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/reexamine_design_reductiongit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWhat 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 | $0.00781 |
| Opus 5 | $0.00000 | $0.00391 |
| Sonnet 5 | $0.00000 | $0.00156 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
reexamine_design_reduction 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Re-examine: Design Reduction (Jony Ive Principles)
Core philosophy
Every element must earn its place. The default answer to "should we add this?" is no. Reduction is not simplification — it's the discipline to remove everything that doesn't serve the user's immediate task.
Kill jargon
- Replace technical terms with plain language users would use
- "Act I/II/III" → "Quick Pulse / Analysis / Deep Dive"
- "Orchestrator" → "Agent", "Trajectory" → "History", "Recon" → "Research"
- "Pipeline" → "Workflow", "Schema" → "Structure", "Emit" → "Send"
- Test: would a non-technical person understand this label in 2 seconds?
Vanity metrics
- Remove stats that don't drive user action (streak counters, "free runs today", total counts without context)
- Keep only metrics that answer "what should I do next?"
- If a number doesn't change behavior, it's decoration — remove it
Earned complexity
- Every tab, button, toggle, and section must justify its existence
- Default: fewer tabs. Combine related content before splitting into separate tabs
- Settings: group by user mental model (Profile, Account, Usage, Integrations), not by feature
- If a feature is used by <10% of users, hide it behind progressive disclosure
Dark patterns
- No auto-expanding panels that steal focus
- No notification badges that never clear
- No "are you sure?" dialogs for reversible actions
- No hidden scroll areas with invisible scrollbars
Tab/surface reduction
- Prefer 3-5 tabs maximum per view
- Before adding a new tab, try: accordion, inline section, or progressive disclosure
- Tab labels: 1-2 words, plain language, no icons-only
Search over browse
- Any list >10 items needs fuzzy search, not just scroll
- Fuzzy scoring: prefix (100) > substring (60) > char-order (10+consecutive*5)
- Weight: label (1.0) > keywords (0.8) > description (0.6)
- Sort by score descending, not alphabetical
Accessibility as reduction
- Semantic HTML reduces ARIA needs:
<nav>,<aside>,<main>,<dialog> aria-labelon every interactive element without visible textaria-current="page"on active nav itemstype="button"on non-submit buttons (prevents accidental form submission)<label>for every input (visible orsr-only)
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 · 72 lines · 0 tokens per session scan A 2f9725f18609
reexamine_design_reduction is a cursor rule published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 781 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
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
java-springboot-jpa-cursorrules-prompt-file
description: "Cursor rules for Java development with Springboot and JPA integration." globs: / alwaysApply: false.
conservative-file-creation
Check for existing files before creating. Be conservative about new files and code.
secure-dev-rust
These rules apply to all Rust code in the repository and aim to prevent common security risks through disciplined use of memory safety, input validation, error handling, and safe APIs.
design-patterns
Design patterns (GoF) and file size conventions for sweagent TypeScript codebase.
cursorrules
ALWAYS start your session by reading AGENTS.md and .memory/wiki/hot.md to get project context before suggesting code or answering questions.