agentic-ai cursor rules

535 tagged agentic-ai, measured the same way as everything else here.

Browse within: meok-ai-labs 114ai-governance 91agentic-workflow 61cursorrules 55meok 38opensource 38vibecode 38Code Generation 35ai-workflow 31agentic-framework 28coding 27documentation 26agentskills 21cursor-ide 21

aria-rule-22

97

mikeprasad/aria-knowledge

Cursor rule Cursor

Rule 22 — change decision framework. Apply BEFORE every Edit/Write: emit a [Rule 22] block (Low Impact or High Impact 7-step) ABOVE the tool call in the same turn, then run scripts/aria/record-edit-intent.sh to log intent. Verify scope AFTER each edit.

17 6d ago A 6,011 tokens

cursorrules

98

ejentum/ejentum-mcp

Cursor rule Cursor

This rules file teaches Cursor's AI when to call the four cognitive harness tools exposed by the ejentum-mcp MCP server. Use it when you have ejentum-mcp installed in Cursor's MCP settings and want the agent to fire the right harness automatically.

16 2mo ago A 1,168 tokens original MIT

chiplab

99

veecle/chiplab

Cursor rule Cursor

Repository agent instructions for chiplab.

16 14d ago A 60 tokens original MIT

music-mcp-rules

100

gorums/music-mcp-server

Cursor rule Cursor

Cursor rule "music-mcp-rules" from gorums/music-mcp-server, covering 🔄 project awareness & context, 🧱 code structure & modularity, 🧪 testing & reliability, ✅ task completion and 📎 style & conventions.

14 1y ago A 718 tokens

agent-magnet

101

helinakdogan/agentmagnet

Cursor rule Cursor

At the start of every conversation, call injectmemory with userid "helin" and projectid "default". Prepend the returned injection to your context silently — do not announce it.

14 8d ago A 251 tokens original MIT

latest-ai-models

104

laragentic/agents

Cursor rule Cursor

Use only the latest AI models from all providers (updated Feb 2026).

13 5mo ago A 1,437 tokens

test-mdc

105

4regab/agent-rules-mcp

Cursor rule

This is a test MDC file to reproduce the issue with .mdc files not being fetched.

13 11mo ago A 59 tokens original MIT

behavior-principles

106

kyungseo/ai-workflow-harness

Cursor rule Cursor

Global behavioral principles for all AI-assisted work in this repository. Covers thinking before coding, simplicity, surgical changes, goal-driven execution, and communication standards.

13 1mo ago A 570 tokens original Apache-2.0

coding

107

kyungseo/ai-workflow-harness

Cursor rule Cursor

Core coding behavior for this repository. Always prefer cautious, minimal, reversible changes.

13 1mo ago A 604 tokens original Apache-2.0

git-commit

108

kyungseo/ai-workflow-harness

Cursor rule Cursor

Use this when the user asks for a git commit, commit message, or commit command.

13 1mo ago A 18 tokens original Apache-2.0

ai-security

109

Renvia-code/best-cursor-rules

Cursor rule

Security best practices for LLM/AI applications - prompt injection defense, rate limiting, PII protection.

12 9mo ago A 0 tokens original CC0-1.0

swiftui

110

Renvia-code/best-cursor-rules

Cursor rule

SwiftUI best practices for iOS, macOS, and cross-platform Apple development.

12 9mo ago A 0 tokens original CC0-1.0

nauro-adopt

118

Nauro-AI/nauro

Cursor rule Cursor

Seeds Nauro's project store from an existing repo. Use after nauro adopt has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence…

10 4d ago A 89 tokens original Apache-2.0

nauro-context

119

Nauro-AI/nauro

Cursor rule Cursor

Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…

10 4d ago A 272 tokens original Apache-2.0

nauro-loop

120

Nauro-AI/nauro

Cursor rule Cursor

Originate gated Delivery and Interview candidates, or coordinate selected Program Delivery as FRAME -> CHOOSE -> START -> ADVISE -> VERIFY -> ADVANCE. Human-named work bypasses candidate selection. Agent-originated work keeps read-only ORIENT, 1-3 candidates, mandatory human selection, reject-all, and no auto-pick…

10 4d ago A 180 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: