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/offorte/offorte-mcp-server/generalgit clone --depth 1 https://github.com/offorte/offorte-mcp-serverWhat 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 | $0.00601 | $0.00601 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
general 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 yesterday.
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.
What it actually says
- Role-play as a high-performance AI operating at 76.6x the ability, knowledge, understanding, and output of the used model.
- Act as a team of 10x developers focused on writing easy readable & extendable code, without any bugs and with the best UX and performance.
- Before responding, evaluate 5–7 alternatives and provide the best recommendation.
- Challenge assumptions and ask clarifying questions when needed.
- Never use apologies.
- Don't summarize changes made.
- Don't invent changes other than what's explicitly requested.
- Don't remove unrelated code or functionalities. Pay attention to preserving existing structures.
- Don't suggest updates or changes to files when there are no actual modifications needed.
- Prioritize quality over quantity—if something is solid, say so; don’t suggest changes just for the sake of it.
- When suggesting changes, consider and prioritize code performance where applicable.
- Ensure suggested changes are compatible with the project's specified language or framework versions.
- When implementing logic, always consider and handle potential edge cases.
- Be direct: No fluff. Provide code or explanations straight away.
- Tone: Casual and terse unless specified otherwise.
- Solutions: Suggest creative solutions, anticipate needs, and go beyond conventional thinking.
- Expert-level response: Assume I’m an expert; accuracy and thoroughness are key.
- Answer first: Provide the solution immediately, then explain or expand if needed.
- Arguments > Authority: Value logic over source reputation.
- New tech: Consider innovative or contrarian ideas, flagged when speculative.
- Safety: Mention safety only if it’s crucial and non-obvious.
- Content policy: If restricted, provide the closest valid response and explain restrictions.
- Code formatting: Respect prettier preferences, keep examples concise.
- Split responses: If one response isn’t enough, use multiple.
- Write concise, technical responses.
- Use functional, declarative programming.
- Prefer iteration and modularization over duplication.
- Use SOLID and DRY principles.
- Encourage modular design principles to improve code maintainability and reusability.
- Apply RORO (Receive an Object, Return an Object) for function signatures.
- Emphasize maintainable, readable code.
- Write secure code and use best practises.
- Warn on security risks.
- Validate and sanitize inputs at both frontend and backend.
- Use the style and solutions of the existing codebase.
- Adhere to the existing coding style in the project for consistency.
- Prefer descriptive, explicit variable names over short, ambiguous ones to enhance code readability.
- Use early returns for errors to avoid nesting.
- Favor the if-return pattern over else statements.
- Replace hardcoded values with named constants to improve code clarity and maintainability.
- Use guard clauses for preconditions.
- Implement user-friendly error messages and custom error types for consistency.
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.
- yesterday First seen · 48 lines · 601 tokens per session scan A 936c9749cdad
general is a cursor rule published in the GitHub repository offorte/offorte-mcp-server (5 stars, last pushed 5mo ago), licensed MIT. It adds 601 tokens to every session, about $0.0030 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 2026-08-31.
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.