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.
git clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/web)<a href="https://agentmods.dev/rules/kensaurus/cursor-kenji/web"><img src="https://agentmods.dev/badge/rules/kensaurus/cursor-kenji/web/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/kensaurus/cursor-kenji/web"><img src="https://agentmods.dev/badge/rules/kensaurus/cursor-kenji/web.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00433 |
| Opus 5.5 | $0.00000 | $0.00173 |
| Sonnet 5.5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
web 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 29d 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
Web build
Web-only target; it shares no patterns with the RN/native side.
Shared logic comes in through an explicit shared package
(packages/shared/), not from the RN src/ tree.
Adjust the globs to your repo's actual web path (e.g.
app/**,components/**for a Next.js root layout).
Stack assumptions (verify before assuming)
- Framework: <FILL IN — Next.js / Vite + React / RN Web>
- Routing: per the framework's convention
- Styling: <FILL IN — Tailwind / CSS Modules / styled-components>
- State: <FILL IN — React Query / Zustand / Redux Toolkit>
Conventions
- React + hooks, TypeScript strict.
- Web-only APIs are fine here:
window,document,localStorage,IntersectionObserver, etc. - Server components / SSR (if Next.js): be deliberate about
'use client'boundaries. - Images: optimized via the framework's image component, not raw
<img>for above-the-fold content. - No
react-nativeimports unlessreact-native-webis explicitly configured.
Hard exclusions
- Never import from the RN
src/tree unless there's an explicit shared package (e.g.,packages/shared/). - Never assume mobile code runs here. RN-only libraries will break the web build.
- Never use native bridge code or
Platform.OSchecks here.
Verification
cd web && npm run build
Or for a quick check without building:
cd web && npm run typecheck
Boundaries
- Do not duplicate logic that already exists in a shared package — import it.
- Do not introduce a new state library if one is already in use.
- Do not commit
.next/,dist/, orbuild/output.
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.
- 29d ago Changed 81046d823a98
- 1mo ago First seen · 61 lines · 0 tokens per session scan A ded748d6cf4d
web is a cursor rule published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 433 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 2026-09-03.
Other cursor rules, from other repositories
performance
Frontend performance optimization rules. Apply when optimizing UI or bundle.
nextjs-rules
You are a Senior Front-End Developer and an Expert in ReactJS, NextJS, JavaScript, TypeScript, HTML, CSS and modern UI/UX frameworks (e.g., TailwindCSS, Shadcn, Radix). You are thoughtful, give nuanced answers, and are brilliant at reasoning. You carefully provide accurate, factual, thoughtful answers, and are a…
styling
Rules for styling - use Tailwind CSS only, no inline styles, use CSS variables for colors, monochromic design pattern, and button icon spacing guidelines.
tailwind-css
Tailwind CSS: utility patterns, design tokens, component extraction.
react-native
React Native: mobile app development, navigation, native modules.
react
React: hooks, composition, performance patterns.