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/b1rdmania/ghostclaw/designnpx skills add b1rdmania/ghostclaw --skill designgit clone --depth 1 https://github.com/b1rdmania/ghostclawWrote 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/b1rdmania/ghostclaw/design)<a href="https://agentmods.dev/skills/b1rdmania/ghostclaw/design"><img src="https://agentmods.dev/badge/skills/b1rdmania/ghostclaw/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 | $0.00000 | $0.02545 |
| Opus 5 | $0.00000 | $0.01273 |
| Sonnet 5 | $0.00000 | $0.00509 |
| Haiku 4.5 | $0.00000 | $0.00254 |
Grade A, and why
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 4d 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 — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Skill
Expert design feedback and UI/UX review based on Impeccable principles. Provides actionable critiques on typography, color, spatial design, motion, interaction patterns, responsive design, and UX writing.
Two-Layer Approach
This skill uses a two-layer architecture for efficient, high-quality design feedback:
Layer 1: Anti-Pattern Detection (Fast)
- Speed: Seconds, not minutes
- Cost: Minimal tokens (~500-1K)
- Model: Haiku or fast model
- Purpose: Quickly identify common AI design mistakes
The first pass scans for 11 common anti-patterns that frequently appear in AI-generated designs:
- Bad contrast choices (gray text on colored backgrounds)
- Cardocalypse (excessive card nesting)
- Inter everywhere (no typographic variation)
- Layout templates (repetitive hero metrics)
- Lazy "cool" design (glassmorphism, neon glows, cyan/magenta)
- Lazy "impact" design (gradient text, bouncing animations)
- Massive icons in cards (oversized Lucide icons)
- Modal abuse (complex features in modals)
- Purple gradients everywhere
- Redundant UX writing (triple redundancy)
- Thick border cards (left border accents on rounded cards)
If anti-patterns are found, the feedback includes:
- What the anti-pattern is
- Why it's problematic
- How to fix it with code examples
- Reference to the full anti-patterns guide
Layer 2: Deep Design Review (Thorough)
- Speed: 30-90 seconds
- Cost: Higher tokens (2-5K)
- Model: Sonnet or high-capability model
- Purpose: Comprehensive design critique across all principles
If no anti-patterns are found (or the user requests it), the skill loads the full reference library and provides detailed feedback on:
- Typography: Font pairing, hierarchy, readability, line height, letter spacing
- Color & Contrast: Palette choices, accessibility, semantic color, gradients
- Spatial Design: Layout, spacing, alignment, white space, density
- Motion Design: Animation purpose, easing, duration, reduced motion
- Interaction Design: Affordances, feedback, error states, progressive disclosure
- Responsive Design: Breakpoints, touch targets, mobile-first thinking
- UX Writing: Clarity, tone, microcopy, error messages
What ships with it
18 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.
- commands/apply.md 8.1 KB
- commands/audit.md 21 KB
- commands/enhance/animate.md 8.9 KB
- commands/init.md 7.5 KB
- commands/normalize.md 11 KB
- config/template.md 1.9 KB
- examples/anti-patterns.md 13 KB
- examples/emergence.json 3.3 KB
- examples/minimal.json 1.1 KB
- examples/velocity.json 3.2 KB
- reference/color-and-contrast.md 5.2 KB
- reference/interaction-design.md 4.1 KB
- reference/motion-design.md 4.6 KB
- reference/responsive-design.md 3.4 KB
- reference/spatial-design.md 3.5 KB
- reference/typography.md 5.4 KB
- reference/ux-writing.md 4.2 KB
- skill.json 689 B
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.
- 4d ago First seen · 407 lines · 0 tokens per session scan A 659a9f17ac98
design is a skill published in the GitHub repository b1rdmania/ghostclaw (92 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,545 tokens. 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
render-style
House style for the renderhtml tool — dark dashboard / architecture-diagram look with stat tiles, bar rows, numbered timeline steps, two-panel grids, status pills, connector arrows, callout bands, and verdict blocks. Read this skill before calling renderhtml so the output is visually consistent. Provides CSS tokens…
bio-atac-seq-differential-accessibility
Find differentially accessible chromatin regions between conditions using DiffBind or DESeq2. Use when comparing chromatin accessibility between treatment groups, cell types, or developmental stages in ATAC-seq experiments.
bio-atac-seq-motif-deviation
Analyze transcription factor motif accessibility variability using chromVAR. Use when identifying which TF motifs show variable accessibility across samples or conditions in ATAC-seq data.
figma-expert
Figma design expert for components, auto-layout, design systems, and developer handoff.
accessibility
Build WCAG 2.1 AA compliant websites with semantic HTML, proper ARIA, focus management, and screen reader support. Includes color contrast (4.5:1 text), keyboard navigation, form labels, and live regions. Use when implementing accessible interfaces, fixing screen reader issues, keyboard navigation, or troubleshooting…
subtitles
Use when subtitles or the spoken text of a YouTube video is needed: pasted video links or IDs, requests to translate a video, read along, follow foreign-language content, or extract what was said. Also use for language learning or accessibility. Fetches timestamped subtitles from any YouTube video. Not for uploading…