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.
npx agentmods add skills/dinhanhthi/coding-friend/cf-designnpx skills add dinhanhthi/coding-friend --skill cf-designgit clone --depth 1 https://github.com/dinhanhthi/coding-friendWrote 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/skills/dinhanhthi/coding-friend/cf-design)<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-design"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-design.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.02297 |
| Opus 5 | $0.00038 | $0.01149 |
| Sonnet 5 | $0.00015 | $0.00459 |
| Haiku 4.5 | $0.00008 | $0.00230 |
Grade A, and why
cf-design 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 5d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cf-design
CLI Requirement: NONE — Works without
coding-friend-cli. See CLI requirements for the full matrix.
Design UI with intent and consistency: $ARGUMENTS
Modes
Three modes, triggered by the first word of $ARGUMENTS:
| Invocation | Mode | Purpose |
|---|---|---|
/cf-design scan [path] |
Scan | Read existing UI files → extract design patterns → save to docs/DESIGN.md |
/cf-design [description] |
Design | Implement new UI from the user's description, using existing patterns as a base |
/cf-design modify [what] -- [how] |
Modify | Change a specific UI element, enforcing consistency with existing patterns |
If $ARGUMENTS is empty, ask the user which mode they want and what their goal is.
Step 0: Custom Guide
Custom guide — auto-loaded below (if the raw command shows instead of its output, run it yourself):
bash "<plugin-root>/lib/load-custom-guide.sh" cf-design
If output is non-empty, integrate returned sections: ## Before → before first step, ## Rules → apply throughout, ## After → after final step.
Step 0.5: Load Existing Design Context
Run: bash "<plugin-root>/skills/cf-design/scripts/load-design-context.sh"
- If
DESIGN.mdexists: read it now and keep it in working memory for all subsequent steps. This is the project's source of truth for visual style. - If not found: note that patterns are unknown and will either be extracted (scan mode) or defined fresh.
Step 1: Determine Mode
Parse $ARGUMENTS:
- Empty → ask the user: "What would you like to do? (a) scan existing UI patterns, (b) design something new, or (c) modify a specific element?"
- First word is
scan(case-insensitive) → Scan mode (Step 2) - First word is
modify(case-insensitive) → Modify mode (Step 4) - Anything else → Design mode (Step 3)
What ships with it
3 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.
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.
- 5d ago First seen · 208 lines · 76 tokens per session scan A 89479665285d
cf-design is a skill published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,297 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.
Other skills, from other repositories
web-design-engineer
Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…
animated-sketch-diagram
生成"黑墨手绘涂鸦"风格的动画架构图/流程图：米色纸面、针管笔墨线、极淡水洗色块、简笔涂鸦图标、序号章、连线上的流动圆点动画、图标微动效。产出单文件自包含动画 HTML（SVG+CSS），可一键导出无缝循环 GIF。当用户想画架构图、流程图、信息图、技术示意图、对比图、pipeline/workflow 可视化，或提到"手绘风""涂鸦风""动图""animated diagram""GIF 架构图"时使用；即使用户没明说要动画，做技术概念科普配图时也应优先考虑本 skill。.
webflow-mcp:interactions
Create, update, list, and delete Webflow IX3 interactions (GSAP animations) through Webflow MCP. Use when the user wants click/hover/load/scroll/mouse-move animations, interaction timelines, or datainteractionstool / createinteraction payloads. Requires beta MCP + ff-ix3-interaction-apis during dogfood.
webflow-mcp:flowkit-naming
Apply Flowkit CSS naming system in Webflow. Use when creating classes, auditing existing naming, or building new components following Flowkit conventions. Flowkit is Webflow's official CSS framework with utility-first approach. Runs headlessly against a page ID — no Designer connection required, except for the…
ardot-style-guide
从头设计或为 Ardot 项目应用视觉主题时使用此技能。 涵盖 searchstyleguide → buildstyleguide 工作流程，用于发现和应用完整的设计系统（颜色、排版、间距、布局模式）。 触发条件："设计落地页"、"创建仪表板"、"应用深色主题"、 "设置设计系统"、"选择调色板"、"为应用选择字体"、 "样式指南"、"视觉风格"、"外观和感觉"。.
printed-curtain-render
Generate a browser-based p5.js curtain simulation that weaves user-supplied PNG, JPEG, or WebP artwork and optional text into individually moving strands. Use when users ask for an interactive curtain or thread simulation, artwork woven into cloth or ropes, image-bearing fabric motion, 可交互线帘/幕布, 图片织入布料, printed…