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/skenetechnologies/skene-cookbook/cursorrulesgit clone --depth 1 https://github.com/SkeneTechnologies/skene-cookbookWrote 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/skenetechnologies/skene-cookbook/cursorrules)<a href="https://agentmods.dev/rules/skenetechnologies/skene-cookbook/cursorrules"><img src="https://agentmods.dev/badge/rules/skenetechnologies/skene-cookbook/cursorrules.svg" alt="Measured on agentmods" 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 | $0.02613 | $0.02613 |
| Opus 5 | $0.01307 | $0.01307 |
| Sonnet 5 | $0.00523 | $0.00523 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade B, and why
cursorrules scanned grade B with 1 finding 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 5d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules .venv Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules for skene-cookbook
Project Context
Repository: skene-cookbook - 764 AI skill library with 36 skill chain recipes Package: @skene/skills-directory v0.2.0 License: MIT Purpose: Pre-built AI skill chains for PLG, sales, customer success, security, and more
Architecture Patterns
Skill Structure (Non-Negotiable)
Every skill MUST follow this exact structure:
skills-library/{domain}/{skill-name}/
├── skill.json # Metadata (name, description, category, risk_level)
├── instructions.md # AI agent execution instructions
└── tests/ # Optional: skill-specific tests
Do NOT:
- Create skills outside
skills-library/executable/orskills-library/reference/ - Modify existing skill structure without updating registry
- Add skills without
skill.jsonandinstructions.md
Registry Auto-Generation
The registry/ directory is AUTO-GENERATED from skills-library/:
- Never manually edit files in
registry/ - Always run
npm run verify:metricsafter skill changes - Registry regeneration syncs badges and counts across README.md, METRICS.md, docs/directory.md
Risk Level Classification
Skills are classified by risk level (defined in skill.json):
Low- Read-only operations, no external dependenciesMedium- Write operations, requires configurationHigh- External API calls, requires credentialsCritical- System-level operations, requires manual review
Rule: When creating a skill that makes external API calls, uses credentials, or modifies data, always set risk_level: "High" or "Critical".
Naming Conventions
Skill IDs
- Format:
{domain}_{action}_{target}(e.g.,sales_analyze_pipeline) - Use snake_case, all lowercase
- Be descriptive but concise (3-5 words max)
File Naming
- Skill directories: kebab-case (e.g.,
analyze-customer-health/) - Python files: snake_case (e.g.,
analyze_skills.py) - JavaScript files: kebab-case (e.g.,
skills-directory.js) - Documentation: SCREAMING_SNAKE_CASE for top-level (e.g.,
AGENTS.md), kebab-case for nested
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.
- 5d ago First seen · 378 lines · 2,613 tokens per session scan B 99ffefc3042c
cursorrules is a cursor rule published in the GitHub repository SkeneTechnologies/skene-cookbook (53 stars, last pushed 6mo ago), licensed MIT. It adds 2,613 tokens to every session, about $0.0131 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). 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
evaluation-protocol
Evaluation protocol for blind skill testing across model tiers.
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.