The rules real projects give Cursor's agent, from .cursor/rules.
MANVENDRA-githubCursor ruleMANVENDRA-github/agentry/.cursor/rules/code-review.mdc
Self-review discipline for in-conversation use — apply before declaring code complete or before committing. Walks correctness, security, maintainability, and convention checks at the time of writing. For focused review of a large diff in a fresh context, delegate to the code-reviewer agent.
BambooGapCursor ruleBambooGap/skills-orchestrator/.cursor/rules/pr-review.mdc
--- id: pr-review name: PR Review summary: "Systematic PR review process with blocking/suggestion/nit severity
MANVENDRA-githubCursor ruleMANVENDRA-github/agentry/.cursor/rules/security-review.mdc
Self-review security discipline applied while writing — walk the threat model of the change (untrusted input, authz, secrets, crypto, dependencies) before handing it off. Invoke before declaring security-relevant code complete or committing it. The in-conversation companion to the security-reviewer agent; for a focused pass on a large diff in fresh context, delegate to that agent.
TencentCursor ruleTencent/LoopForge/.cursor/rules/code-review.mdc
代码审查规则：审查维度、严重等级判定、报告格式。由 code-reviewer agent 在 CODE-REVIEW 阶段加载。
carmentacollectiveCursor rulecarmentacollective/carmenta/.cursor/rules/code-review-standards.mdc
When doing code reviews
edhoferdianCursor ruleedhoferdian/EEF/.cursor/rules/language-code-review-edho-ferdian.mdc
Language- and framework-specific code review lenses layered on top of the general four-domain review in code-review-edho-ferdian — idioms, framework security misconfigurations, ORM/query correctness, performance traps, and testing conventions, auto-detected across ~20 stacks (React, Python, Go, Java/Spring, Ruby, and more — see the reference table below for the full list). Use whenever a review touches a specific language/framework and the generic checklist isn't enough — \"review kode Go/Python/React ini\", \"audit Django models\", \"cek FastAPI endpoint ini\", or when the user names a stack while asking for review. Loads only the lens file(s) matching the detected stack. Inherits Reflection and Critique-Correction gates from code-review-edho-ferdian.
galyarderlabsCursor rulegalyarderlabs/galyarder-framework/.cursor/rules/code-reviewer.mdc
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
MicrosoftCursor rulemicrosoft/data-formulator/.cursor/rules/implementation-review-checklist.mdc
Require structural code review after implementation before final response
edhoferdianCursor ruleedhoferdian/EEF/.cursor/rules/frontend-engineering-edho-ferdian.mdc
Authoring and configuration guidance for building React/Next.js frontend applications well from the start — component composition, UX/interaction recipes, Vite config, HeroUI setup, and AI-slop detection (see the Reference files table below for the full breakdown). A companion to language-code-review-edho-ferdian (which reviews code after it's written) — use this when DESIGNING or WRITING new frontend code, not when reviewing existing code. Trigger phrases: \"bagaimana cara structure component ini\", \"best practice React untuk X\", \"setup Vite untuk Y\", \"biar UI-nya gak keliatan AI banget\", \"kok hasil desainnya generic/template banget\", or when starting a new frontend feature.
alexandrershovCursor rulealexandrershov/assumption-checkpoint-skill/.cursor/rules/assumption-checkpoint.mdc
Use Assumption Checkpoint when diagnosing bugs, changing code, reviewing code, explaining unfamiliar code, making implementation decisions, or calling work complete.
Surya8991Cursor ruleSurya8991/AgentMaster/.cursor/rules/codereview.mdc
Blunt, factual code review. No sugar coating. Finds bugs, security issues, performance problems, and architecture flaws. Use when user says /codereview or asks to review code.
vikisingh23Cursor rulevikisingh23/neuraforge-ai/.cursor/rules/code-review.mdc
NeuraForge AI — code-review
danielvm-gitCursor ruledanielvm-git/bigpowers/.cursor/rules/request-review.mdc
Dispatch a fresh reviewer agent with a clean context to critique the code after audit-code passes. The reviewer has no shared state with the coding agent and gives a genuine second opinion. Use after audit-code passes, before committing, or when user wants an independent code review.
agentset-aiCursor ruleagentset-ai/agentset/.cursor/rules/clean-code.mdc
Guidelines for writing clean, maintainable, and human-readable code. Apply these rules when writing or reviewing code to ensure consistency and quality.
edhoferdianCursor ruleedhoferdian/EEF/.cursor/rules/code-review-edho-ferdian.mdc
Senior-engineer code review across five domains — Code Quality, Security, Performance, Blueprint/Spec Consistency, and Test Quality — plus conditional lenses auto-detected from scope (database, accessibility, RAG, ML, healthcare, agent/LLM — see Phase 0 below for the full list). Produces an evidence-backed findings report with confidence-labeled severities and an adaptive fix. Use whenever the user wants code reviewed, audited, or checked before merge/deploy: \"review this\", \"audit\", \"cek kode\", \"review PR\", \"is this production-ready\", \"find bugs/security issues\" — even without the word \"review\". Includes Reflection and a Critique-Correction Loop to suppress false positives. If the request is entirely about security (\"security audit\", \"cek keamanan kode ini\"), route to `security-review-edho-ferdian` instead — that skill is the single source of truth for security review criteria.
raye-dengCursor ruleraye-deng/open-code-review/.cursor/rules/open-code-review.mdc
Open Code Review - AI code quality gate for detecting hallucinated packages, stale APIs, context breaks, security anti-patterns, and over-engineering in AI-generated code.
brianwestphalCursor rulebrianwestphal/glassbox/.cursor/rules/glassbox.mdc
Read the latest Glassbox code review and apply all feedback annotations
rlaopeCursor rulerlaope/nen/.cursor/rules/nen-transmuter.mdc
Behavior-preserving refactoring under characterization tests, plus severity-rated code review. Use when the user says \"refactor\", \"clean up\", \"tech debt\", \"code review\", \"extract\", \"rename\", \"restructure\", \"this file is a mess\", or \"impossible to modify\"; when every small change breaks something unrelated; when cleanup has to land before the next feature has anywhere to go; when code is called hard to change, scary to touch, or too tangled to test; when requirements shifted and the current shape fights the new feature; when a PR needs review for structure and maintainability; or when every small change keeps ballooning because everything touches everything.
edhoferdianCursor ruleedhoferdian/EEF/.cursor/rules/system-design-edho-ferdian.mdc
Mid-project architectural decision-making — Architecture Decision Records (ADRs), structured trade-off analysis, non-functional-requirements review, and scaling-tier planning for an existing system. Use for \"desain arsitektur\", \"keputusan teknis besar\", \"bikin ADR\", \"trade-off antara X dan Y\", \"should I refactor this to microservices/monolith/event-driven\", a scaling or capacity question, or any task from dev-kickoff-edho-ferdian that surfaces an uncovered ARCHITECTURE decision mid-project (not at kickoff — kickoff's own PDR process in Phase 0/1 handles that). Not for restating a single task's plan (that's dev-kickoff's PLAN stage) and not for reviewing code that already exists (that's code-review-edho-ferdian's Blueprint/Consistency domain).
streamshubCursor rulestreamshub/streamshub-mcp/.cursor/rules/code-review.mdc
Code review checklist for StreamsHub MCP pull requests
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.
