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/_project)<a href="https://agentmods.dev/rules/kensaurus/cursor-kenji/_project"><img src="https://agentmods.dev/badge/rules/kensaurus/cursor-kenji/_project/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/_project"><img src="https://agentmods.dev/badge/rules/kensaurus/cursor-kenji/_project.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 | $0.00698 | $0.00698 |
| Opus 5.5 | $0.00279 | $0.00279 |
| Sonnet 5.5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
_project 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project conventions
Targets
android/— native Android (Kotlin/Java/Gradle)ios/— native iOS (Swift/Obj-C/Xcode)src/— shared React Native JS/TSweb/— web build (separate target)
Adjust these paths if your monorepo uses a different layout (e.g.
apps/mobile/{android,ios,src}/orpackages/web/).
Developer environment (no Mac)
The developer works on Linux/Windows; there is no Mac. This means:
- iOS cannot be built or tested locally, so
xcodebuild,pod install,xcrun simctl, and Xcode are not options to hand the developer; iOS work routes through CI. - iOS verification happens entirely on GitHub Actions CI with macOS runners.
- iOS distribution happens via TestFlight — the developer installs builds on a real iPhone from TestFlight after CI uploads them.
- Android local dev uses ADB + Android emulator + Metro for hot reload.
- For iOS-affecting changes, the loop is: edit → verify TS / lint / Android compile locally → push → CI builds iOS → TestFlight → install on device.
When the developer reports an iOS issue, look in shared JS first —
most "iOS bugs" also reproduce on Android, the only place they can be
verified locally. If it is genuinely iOS-specific (native bridge,
Podfile, iOS-only code), edit the file and trigger CI instead of
asking the developer to run pod install or open Xcode;
/ios-ci-logs reads the failure.
Hard rules
- Identify the target before editing. The path tells you which.
- Each target's patterns stay in its own tree:
- No JSX/React in
android/orios/ - No native bridge code in
src/ - No
react-nativeimports inweb/(unlessreact-native-webis configured) - No browser APIs (
window,document,localStorage) insrc/
- No JSX/React in
- Never declare a task complete without running the verification command for the affected target.
- For iOS-affecting changes: declare "ready to ship to CI" — never claim "iOS verified" since you cannot.
- TypeScript strict; do not introduce
anywithout an inline justification comment. - Never disable a lint rule inline without an explanatory comment.
- Never commit secrets, signing keys,
local.properties,.env, or*.keystore.
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.
- 1mo ago Changed · -5 tokens per session 2da1760b8ade
- 1mo ago First seen · 70 lines · 703 tokens per session scan A 50b503307fe3
_project is a cursor rule published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 26d ago), licensed MIT. It adds 698 tokens to every session, about $0.0028 per session on Opus 5.5. 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
kotlin-rules
You are a Senior Kotlin programmer with experience in the Android framework and a preference for clean programming and design patterns.
flutter-rules
You are an expert in Flutter, Dart, Riverpod, Freezed, Flutter Hooks, and Supabase.
react-native
React Native: mobile app development, navigation, native modules.
task-tracking
Adaptive task status tracking protocol (Single Source of Truth).
workflow-examples
CRITICAL: Contains mandatory examples for correct workflow implementation. DO NOT assume workflow patterns without consulting this documentation first.
archive-examples
CRITICAL: Contains mandatory examples for correct archive formatting. DO NOT archive tasks without consulting this documentation first.