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.
git clone --depth 1 https://github.com/CrashBytes/claude-role-skillsWrote 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/commands/crashbytes/claude-role-skills/design-system)<a href="https://agentmods.dev/commands/crashbytes/claude-role-skills/design-system"><img src="https://agentmods.dev/badge/commands/crashbytes/claude-role-skills/design-system.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 5.1 | $0.00007 | $0.00437 |
| Opus 5 | $0.00003 | $0.00218 |
| Sonnet 5 | $0.00001 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
design-system 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 7d 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.
What it actually says
Design System
Design, initialize, or audit a component design system.
Arguments
Action: $ARGUMENTS
Workflow
If action is init (or no existing system detected):
-
Scaffold design tokens
- Colors: primary, secondary, neutral (8-10 shades), semantic (success, warning, error, info)
- Spacing: 4px base unit scale (4, 8, 12, 16, 24, 32, 48, 64)
- Typography: font families, modular scale (1.25 ratio), line heights
- Shadows: elevation levels (sm, md, lg, xl)
- Borders: radii, widths
- Breakpoints: sm (640px), md (768px), lg (1024px), xl (1280px)
-
Define component API conventions
- Standard props:
size,variant,disabled,className - Composition pattern: composable children over complex prop objects
- Ref forwarding pattern
- Polymorphic
asprop pattern
- Standard props:
-
Generate starter components
- Button (primary, secondary, outline, ghost, destructive)
- Input (text, email, password, with label and error state)
- Card (header, body, footer composition)
If action is audit:
- Scan the codebase for existing components, tokens, and patterns
- Identify inconsistencies: duplicate colors, inconsistent spacing, mixed naming conventions
- Report: what exists, what's missing, what needs consolidation
If action is add-component <name>:
- Generate the component following existing design system patterns
- Include: component file, types, accessible markup, keyboard handling
- Follow existing naming and prop conventions detected in the codebase
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.
- 7d ago First seen · 49 lines · 7 tokens per session scan A 42f7e74116b5
design-system is a command published in the GitHub repository CrashBytes/claude-role-skills (6 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 437 once invoked, about $0.0000 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 commands, from other repositories
customize
Modify site appearance through frontmatter.
color-palette
Generate an accessible colour palette from a hex value.
ux-extract
Exhaustively extract UX patterns from a reference web app into a reusable pattern library.
summary
Generate a consolidated project brief from design artifacts. For the full spec package with YAML specs and validation, use /compile instead.
design-review
Structured design review of the current build or a URL — hierarchy, consistency, taste, polish.
close-sprint
Close the sprint — record Increment + velocity, return unfinished stories/bugs to the backlog.