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/pymodel/designer-skill/designer-skill-uigit clone --depth 1 https://github.com/PyModel/designer-skillWhat 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 | $0.00311 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
designer-skill-ui 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.
What it actually says
Designer Skill MCP Rule
Before editing or generating any UI, layout, landing page, component, dashboard, or visual design:
- Call
get_preflight_brief. - Call
commit_design_directionand get PASS before writing code:- register:
brandorproduct - one-line design read: surface + audience + visual language
- design variance, motion intensity, and visual density: whole numbers from 1–10
- aesthetic system (one per surface)
- physical scene (one sentence)
- layout families
- typography direction
- anti-slop risks (≥2)
- inverse-test pass + description
- register:
- Call
load_project_contextwhen PRODUCT.md / DESIGN.md may exist. - Call
dispatch_intentand load only the recommended references viaget_reference. - Implement the design.
- Call
review_and_gateon changed files before the final response. - Do not claim completion if
review_and_gatereturns FAIL or blocking slop findings remain.
Foundation: Brief by default → commit direction before code → deep refs on demand → deterministic gate before done.
Copy to .cursor/rules/ in your project, or symlink from this file.
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 · 31 lines · 0 tokens per session scan A 0703886c6e69
designer-skill-ui is a cursor rule published in the GitHub repository PyModel/designer-skill (30 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 311 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 cursor rules, from other repositories
general
Wonder Blocks design system conventions, component patterns, and coding standards.
ar
Source: docs/agents/ar.md Regenerate: npm run agents:sync -w packages/openbridge-webcomponents -->.
taste-enforcement
These dials drive all downstream decisions. Adjust per-prompt when the user specifies a different mood.
interface-micro-polish
Nested surfaces must be mathematically related: outer radius = inner radius + padding.
ux-audit
UX audit and design guidance skill.
cursor-mcp-note
Two MCP servers are registered in .cursor/mcp.json in this directory. JSON does not support inline comments, so the paths and environment notes are explained here.