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/perniemann/pncore/pn-design-systemgit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/rules/perniemann/pncore/pn-design-system)<a href="https://agentmods.dev/rules/perniemann/pncore/pn-design-system"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/pn-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 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
pn-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design system rules
Token Usage
- Use design tokens (CSS variables or theme objects) over raw values for color, spacing, typography, radius, and shadows.
- No one-off hex colors, raw px values, or literal font families in components — use tokens.
- Semantic token names in components (
--color-primary,--space-4). Reserve primitive tokens (--blue-500) for token definition files only. - Keep theme overrides (light/dark) in a single location. Components reference tokens that switch by theme — they don't know about themes directly.
- When adding new values that may be reused: add as a token first. Document intentional one-offs.
Color Tokens (OKLCH)
- Use OKLCH for new color systems — perceptually uniform, better dark mode scaling than HSL.
- Tint neutrals with the brand hue at chroma 0.005–0.01 for subconscious cohesion. Never pure gray.
- Never use
#000or#fff— always tint. Pure black/white don't exist in nature. - Two-layer token hierarchy:
- Primitive:
--blue-500: oklch(60% 0.15 250)— never used directly in components - Semantic:
--color-primary: var(--blue-500)— what components reference
- Primitive:
- Redefine semantics only per theme (e.g.
[data-theme="dark"]); primitives stay defined once.
→ Full primitive/semantic/dark-mode OKLCH token example and palette depth: pn-color-system skill.
Dark Mode Architecture
- Dark mode is not inverted light mode — define independent semantic colors per theme.
- Dark mode depth uses lighter surfaces, not shadows:
--surface-1through--surface-3with increasing lightness. - Desaturate accent slightly in dark mode (reduce chroma by ~0.02).
- Reduce text contrast slightly in dark mode — pure white on pure black strains eyes.
Spacing Tokens
- Use a base-4 or base-8 scale (
--space-1: 0.25remthrough--space-32: 8rem). - Spacing MUST create rhythm: tight spacing (--space-1 to --space-3) within components, generous spacing (--space-12 to --space-24) between sections.
- Never
padding: 24pxeverywhere — different contexts need different densities.
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 · 54 lines · 803 tokens per session scan A 91daf880c45d
pn-design-system is a cursor rule published in the GitHub repository perniemann/pnCore (0 stars, last pushed yesterday), licensed MIT. It adds 803 tokens to every session, about $0.0040 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
t-800-mandatory-routing
ОБЯЗАТЕЛЬНО: создание и правка субагентов, skills, commands, rules, hooks — только через T-800 Agent (цех Skynet). Сначала intake? + scout + research DEEP + brain-lead, затем t-800-factory. Не собирать артефакты ad-hoc в main chat.
t-800-operator-routing
Маршрутизация к T-800 Operator для русскоязычных новичков: первый запуск Cursor, вопросы про Agent/Ask/Plan/Debug, rules, skills, MCP, автоматизацию, просьбы объяснить «на пальцах». Делегируй Task(t-800-operator), не дублируй длинные объяснения в основном чате.
t-800-factory-routing
Маршрутизация к T-800 Factory: создание субагентов, проектирование плагина, интеграция агентов, реестр, граф связей, масштабирование 100+ agents. Делегируй Task(t-800-factory), не создавай агентов ad-hoc в main chat.
t-800-knowledge-refresh
Обновление базы знаний T-800: когда появились новые функции Cursor, устарел manifest (>30 дней), есть UPDATE-QUEUE.md с pending, пользователь спрашивает про фичу которой нет в KB, или после changelog Cursor. В проекте Cursor Junior делегируй обслуживание Task(t-800-maintainer).
t-800-cloud-hub-routing
Маршрутизация Cloud Hub Automation Setup: при /t800-cloud-hub, /t800-hub-setup или правках /cloud-hub/ → Task(t-800-cloud-hub-lead). Не always-on.
codesynapse-cli
Use this rule to answer codebase architecture questions, trace dependencies, find callers/callees, calculate blast radius, and explore the code graph. Triggers on: "how does X work", "what handles Y", "where is Z defined", "explain the mechanism", "who calls", "blast radius", "shortest path", "trace request flow"…