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 rules/gosha70/code-copilot-team/design-systemgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWhat 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 | $0.00042 | $0.01580 |
| Opus 5 | $0.00021 | $0.00790 |
| Sonnet 5 | $0.00008 | $0.00316 |
| Haiku 4.5 | $0.00004 | $0.00158 |
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 2d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Protocol
Invoke this skill for any web UI work (new frontend, new screen, UI refactor). Its job: stop AI-generated UI from converging on the statistical mean of the training data ("AI slop") by committing design decisions before code, and enforcing them as a machine-checkable filter.
Root cause it fixes: LLMs emit the highest-probability "nice" defaults —
Inter font, purple→blue gradients, shadcn-default cards, centered hero + three
feature columns, <div onClick> accessibility. No prompt adjective escapes this;
only pre-committed constraints do. This skill produces and enforces those
constraints.
The steering bundle: DESIGN.md + design/tokens.json
Every UI-bearing project commits a bundle, not a prose memo:
DESIGN.mdat repo root — human + machine readable (YAML front-matter tokens- prose rationale and bans).
design/tokens.json— DTCG-format design tokens, two-tier primitive → semantic. Components reference only semantic tokens (else dark mode / re-theming becomes a rewrite). Compiles totokens.css(Tailwind v4@theme→ CSS variables).
If the bundle is missing, author it first (Step 1–2). If it exists, read it before writing any component and build strictly within it.
Step 1 — Derive direction from the business domain (not taste)
"Clean and modern" is the slop default, not a direction. Derive an opinionated direction from the app's domain:
- Brand archetype (pick a primary + secondary from Jung's 12 — Ruler, Hero, Outlaw, Caregiver, Creator, Explorer, Sage, …). Each maps to visual semiotics: Ruler → restrained composition, elegant type, muted+metal; Outlaw → bold edgy type, dark + acid accent; Caregiver → soft, warm, rounded, reassuring.
- Target user + key tasks → information density and IA (a compliance analyst scanning tables ≠ a consumer onboarding flow).
- Tone → voice/copy rules + type personality.
- Lock one aesthetic direction from a small enumerated set (Swiss/editorial, brutalist, industrial-mono, organic, warm-minimal, high-density-data) and commit its tokens.
- Reference-ground: 1–3 real UIs whose feeling matches — extract palette, type scale, density; use to set constraints, never to clone.
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.
- 2d ago First seen · 115 lines · 42 tokens per session scan A 8c53943e7cab
design-system is a cursor rule published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,580 once invoked, about $0.0002 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.