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/gabimoncha/cursor-rules-cliWrote 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/gabimoncha/cursor-rules-cli/project-structure)<a href="https://agentmods.dev/rules/gabimoncha/cursor-rules-cli/project-structure"><img src="https://agentmods.dev/badge/rules/gabimoncha/cursor-rules-cli/project-structure/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/gabimoncha/cursor-rules-cli/project-structure"><img src="https://agentmods.dev/badge/rules/gabimoncha/cursor-rules-cli/project-structure.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 | $0.00006 | $0.01081 |
| Opus 5.5 | $0.00002 | $0.00432 |
| Sonnet 5.5 | $0.00001 | $0.00216 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
project-structure 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules CLI
A command-line tool for bootstrapping and maintaining Cursor IDE rule files in any project, offering interactive setup, auditing, and repository summarisation via Repomix.
Purpose
Provide developers with an easy-to-use CLI that:
- Installs default and community Cursor rules into the current repository.
- Generates a compact XML snapshot of the codebase using Repomix so AI assistants get rich context.
- Audits and sanitises existing rule files for potential security issues.
- Offers quality-of-life features such as shell-completion, version checks, and update notifications.
Key features
- 🚀 Interactive init – guided prompts to install rule templates and (optionally) run Repomix.
- 🧩 Template library – ships with default rules plus [awesome-cursorrules] templates.
- 🔍 Audit & Scan – detect and optionally fix vulnerable or malformed rule files.
- 🪄 Repomix integration – create
repomix-output.xml&repomix.config.jsonwith sensible defaults. - 🖥 Shell completion – install/uninstall tab-completion for supported shells.
- 📦 Workspaces ready – published as a Bun package, compiled to ESM JavaScript.
Directory structure
.
├── .github/ # GitHub configuration and CI workflows
│ └── workflows/ # Continuous-integration definitions (tests, release)
├── awesome-cursorrules/ # Git submodule with a catalogue of community rule templates
├── cli/ # Source for the published `@gabimoncha/cursor-rules` package
│ ├── bin/ # Executable entry file distributed on npm
│ ├── src/ # TypeScript source code
│ │ ├── audit/ # Regex & Unicode spoofing detection helpers
│ │ ├── cli/ # Command implementations (init, list, repomix, scan, …)
│ │ ├── core/ # Business-logic utilities shared across commands
│ │ ├── shared/ # Logger, constants, error handling, etc.
│ │ └── templates/ # Built-in rule templates copied during `init`
│ ├── package.json # Manifest for the CLI workspace
│ └── README.md # Package-level documentation
├── docs/ # Detailed markdown documentation (guide, commands, contributing)
├── example/ # Lightweight sample project used in tests & demos
│ ├── parent_folder/ # Nested example showcasing recursive scanning
│ └── single_folder/ # Alternative flat example structure
├── scripts/ # Development helper scripts (template copy, vulnerability check)
├── .tool-versions # Toolchain versions (e.g., Yarn)
├── FUTURE_ENHANCEMENTS.md # Roadmap and upcoming improvements
├── LICENSE # MIT license
├── package.json # Root workspace manifest (Yarn workspaces & scripts)
└── README.md # High-level project overview and usage instructions
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 First seen · 103 lines · 6 tokens per session scan A a326e2634569
project-structure is a cursor rule published in the GitHub repository gabimoncha/cursor-rules-cli (50 stars, last pushed 1y ago), licensed MIT. It adds 6 tokens to every session and 1,081 once invoked, about $0.0000 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).