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/nedcodes-ok/cursorrules-collection/taurigit clone --depth 1 https://github.com/nedcodes-ok/cursorrules-collectionWhat 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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
tauri 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tauri Cursor Rules
You are an expert Tauri developer. Follow these rules:
Architecture
- Frontend is a web app (React/Svelte/Vue). Backend logic in Rust (src-tauri/)
- Use Tauri commands (#[tauri::command]) for frontend→backend communication
- Use events (app.emit/app.listen) for backend→frontend push notifications
- Keep frontend framework-agnostic where possible — @tauri-apps/api abstracts the bridge
Commands
- #[tauri::command] functions are the API boundary. Type inputs and outputs carefully
- Return Result<T, String> from commands. Never panic in command handlers
- Use State parameter for shared app state (managed via app.manage())
- Async commands with async keyword — Tauri runs them on a thread pool
- Serialize/deserialize with serde. All command inputs/outputs must impl Serialize + Deserialize
State Management
- App state via tauri::State<Mutex> or tauri::State<RwLock> for thread safety
- Initialize state in setup() callback, not in main()
- Use Arc<Mutex> only when state needs to be shared outside command handlers
- Database connections: use connection pools (r2d2/deadpool) in managed state
Security
- Allowlist in tauri.conf.json — only enable APIs you actually use
- Validate all inputs from frontend in command handlers. Frontend is untrusted
- Use tauri::scope for file system and shell access restrictions
- Never expose shell commands directly. Wrap in typed Rust functions
- CSP configured in tauri.conf.json. No unsafe-eval
Events
- app.emit_all() to broadcast to all windows. app.emit_to() for specific windows
- Frontend listens via listen()/once() from @tauri-apps/api/event
- Use typed event payloads. Define shared types in a types module
- Clean up listeners in frontend component unmount/destroy
Build & Packaging
- tauri.conf.json for app metadata, window config, security settings
- Use Tauri's updater for auto-updates with signing
- Platform-specific code via cfg attributes: #[cfg(target_os = "macos")]
- Test Rust backend independently: cargo test in src-tauri/
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 · 48 lines · 513 tokens per session scan A 3d341f5d4721
tauri is a cursor rule published in the GitHub repository nedcodes-ok/cursorrules-collection (37 stars, last pushed 6mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 per session on Opus 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 2026-08-30.