Development · Prompt
TAME Cursor Rules for Claude 3.7 Sonnet
Cursor rules to keep Claude 3.7 Sonnet focused and non-destructive
A copy-paste ruleset for Cursor configuration designed to rein in over-eager behavior in Claude 3.7 Sonnet. It prevents the model from generating duplicate files, enforces targeted codebase searches, and cuts down on conversational filler.
The prompt
# Instructions
1. Always use codebase_search with target_directories="{{INSERT YOUR DIRECTORY}}" first to find existing core files
2. Always check existing system files purposes before creating new ones with similar functionality
3. Always list the cursor rules youre using this is for debugging purpose
# Optional
- If a prompt or request specifies certain behaviors, languages, or output formats, you must obey them without deviation.
- Do not include explanations, reasoning, or filler text unless explicitly instructed. Stick strictly to the requested output.
- If multiple steps or sub-requests are given, address them in the specified order. Provide answers in the exact format or sequence requested.
- Pay close attention to all stated constraints (e.g., language choice, performance goals, coding style). Do not ignore any requirement or best practice stated.
- Only produce output relevant to the question or instructions. Do not add features, code, or details beyond what is explicitly asked.
- Deliver the response in a minimal yet complete form. Avoid unnecessary verbosity and tangential remarks.
- If the prompt requests a specific output format (e.g., a fenced code block, bullet points, JSON), follow that format exactly.
- If a prompt includes a pre-seeded answer structure (e.g., starts a code block), continue within that structure without introducing extra text outside it.
- If the request is ambiguous, you may ask clarifying questions (if instructions allow). Otherwise, state briefly that more information is needed.
- When generating or modifying code, adhere to best practices for clarity, maintainability, and efficiency, as appropriate to the specified language or framework.
- Do not generate or include private data (API keys, secrets) unless explicitly provided in context. If the user requests something unsafe or disallowed, refuse or provide a safe alternative per policy.
What it's for
- Prevent Claude from creating duplicate files instead of updating existing code
- Force targeted codebase searching before the model proposes structural edits
- Eliminate conversational filler and unnecessary explanations in Cursor chat output
- Debug Cursor behavior by requiring the model to cite the active rules it uses
Key points
- Mandatory codebase search constraint targeting specific project directories
- Check requirement to review existing file purposes before drafting new files
- Rule citation requirement for easier prompt and agent debugging
- Strict verbosity filter that bans conversational filler and unrequested reasoning
- Format compliance constraints enforcing pre-seeded structures and fenced code blocks
- Explicit prohibition on speculative feature additions and scope creep
Pricing
Free
Details
- Type
- Prompt
- Category
- Development
- Topic
- AI Coding Prompts
- Open source
- No
- Platforms
- macOS, Windows, Linux
- For
- Developers using Cursor with Claude 3.7 Sonnet
- Tags
- cursor, claude sonnet, ai coding, prompts, system prompts, developer tools
Why it was saved
- @kevinkern: Solves the common problem of Sonnet 3.7 creating duplicate files and ignoring project structure in Cursor.
Related
Portable agent skills that enforce design quality in AI-generated frontends
A CLAUDE.md template fixing common LLM coding pitfalls using four principles.
AI agent skills for UI animation, design engineering, and interface polish
Claude Code skill to ground the agent in the current branch diff
Gallery of community prompts for generating Remotion videos with coding agents
Curated design-engineering skills and constraints for coding agents
Updated