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/homenshum/nodebenchai/product_design_dogfoodgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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/homenshum/nodebenchai/product_design_dogfood)<a href="https://agentmods.dev/rules/homenshum/nodebenchai/product_design_dogfood"><img src="https://agentmods.dev/badge/rules/homenshum/nodebenchai/product_design_dogfood.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 | $0.00346 |
| Opus 5 | $0.00000 | $0.00173 |
| Sonnet 5 | $0.00000 | $0.00069 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
product_design_dogfood 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.
What it actually says
Product Design Dogfood (Jony Ive Review)
Ship quality is proven in the running UI, not in a diff.
Definition of done (UI-visible)
When you claim a UI change is “done”, it must be verifiable inside the app UI:
- Dogfood route exists:
/dogfoodloads. - Evidence is viewable:
/dogfoodshows a gallery or clear “missing artifacts” instructions. - Screenshots are current: after dogfooding, publish the screenshot manifest so the UI can render it (
npm run dogfood:publishornpm run dogfood:full:local).
Dogfood protocol (route-by-route)
For every route/screen touched (and adjacent screens with shared layout):
- First-impression clarity: can a new user explain what to do in 5 seconds?
- Hierarchy: one primary action; secondary actions are visually quiet.
- Typography: headings are not shouting; body text is readable; no gray-on-black mush.
- Spacing: consistent rhythm; avoid random padding/margins; align baselines.
- States: empty/loading/error states look intentional (not a blank white card).
- Interactions: focus rings, keyboard navigation, hover/press states, scroll containment.
Mandatory mindset
Follow analyst_diagnostic:
- Diagnose the root cause (render path, data ownership, stored vs computed).
- Fix the cause so the bug becomes impossible, not merely hidden.
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 · 31 lines · 0 tokens per session scan A c955fc5da776
product_design_dogfood is a cursor rule published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 346 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
figma-performance
Handling large documents efficiently in the Plugin API.
ant-design
本规范为在 React 应用程序中使用 Ant Design (antd) UI 库的项目制定最佳实践和编码标准。涵盖代码组织、性能、安全、测试和常见陷阱，确保应用程序的可维护性和高效性。.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.
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.
cli-error-handling
CLI command error handling patterns.