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/datacovey/nornweave/design-principlesgit clone --depth 1 https://github.com/DataCovey/nornweaveWrote 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/datacovey/nornweave/design-principles)<a href="https://agentmods.dev/rules/datacovey/nornweave/design-principles"><img src="https://agentmods.dev/badge/rules/datacovey/nornweave/design-principles.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 | $0.02723 |
| Opus 5 | $0.00000 | $0.01362 |
| Sonnet 5 | $0.00000 | $0.00545 |
| Haiku 4.5 | $0.00000 | $0.00272 |
Grade A, and why
design-principles 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 5d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Principles
This rule enforces precise, crafted design for enterprise software, SaaS dashboards, admin interfaces, and web applications. The philosophy is Jony Ive-level precision with intentional personality — every interface is polished, and each is designed for its specific context.
Give priority to the shadcn/ui design components.
Design Direction (REQUIRED)
Before writing any code, commit to a design direction. Don't default. Think about what this specific product needs to feel like.
Think About Context
- What does this product do? A finance tool needs different energy than a creative tool.
- Who uses it? Power users want density. Occasional users want guidance.
- What's the emotional job? Trust? Efficiency? Delight? Focus?
- What would make this memorable? Every product has a chance to feel distinctive.
Choose a Personality
Enterprise/SaaS UI has more range than you think. Consider these directions:
Precision & Density — Tight spacing, monochrome, information-forward. For power users who live in the tool. Think Linear, Raycast, terminal aesthetics.
Warmth & Approachability — Generous spacing, soft shadows, friendly colors. For products that want to feel human. Think Notion, Coda, collaborative tools.
Sophistication & Trust — Cool tones, layered depth, financial gravitas. For products handling money or sensitive data. Think Stripe, Mercury, enterprise B2B.
Boldness & Clarity — High contrast, dramatic negative space, confident typography. For products that want to feel modern and decisive. Think Vercel, minimal dashboards.
Utility & Function — Muted palette, functional density, clear hierarchy. For products where the work matters more than the chrome. Think GitHub, developer tools.
Data & Analysis — Chart-optimized, technical but accessible, numbers as first-class citizens. For analytics, metrics, business intelligence.
Pick one. Or blend two. But commit to a direction that fits the product.
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.
- 5d ago First seen · 242 lines · 0 tokens per session scan A a773ed54782f
design-principles is a cursor rule published in the GitHub repository DataCovey/nornweave (27 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,723 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
design
All tasks related to updating frontend components, CSS, and general styling.
antd-design-system
本规范适用于现有使用 Ant Design + antd-style 的组件维护。.
figma-to-code
Cursor rule "figma-to-code" from dtyq/magic, covering figma to code conversion rules, 设计稿转代码流程, 1. 分析设计稿, 2. 组件拆分策略 and 3. 样式实现规范.
figma-shadcn-ui-generate
1:1 Figma design implementation using shadcn/ui, Tailwind CSS, and React. Apply when implementing or converting Figma designs to code, building UI from design specs, or when user mentions Figma URLs or design-to-code.
stfu
STFU mode. Keep Cursor responses direct, concise, and focused on the requested result.
nanoagent-agent-guide
Source-first guide to understanding AI agents — when the user wants to build, debug, or reason about an agent's internals (tool calling, memory, subagents, teams, compaction, safety), route them to the corresponding nanoagent chapter (100 lines of Python each).