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.
forrestchangCursor ruleforrestchang/andrej-karpathy-skills/.cursor/rules/karpathy-guidelines.mdc
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Surging2 mentions in 2 weeks
11 projects use a version of this
contextmuxCursor rulecontextmux/contextmux/.cursor/rules/skill-ponytail-review.mdc
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.
first-flukeCursor rulefirst-fluke/fullstack-starter/.cursor/rules/quality.mdc
Quality assurance standards for security (OWASP), performance, accessibility (WCAG), and code quality reviews
srl-labsCursor rulesrl-labs/containerlab/.cursor/rules/karpathy-guidelines.mdc
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
No other project uses it yet
moclam1905Cursor rulemoclam1905/CocktailRecipes/.cursor/rules/tool-rules/git-commit-push-agent.mdc
This rule governs the process of committing and pushing changes to git repositories. It should be applied whenever: (1) The user indicates they want to commit or push changes, (2) The user asks about git commit conventions, (3) The user wants to update or save their work to git, or (4) Any git-related commit and push operations are requested. The rule ensures consistent commit message formatting, proper change documentation, and maintainable git history. It's particularly important for maintaining clear project history, facilitating code reviews, and ensuring proper documentation of changes. This rule helps maintain high-quality commit messages that explain both what changed and why, making it easier for both humans and AI to understand the project's evolution.
lhpaulCursor rulelhpaul/ai-dev-framework-template/.cursor/rules/code.mdc
Code quality conventions. Apply when writing, editing, or reviewing any source code file.
wuisabel-gifCursor rulewuisabel-gif/HAL/.cursor/rules/capability-security-review.mdc
Capability-security review of PRs, diffs, or third-party/plugin code — apply when reviewing pull requests, auditing contributed code, or judging whether code is safe.
NVIDIACursor ruleNVIDIA/ai-cloud-validation/.cursor/rules/karpathy-guidelines.mdc
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
learner124-cloudCursor rulelearner124-cloud/Brilliant-Claude-Skills/.cursor/rules/blueprint.mdc
Blueprint — behavioral guidelines for coding agents. Use when writing, reviewing, or refactoring code to ensure accuracy, simplicity, and surgical changes.
DataDogCursor ruleDataDog/dd-trace-py/.cursor/rules/native-code.mdc
Native code (C/C++/Rust/Cython) review checklist for dd-trace-py
ishandutta2007Cursor ruleishandutta2007/claude-skills-by-karpathy/.cursor/rules/claude-skills-karpathy.mdc
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
cfreglyCursor rulecfregly/gpu-perf-tune/.cursor/rules/coding-guidelines.mdc
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
andr-caCursor ruleandr-ca/agentharness/.cursor/rules/python-conventions.mdc
Use when writing or reviewing Python code — naming conventions, type hints, common pitfalls (mutable defaults, bare except, is-vs-==), and testing structure.
lucamezzaliraCursor rulelucamezzalira/mfe-skills/.cursor/rules/mfe-boundary-review.mdc
Reviews and generates micro-frontend code against eight boundary rules from Building Micro-Frontends (O'Reilly), plus governance extensions for feature-flag scope, edge strategy, SSR ownership, and boundary fitness functions. Use when a user says "review my shell code", "is this a boundary violation?", "generate a Module Federation shell", "how do I mount this MFE?", "review my micro-frontend architecture", "set up event communication between MFEs", "create a new micro-frontend", "how should we use edge with MFEs?", "where should feature flags live?", or "how do I enforce boundaries in a monorepo?". Loads automatically when the user pastes shell integration code, Module Federation config, Single SPA registration, or Native Federation routes. Does not activate for component-level code within a single deployed unit, or for generic React, Vue, or Angular questions with no cross-team deployment angle.
sakurablushCursor rulesakurablush/zeroagent-studio/.cursor/rules/zeroagent-reviewer.mdc
Code and architecture review for ZeroAgent Studio. Use for PR feedback or quality assessment — do not implement fixes unless asked.
madebyarisCursor rulemadebyaris/advance-minimax-m3-cursor-rules/.cursor/rules/fable5-coding-craft.mdc
Fable 5 coding craft: locate-before-write, root-cause method, simplicity taste, error-handling philosophy, test integrity, refactoring discipline, and counters to common LLM coding failure modes. Load when writing, refactoring, debugging, or reviewing non-trivial code in any language.
btseeeCursor rulebtseee/clean-code-skills/.cursor/rules/clean-code.mdc
Apply language-agnostic clean-code discipline to all code writing, editing, reviewing, testing, and refactoring, including file placement, single responsibility, and verified completion.
contextmuxCursor rulecontextmux/contextmux/.cursor/rules/skill-ponytail.mdc
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
andr-caCursor ruleandr-ca/agentharness/.cursor/rules/big-work-plan-review.mdc
Use before implementing big work — new systems, pipelines, daemons, or anything stateful/concurrent — where a bug would be expensive to find after code exists. Requires a written implementation plan to pass multi-round adversarial review by two independent LLM reviewers before any code is written. Not for scoped bug fixes or single-file changes; see requirements-clarification for those.
Vladimir-BrCursor ruleVladimir-Br/swiftui-project-template/.cursor/rules/30-ai-marker.mdc
Convention for marking AI-generated code for later human review
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.
