~ / leaderboard / subagent / critic
Subagent · #83
critic
双模型工作流的安全审查子代理。由全局者在工作者「关键决策点」的「安全相关」项非空时调用,对工作者点名的相关文件做结构化审查并返回报告。只读,不可修改任何文件。
14rigs use it
0%of all rigs
19.3kavg rig context tax
Get it
$ npx degit Yeachan-Heo/oh-my-claudecode/agents .claude/agents From the most-starred rig that ships it: Yeachan-Heo/oh-my-claudecode. Same-named subagents in different rigs may differ — review before use.
Often used together with
planner · 6architect · 6research · 5analyst · 5reviewer · 4scout · 4review · 3tdd · 3researcher · 3verify · 3
Rigs using critic (14)
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
Orchestrator 14.5k tok ·
parcadei/Continuous-Claude-v3
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Orchestrator 3.1k tok ·
rjmurillo/ai-agents
Open-source multi-agent toolkit for Claude Code and GitHub Copilot CLI: 22 agents, plan-to-ship workflows, review and security gates, plugin marketplace.
Orchestrator 19.7k tok ·
angadhn/botference
One room, three minds: a multi-LLM planning council for your terminal — you, Claude Code, and Codex debate and ship an implementation plan.
Orchestrator 700 tok ·
navox-labs/agents
15-agent AI engineering team for Claude Code. Full sprint cycle: Think, Plan, Build, Review, Test, Ship, Reflect. Zero dependencies.
Orchestrator 5.1k tok ·
SmartAndPoint/ProjectStore
Decisions, specs and stories as plain markdown, for every coding agent. Code changes. Context stays.
Orchestrator 5.3k tok ·
kok1eee/o-m-cc
Personal lab for side projects
Orchestrator 4.7k tok ·
gufranco/claude-engineering-rules
Opinionated Claude Code engineering config: 11 always-on rules, 63 on-demand standards, 30 slash-command skills, 33 runtime hooks, 9 custom agents, 36 MCP servers, and a 774-item review checklist across 69 categories
YOLO Cowboy 156.1k tok ·
raghunandanprk/ases-ai-scrum-system
Structured AI Scrum workflow with context control, command-driven execution, and full project lifecycle management for Claude Code.
Fort Knox 1.8k tok ·
Haven16262/dual-model-workflow
双模型协作开发工作流:一个当全局者、一个当工作者(默认示例接 DeepSeek),用三个 Markdown 文件协调 | A dual-model AI coding workflow — Overseer + Worker (DeepSeek by default), coordinated via three Markdown files
Pragmatist 107 tok ·
sameerhimati/claude-code-kit
My Claude Code setup: skills, agents, hooks, and rules.
Orchestrator 2.0k tok ·
TomSzenessy/AI_TEMPLATE
Self-healing starting point for AI-agent-built projects of any size: docs bound to code, generated host adapters, delegation roles, and deterministic gates for any agent or model.
Orchestrator 12.7k tok ·
Luis85/agentic-workflow
The Specorator Workflow bundled in a Claude Plugin - spec-driven, agentic development workflow. Specs first, code second.
Orchestrator 41.3k tok ·
SchotjeChrisman/agentic-workflow
A self-improving Claude Code setup
Orchestrator 2.8k tok ·