cursor agents

luismiglezmohino/ai-dev-agents

Agent

System orchestrator that routes requests to specialized agents and coordinates cross-verification.

AKSoftCode/aicrew

Agent

Use when API routes, service layer, or backend business logic is being changed.

AKSoftCode/aicrew

Agent

Speculative-context scout: cheap graph-first discovery that emits a fixed SCOUT: schema for a capable main agent to verify and act on.

AKSoftCode/aicrew

Agent

Use when database schema, model files, or migration files are being changed.

kubosho/cursor-rule-deck

Agent

An agent that suggests a correctly formatted Git commit message from a task description or the changes in a repository. Git is a system for recording code changes.

kubosho/cursor-rule-deck

Agent

An agent for carrying out coding tasks through planning, implementation, step-by-step checks, and a final report.

kubosho/cursor-rule-deck

Agent

An agent that follows test-driven development, a method where tests are written before the implementation and guide each small change.

erniker/understudy

Agent Claude Code

DevOps Engineer — infrastructure, CI/CD, operations.

erniker/understudy

Agent Claude Code

QA Engineer — testing, quality, testing strategy.

erniker/understudy

Agent Claude Code

Security Expert — threat modeling, security reviews, hardening.

atpaawej/openboard

Agent

Anthropic's Claude Code CLI tool natively supports Model Context Protocol (MCP) servers via stdio.

atpaawej/openboard

Agent

Cursor supports Model Context Protocol (MCP) servers configured via JSON configuration files or Cursor Settings.

atpaawej/openboard

Agent

OpenBoard connects to any client or agent framework supporting the Model Context Protocol (MCP) over stdio.

YashvantHange/SuperMemory

Agent

Role: Extract text from scanned PDFs via OCR Workflow: pdf-pipeline Step: ocr Namespace: team:eng.

YashvantHange/SuperMemory

Agent

Role: Coordinate planner and workers in multi-agent PDF pipeline Workflow: pdf-pipeline Namespace: team:eng.

YashvantHange/SuperMemory

Agent

Role: Route documents to the correct processing pipeline Workflow: pdf-pipeline Step: planner Namespace: team:eng.

CoinRithm/coinrithm-agent-trading

Agent

Forking an example agent is the fastest way to start — and the fastest way to ship someone else's strategy by accident. A real user forked Contrarian Carl for a pump-fade experiment, edited the obvious files, and the agent kept proposing mean-reversion breakdown shorts: the donor's doctrine lives in more files than…

mysleekdesigns/crawlforge-mcp

Agent Claude Code

Performance monitoring and optimization specialist. Tracks system performance, identifies bottlenecks, and ensures optimal resource usage. Use during load testing and optimization phases.

mysleekdesigns/crawlforge-mcp

Agent Claude Code

Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.

mysleekdesigns/crawlforge-mcp

Agent Claude Code

Security specialist for CrawlForge MCP Server. Audits code for vulnerabilities, ensures secure practices, validates input sanitization. Use PROACTIVELY before deployments and after major changes.

adonai-labs/agent-runway

Agent

Senior software architect for design decisions, trade-off analysis, and architectural review. Use when evaluating a design proposal, choosing between approaches, writing an ADR, reviewing system boundaries, or when /lead encounters a Complex task in Phase 0.

adonai-labs/agent-runway

Agent

Adversarial reviewer for high-impact decisions. Challenges the chosen approach from a clean, unbiased context. Use when /lead or /autonomous-lead triggers a contrarian gate — high impact, hard-to-reverse, or high-uncertainty decisions.

adonai-labs/agent-runway

Agent

Systematic code reviewer for .NET/C#. Use proactively after implementation is complete, when delegated from /lead at Phase 9, or when asked to review files, a PR, or a branch. Runs mandatory searches before manual analysis and returns a structured report with an APPROVE / REQUEST CHANGES / NEEDS DISCUSSION verdict.

JoakimCarlsson/bastion

Agent Claude Code

Final review of the diff for correctness, security, conventions, and spec conformance. Waits for CI green. On clean verdict, appends one line to LEARNINGS.md and signals merge-ready. On blocking findings, emits HANDOFF:FIX to coder. Read-only on source code.