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 skills add ivy00johns/Skill-Madness --skill claude-design-briefgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/claude-design-brief)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/claude-design-brief"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/claude-design-brief/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.
<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/claude-design-brief"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/claude-design-brief.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00179 | $0.02285 |
| Opus 5 | $0.00089 | $0.01143 |
| Sonnet 5 | $0.00036 | $0.00457 |
| Haiku 4.5 | $0.00018 | $0.00229 |
Grade A, and why
claude-design-brief 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 11d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Design Brief
Naming exception: This skill's name starts with
claude-— a prefix Anthropic reserves for first-party skills. Kept deliberately: the skill targets Claude Design specifically, and a name that doesn't say "claude" would be less discoverable. Perskills/meta/skill-writer/references/frontmatter-spec.md,skill-reviewWARNs but does not FAIL on this pattern when the skill genuinely targets the corresponding Anthropic product.
Produce paste-ready prompts for Claude Design (the artifact/design-canvas tool at claude.ai) that are vivid and project-specific enough that Claude Design has nothing left to ask — it opens its canvas and starts drawing on the first message.
The failure mode the skill exists to prevent: a prompt so vague that Claude Design interrogates scope, tone, palette, typography, hero, device, and a dozen other decisions one at a time. The fix is not to answer those questions in a labeled numbered list — it's to write a design brief dense enough with committed, specific opinion that the questions never arise. How you structure that brief should fit the project, not a template.
Announce at start: "Using claude-design-brief to write a paste-ready Claude Design prompt for [project]."
Sibling vs Mode Selection
This skill is the sibling of ui-brief (which targets Claude Code / production builds, not the Claude Design canvas). It runs in either with-brief mode (a UI-CHALLENGE.md already exists — translate it) or standalone mode (research → Claude Design directly). See references/usage-modes.md for the full comparison table, hallmarks of each mode, what they share, and how the greenfield/rebuild axis layers on top.
Coverage Guide — What Needs To Be In The Brief
These are the decisions Claude Design is likely to lack if you don't address them. Cover each one in whatever form fits the project — as prose, per-direction blocks, embedded in the opening framing, or wherever it lands most naturally. They do not need to be labeled or in any fixed order. The test is not "did I address all 12 categories by name" — it is "does this brief leave Claude Design nothing to ask."
What ships with it
8 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.
- references/anti-patterns.md 3.7 KB
- references/canvas-constraints.md 1.9 KB
- references/direction-examples/bold.md 2.9 KB
- references/direction-examples/experimental.md 3.1 KB
- references/direction-examples/safe.md 2.6 KB
- references/prompt-template.md 9.3 KB
- references/usage-modes.md 3.4 KB
- references/variation-and-risks.md 3.4 KB
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.
- 11d ago First seen · 121 lines · 179 tokens per session scan A cab8147f5a68
claude-design-brief is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed today), licensed MIT. It adds 179 tokens to every session and 2,285 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.