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_polishgit 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 | $0.00465 |
| Opus 5 | $0.00000 | $0.00233 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
reexamine_polish 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
Re-examine: Visual Polish
Skeleton loading
- Replace blank areas during fetch with skeleton placeholders (gray shapes matching final layout)
- Shimmer animation:
background: linear-gradient(90deg, #2a2a3a 25%, #3a3a4a 50%, #2a2a3a 75%) background-size: 200% 100%; animation: shimmer 1.5s infinite- Respect
prefers-reduced-motion→ static gray background, no shimmer
Staggered fade-ins
- Cards/list items appear with slight delay cascade: 50ms, 100ms, 150ms per item
- Use
animation-delayortransition-delay— not JS setTimeout - Keep total cascade under 500ms (10 items max before grouping)
- Disable under
prefers-reduced-motion
Transitions
- State changes (expand/collapse, show/hide) get 200-300ms ease transitions
- Use
transition: all 0.2s easeon the specific properties, notallin production - Hover effects: subtle scale (1.02), shadow lift, or background shift
- Don't animate
width/height— usetransform: scale()ormax-heightfor performance
Micro-interactions
- Button press: brief scale-down (0.97) on
:active - Tooltip on hover for truncated text (CSS
text-overflow: ellipsis+titleattribute) - Copy-to-clipboard: brief "Copied!" feedback toast
- Empty states: helpful message + action button, not just blank space
Print stylesheet
@media print: light background, dark text, visible borders- Hide interactive controls (buttons, search, navigation)
- Severity badges: add borders (colors may not print)
- Page-break-inside: avoid on cards
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 · 38 lines · 465 tokens per session scan A 3c2e003d8fa7
reexamine_polish 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 465 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
frontend-10x-motion
Motion, parallax, 3D, shader, and performance rules for distinctive frontend work.
pn-blender
Blender scripting conventions: Python style for bpy, no absolute paths, consistent naming, Geometry Nodes scripting, extension manifest. Use when editing Blender Python scripts, add-ons, or Geometry Nodes setups.
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.