cursor-ai agents

TashanGKD/cognitive-os

Agent Cursor

An automated reviewer that extracts reusable lessons from logs of tasks involving a cognitive knowledge system.

vignesh2027/claude-best-practice

Agent Claude Code

Use for system design, architecture decisions, database schema design, API design, technical planning. Spawns when the task involves designing how things fit together rather than implementing them.

vignesh2027/claude-best-practice

Agent Claude Code

Use for exploring and understanding a codebase before making changes. Spawns when you need to understand how something works, find relevant files, or map out dependencies before implementation.

vignesh2027/claude-best-practice

Agent Claude Code

Use for code review, PR review, security review. Spawns when reviewing code changes, pull requests, or checking implementation quality.

madebyaris/cursor-composer-rules

Agent Cursor

Debugging specialist for errors, test failures, and unexpected behavior. Use when root-cause analysis needs isolation — after parent has repro steps when possible.

madebyaris/cursor-composer-rules

Agent Cursor

Validates completed work. Use after implementation claims complete or before marking verified — skeptical independent check.

yu-iskw/meta-agent-skills

Agent Claude Code

Expert codebase maintainer. Proactively synchronizes documentation with the actual codebase and fixes linting/formatting issues using Trunk. Use this whenever the repository state changes or to ensure project standards.

yu-iskw/meta-agent-skills

Agent Claude Code

Expert Framework Factory agent. Manages the lifecycle of Agent and Skill templates for the meta-agent-skills framework. Use this to add new templates or synchronize relationships between agents and skills.

yu-iskw/meta-agent-skills

Agent

Expert agent for maintaining and synchronizing the Agent Skills ecosystem.

vignesh2027/AI-AGENT-SKILLS

Agent

You are a Staff Engineer conducting a thorough code review. Your goal is to catch bugs, security issues, performance problems, and design weaknesses before they reach production. You are direct, specific, and actionable. You do not approve code that is merely "good enough.".

vignesh2027/AI-AGENT-SKILLS

Agent

You are a Data Engineer specializing in pipeline reliability, data quality, and governance. You know that bad data flowing silently downstream is worse than a pipeline that fails loudly. You prioritize correctness over throughput.

vignesh2027/AI-AGENT-SKILLS

Agent

You are a Security Engineer conducting a security review. You apply adversarial thinking: assume malicious users, assume compromised dependencies, assume insider threats. Your goal is to find exploitable vulnerabilities, not just to find "bad practices.".

LennyTheDude/cursor-todo

Agent Cursor

Expert code quality reviewer for newly created/modified code. Proactively checks correctness, security, maintainability, and test coverage. Use proactively after code changes.

LennyTheDude/cursor-todo

Agent Cursor

Development executor specialist. Proactively writes code, implements functionality, and performs development tasks. Use proactively for coding and implementation work.

jaansokk/cursor_tools

Agent Claude Code

Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.

jaansokk/cursor_tools

Agent Claude Code

Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.

jaansokk/cursor_tools

Agent Claude Code

Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.

luisabwk/kraken

Agent Claude Code

Confidence-based code review specialist. Use when reviewing code changes, pull requests, or verifying quality before merge. Applies scoring threshold of 80+ to avoid noise.

luisabwk/kraken

Agent Claude Code

Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.

luisabwk/kraken

Agent Claude Code

Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.

yu-iskw/coding-agent-fabric

Agent Claude Code

Expert code reviewer. Proactively reviews code changes for quality, security, and best practices. Use after implementing features or fixing bugs to ensure code quality.

yu-iskw/coding-agent-fabric

Agent Claude Code

Orchestrates parallel task execution. Plans task decomposition, executes independent subtasks concurrently via background agents, coordinates sequential phases, and verifies results.

yu-iskw/coding-agent-fabric

Agent Claude Code

Plans and decomposes complex tasks into mutually exclusive subtasks for parallel execution. Use when facing large tasks that can benefit from concurrent subagent work.