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/phidn/cursor-feedback/cursorrulesgit clone --depth 1 https://github.com/phidn/cursor-feedbackWhat 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 | $0.00553 | $0.00553 |
| Opus 5 | $0.00277 | $0.00277 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
cursorrules 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
Interactive Feedback Rule
-
Always Use Interactive Feedback for Questions:
- Before asking the user any clarifying questions, call
interactive-feedback-mcp.interactive_feedback - Provide the current project directory and a summary of what you need clarification on
- Wait for the interactive feedback response before proceeding
- Before asking the user any clarifying questions, call
-
Always Use Interactive Feedback Before Completion:
- Before completing any user request, call
interactive-feedback-mcp.interactive_feedback - Provide the current project directory and a summary of what was accomplished
- If the feedback response is empty, you can complete the request without calling the MCP again
- If feedback is provided, address it before completing the request
- Before completing any user request, call
-
Required Parameters:
project_directory: Full absolute path to the project directorysummary: Short, one-line summary of the question or completed work
-
Examples:
// ✅ DO: Call interactive feedback before asking questions // Before asking: "Which database should we use?" await interactive_feedback({ project_directory: "/Users/oplacrm/workspace/working/work_frontend/frontend", summary: "Need clarification on database choice for the project" });// ✅ DO: Call interactive feedback before completing requests // After implementing a feature await interactive_feedback({ project_directory: "/Users/oplacrm/workspace/working/work_frontend/frontend", summary: "Completed user authentication implementation with JWT" });// ❌ DON'T: Ask questions directly without interactive feedback // "What framework would you like to use?" - Missing interactive feedback call// ❌ DON'T: Complete requests without interactive feedback // "I've finished implementing the feature." - Missing interactive feedback call -
Workflow Integration:
- This rule applies to all interactions, regardless of the specific task or technology
- Interactive feedback helps ensure user satisfaction and catches any missed requirements
- The feedback mechanism allows for real-time course correction and validation
-
Exception Handling:
- If the interactive feedback tool is unavailable, proceed with completion flow
- Log when interactive feedback cannot be used for debugging purposes
- Never loop the interactive feedback call if the response is empty on completion
-
Best Practices:
- Keep summaries concise but descriptive
- Always use the full absolute path for project_directory
- Use interactive feedback as a quality gate, not a blocker
- Respect empty feedback responses as approval to proceed
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 · 67 lines · 553 tokens per session scan A ebef9285feae
cursorrules is a cursor rule published in the GitHub repository phidn/cursor-feedback (8 stars, last pushed 1y ago), licensed MIT. It adds 553 tokens to every session, about $0.0028 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
learned-conventions
从对话反馈中积累的编码约定和偏好.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
test-plan
Plan Katalon True Platform/TestOps testing for a release, sprint, or feature. Use when you need to translate quality goals into scope, prioritize testing by requirement coverage and risk, decide what to test first, or build the executable plan structure (folders, suites, and sprint/release association) that stands in…