sketch

sketch is a skill for Claude Code, Codex from saajunaid/caddis-plugin. It costs 41 tokens per session (1,108 once invoked), scanned A, original, MIT.

A way to create two or three interactive HTML versions of a user interface so different directions can be viewed side by side.

In plain words
What is it for?
Use it for early design exploration, screen sketches, and comparing interface variants.
Why use it?
It makes it easier to compare layout ideas before choosing one for production.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: built for hermes-agent.

Good fit Use it for early design exploration, screen sketches, and comparing interface variants.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saajunaid/caddis-plugin/sketch
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 saajunaid/caddis-plugin --skill sketch
Clone the repo
git clone --depth 1 https://github.com/saajunaid/caddis-plugin

Made for: Claude Code, Codex.

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 sketch

README.md
[![agentmods](https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/sketch/github.svg)](https://agentmods.dev/skills/saajunaid/caddis-plugin/sketch)
Your own site
<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/sketch"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/sketch/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 sketch

Your own site · 80×15
<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/sketch"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/sketch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,108 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 $0.00041 $0.01108
Opus 5.5 $0.00016 $0.00443
Sonnet 5.5 $0.00008 $0.00222
Haiku 4.5 $0.00004 $0.00111

Measured 19d ago against content hash b1f959458913, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sketch 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 19d 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.

.github/skills/frontend/sketch/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sketch

Generate 2–3 contrasting interactive HTML mockups to explore design directions before committing. Produces a side-by-side comparison table with trade-offs and an opinionated recommendation.

This is for exploration, not production. For a polished, framework-feasibility-checked, implementation-annotated mockup ready for handoff, use mockup after a sketch direction is chosen.

When to Use (vs. Alternatives)

Use sketch when... Use mockup when...
Exploring "what could this look like?" A direction is chosen and needs implementation detail
Comparing layout or density stances Need framework feasibility validation
Need 2–3 options to react to Need component annotations + data source mapping
Early ideation, no locked design Ready to hand off to a developer/agent

Process

Step 1 — Intake (3 questions)

Before building anything, get:

  1. Feel / vibe — what emotional response should this UI create? (e.g., "fast and focused", "warm and editorial", "clinical and precise")
  2. Visual references — any sites, apps, or design systems they like? (Optional but valuable)
  3. Primary user action — the ONE thing a user most needs to do on this screen

Step 2 — Variants (2–3 files)

Build variants that take genuinely different design stances. Each variant should differ on at least one of:

  • Density: compact vs airy
  • Emphasis: what's visually dominant
  • Aesthetic: minimal vs expressive, light vs dark
  • Layout: sidebar vs top nav vs cards vs list
  • Hierarchy: flat vs layered, single column vs multi-column

Technical requirements for each variant:

  • Single self-contained HTML file (no build step, no external CSS files)
  • Inline <style> only
  • System fonts OR a single Google Font (<link> tag is fine)
  • Tailwind CDN acceptable (<script src="https://cdn.tailwindcss.com">)
  • Realistic content — no "Lorem ipsum", no "Button 1 / Button 2"
  • Interactive elements: hover states, clickable links, simple state transitions
  • Mobile-responsive (at minimum, don't break on narrow viewports)

Read the full file on GitHub · 105 lines

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. 19d ago Changed · -11 tokens per session b1f959458913
  2. 1mo ago First seen · 105 lines · 52 tokens per session scan A 3f70d24aef81

Subscribe to this mod's changes

sketch is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,108 once invoked, about $0.0002 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 2026-09-03.