with it

23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 381 lines · 94 tokens per session scan A 754726eb275b

Subscribe to this mod's changes

master-go-to-code is a skill published in the GitHub repository willnie9/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 5,670 once invoked, about $0.0005 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.

Autonomous AgentsDesign and UXFrontendai-agentsai-workflowbug-fixingci-cd-pipelineclaude-code-skill
Related

Other skills, from other repositories

aceternity-ui

100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.

secondsky/claude-skills · 48 tokens

base-ui-react

MUI Base UI unstyled React components with Floating UI. Use for accessible components, Radix UI migration, render props API, or encountering positioning, popup, v1.0 rc / pre-GA issues.

secondsky/claude-skills · 47 tokens

julilaoshi-design

Public-safe julilaoshi-design workflow for official Pencil MCP execution and the free browser-first julilaoshi-design Web 2.0 editor. Use when a task needs Pencil handshake/canvas edits, .pen execution, screenshot review, or lightweight HTML design-to-web tweaking without redistributing official Pencil or leaking…

julilaoshi/julilaoshi-design · 68 tokens

google-fonts

Google Fonts typography system generator. Suggests single fonts (strict mode) and font pairs (contrast mode) with complete typographic scales following Tailwind Typography rhythm concepts. Generates CSS custom properties, Tailwind config, and embed links. Trigger: "choose a font", "font pairing", "typography system"…

sliday/google-fonts-skill · 117 tokens

3d-web-experiences

Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…

madebyaris/advance-minimax-m3-cursor-rules · 147 tokens

frontend-taste

Premium frontend design skills that override LLM defaults. Prevents generic 'AI-looking' UI. Enforces deterministic typography, calibrated color, asymmetric layouts, spring physics, hardware-accelerated motion. Triggers: 'UI tasarla', 'design a UI', 'premium landing page', 'frontend taste', 'anti-slop', 'dashboard…

fatihkan/badi · 104 tokens