The rules real projects give Cursor's agent, from .cursor/rules.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
PakvotheCursor rulePakvothe/i1n-cli/.cursor/rules/i1n.mdc
tone. Precise and technical. Prioritize accuracy and domain-specific terminology. Be concise and unambiguous. ## MCP Server (Recommended) i1n has a native MCP server. If it's installed, **prefer using MCP
Peak-StudiosCursor rulePeak-Studios/peak-agent-toolkit/.cursor/rules/peak-scripts.mdc
Use public Peak Studios documentation when modifying Peak FiveM scripts
RagnarPitlaCursor ruleRagnarPitla/microsoft-agent-skills-private-archive/.cursor/rules/copilot-studio-auth-patterns.mdc
Choose and debug authentication for a Copilot Studio agent. Use when deciding how users sign in, when an agent cannot call a downstream API as the signed-in user, when a token or User variable is empty or shows as Unknown, when an agent cannot be published to the intended channel, or when you need to control who in the organisation can talk to an agent.
RagnarPitlaCursor ruleRagnarPitla/microsoft-agent-skills-private-archive/.cursor/rules/ground-agents-in-work-context.mdc
Choose the right grounding layer for an agent across the Microsoft IQ stack - Work IQ, Fabric IQ, Foundry IQ, Web IQ. Use when an agent can see someone's email, calendar and Teams messages but not the approval rules or business entities it needs, when deciding between workplace signals and an ontology over business data, when someone maps a conceptual \"Business IQ\" or \"Work IQ\" onto Microsoft's products and gets the opposite of what they expected, when an agent needs GL accounts, vendors or authorisation thresholds rather than documents, or when an unattended background agent is being designed on top of Work IQ.
sijeeshmizihaCursor rulesijeeshmiziha/visionagent/.cursor/rules/tool-evaluation.mdc
Evaluation-driven tool improvement—prototype, evaluate, analyze, collaborate with agents
Surya8991Cursor ruleSurya8991/AgentMaster/.cursor/rules/agent-master.mdc
Meta-orchestrator that classifies tasks and routes to the right combination of installed skills across caveman (output compression), superpowers (dev workflow), anthropic-skills (business/domain expertise), and wired tactical libraries (wshobson, davila7, impeccable, anthropic-official, rea). 27 routing categories including whole-codebase analysis via repomix-pack, LLM/AI app dev, reverse-engineering/binary analysis via REA + ida-pro-mcp, live DAP debugging (debug-skill), an optional opt-in scientific-skills library (K-Dense, bio/chem/med), a live task dashboard, meta skill discovery, and curated tactical skill libraries (wshobson, davila7) for backend/security/CI-CD/database depth. Also scaffolds the canonical project-doc spine (README/AGENTS.md/CLAUDE.md/PROJECTLOG.md) in new projects via `/agent-master scaffold`. Invoke with /agent-master. Use as default entry point for ambiguous or multi-domain requests.
Tamircohen28Cursor ruleTamircohen28/tamirs-superpowers/.cursor/rules/hooks-guide.mdc
Constraints and patterns for editing hook scripts — use when modifying hooks/*.sh or hooks/hooks.json
Tamircohen28Cursor ruleTamircohen28/tamirs-superpowers/.cursor/rules/plugin-structure.mdc
Core facts about this repo — what it is, what NOT to do, and how it is distributed
tech-sumitCursor ruletech-sumit/mcp-webmcp/.cursor/rules/server-rules.mdc
Rules for mcp-webmcp package
thisrohanguptaCursor rulethisrohangupta/harness-skills/.cursor/rules/harness.mdc
Code skills for working with Harness.io CI/CD platform. All skills use the Harness MCP v2 server's consolidated tool interface. ## MCP v2 Server All skills use the [Harness MCP
webmycCursor rulewebmyc/Respira-Tally/.cursor/rules/byterover-rules.mdc
ByteRover MCP Custom Instructions
yavdaanalyticsCursor ruleyavdaanalytics/traceback/.cursor/rules/traceback.mdc
alwaysApply: true --- You have access to the **traceback** MCP server for semantic recall over past coding-agent sessions. ## MANDATORY — first tool call (contract violation if skipped) For **every** user message
abdelrahman-elkotCursor ruleabdelrahman-elkot/universal-ai-software-company/.cursor/rules/software-company.mdc
Universal Software Company Operating System v2.1 (11 Department Leads, Dynamic Squad Assembly, 5-Phase Pipeline & Zero Stale Docs Gate)
abxn4rCursor ruleabxn4r/archon-skills/.cursor/rules/berners.mdc
ALWAYS invoke when the user mentions Berners (e.g., 'Berners', 'ask Berners', 'run Berners', 'consult Berners') or asks to write an SEO blog post, optimize for AI search (GEO/AEO), audit content for AI slop, build search traffic engines, or generate organic traffic for Pastebase. Dual-retrieval organic traffic architect enforcing zero AI artifacts, Google Information Gain, and machine-parsable schema architecture.
adammatthewsteinbergerCursor ruleadammatthewsteinberger/claudeloop/.cursor/rules/claudeloop-agent-sdk.mdc
Explains how claudeloop integrates with claude-agent-sdk (ClaudeAgentOptions, ClaudeSDKClient vs query(), RateLimitEvent, ResultMessage, AssistantMessage, session discovery via list_sessions()) and the never-block-on-a-human design (permission_mode, can_use_tool, AskUserQuestion handling, hooks). Use this whenever building or modifying src/claudeloop/infrastructure/agent/ (the M2+ agent gateway, options builder, message translation, session catalog, capacity probe), whenever the user asks about the Claude Agent SDK, ClaudeAgentOptions fields, session resumption, rate-limit events, or why a run might block on a human. Make sure to consult this before writing any code that calls claude_agent_sdk directly — infrastructure/agent/ is the ONLY place that import is allowed, per the onion architecture (see the claudeloop-architecture skill), and getting the never-block guarantees wrong here defeats the entire purpose of this project.
afaraha8403Cursor ruleafaraha8403/balakit/.cursor/rules/seo-ai-search.mdc
Universal guidelines for SEO and AI-search implementation — meta tags, JSON-LD, llms.txt, crawlability, and adversarial security.
afaraha8403Cursor ruleafaraha8403/MCP-Scooter/.cursor/rules/mcp-registry.mdc
Rules for working with MCP Scooter registry and creating new MCP definitions
andr-caCursor ruleandr-ca/agentharness/.cursor/rules/dependency-audit.mdc
Use when adding dependencies, reviewing a project's dependency tree, or checking for known vulnerabilities and ownership risk — covers pip-audit, npm audit, govulncheck, lock file hygiene, update policy, and trust assessment.
andrii-lytvynkoCursor ruleandrii-lytvynko/ZenBox-Prototype/.cursor/rules/garden-design-system.mdc
Enforce Zendesk Garden Design System for all components, styling, tokens, and typography
contextmuxCursor rulecontextmux/contextmux/.cursor/rules/skill-find-before-writing.mdc
Use before creating any new helper, hook, component, selector, type or utility — search the codebase for an existing implementation first.
Instruction files for Cursor's agent, kept in .cursor/rules/ as .mdc files.
A rule can apply only to files matching a pattern, or only when the agent asks for it. AGENTS.md always applies.
Copy the .mdc file into your project's .cursor/rules/ directory and adjust its globs.
Open a rule to see its discussion. Reports from people and their agents are coming.
