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/tyrchen/cursor-rust-rules/cligit clone --depth 1 https://github.com/tyrchen/cursor-rust-rulesWhat 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 | $0.07035 |
| Opus 5 | $0.00000 | $0.03517 |
| Sonnet 5 | $0.00000 | $0.01407 |
| Haiku 4.5 | $0.00000 | $0.00703 |
Grade A, and why
cli 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 — 1,118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🖥️ RUST CLI APPLICATION STANDARDS
TL;DR: Modern CLI application patterns using clap 4.0+ with derive features, subcommands, enum_dispatch, and production-ready command execution architecture.
🔍 CLI APPLICATION DESIGN STRATEGY
graph TD
Start["CLI Application"] --> CLIType{"CLI<br>Complexity?"}
CLIType -->|Simple| SimpleCLI["Single Command CLI"]
CLIType -->|Complex| ComplexCLI["Multi-Command CLI"]
SimpleCLI --> DirectExecution["Direct Execution"]
ComplexCLI --> SubcommandArch["Subcommand Architecture"]
SubcommandArch --> EnumDispatch["enum_dispatch Pattern"]
EnumDispatch --> TraitExecution["CommandExecutor Trait"]
DirectExecution --> ErrorHandling["Error Handling"]
TraitExecution --> ErrorHandling
ErrorHandling --> UserFeedback["User Feedback"]
UserFeedback --> ProgressIndicators["Progress Indicators"]
ProgressIndicators --> Configuration["Configuration Management"]
Configuration --> Testing["CLI Testing"]
Testing --> Documentation["Help & Documentation"]
Documentation --> Completion["Shell Completion"]
Completion --> Production["Production CLI"]
style Start fill:#4da6ff,stroke:#0066cc,color:white
style SimpleCLI fill:#4dbb5f,stroke:#36873f,color:white
style ComplexCLI fill:#ffa64d,stroke:#cc7a30,color:white
style EnumDispatch fill:#d94dbb,stroke:#a3378a,color:white
🎯 CLI FRAMEWORK REQUIREMENTS
Clap 4.0+ Configuration
- Use clap 4.0+ with derive features - Modern declarative CLI definition
- Subcommand architecture - Organized command structure for complex CLIs
- enum_dispatch pattern - Efficient command execution with trait dispatch
- Comprehensive error handling - User-friendly error messages and exit codes
📦 CLI DEPENDENCIES
# Cargo.toml - CLI application dependencies
[dependencies]
# CLI framework
clap = { version = "4.0", features = ["derive", "env", "unicode", "wrap_help"] }
enum_dispatch = "0.3"
# Error handling
anyhow = "1.0"
thiserror = "2.0"
# Async runtime (if needed)
tokio = { version = "1.45", features = ["macros", "rt-multi-thread", "fs", "process"] }
# Logging and tracing
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter", "json", "chrono"] }
# Configuration and environment
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"
serde_yaml = "0.9"
# Utilities
colored = "2.0" # Terminal colors
indicatif = "0.17" # Progress bars
dialoguer = "0.11" # Interactive prompts
console = "0.15" # Terminal utilities
# Optional: Advanced CLI features
clap_complete = "4.0" # Shell completions
clap_mangen = "0.2" # Manual page generation
[dev-dependencies]
assert_cmd = "2.0" # CLI testing
predicates = "3.0" # Assertion predicates
tempfile = "3.0" # Temporary files for testing
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 · 1,118 lines · 0 tokens per session scan A e1240b5aced3
cli is a cursor rule published in the GitHub repository tyrchen/cursor-rust-rules (27 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,035 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
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.