Autonomous native-tmux supervisor for Grok: launches a Dad/Son pane pair, keeps recurring supervision loops alive, records trajectory evidence, and gates checkpoint acceptance on real verification.
★not rated 23 3mo agoA
tokens not measured
originalMIT
21 skills that guide you from Cowork beginner to power user. Bridge the gap between what Cowork can do and what you know how to make it do. By Everyday AI.
Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.
★not rated 23▲
+1 2mo agoA
tokens not measured
originalMIT
Global index of your Claude Code projects. Disambiguates generic commands ("write the changelog") by resolving a name/alias to a path, knowing which folder owns a skill/command, detecting parent workspaces (monorepos), and creating + indexing new projects in the right place.
★not rated 22 2mo agoA
tokens not measured
originalMIT
Create and update AgentCore runtime agents in a DEPLOYED instance of this accelerator. Use whenever the user wants to create a new agent, build an orchestrator/swarm/graph agent, add or remove tools/MCP-servers/skills from an existing agent, change an agent's model or system prompt, or otherwise modify a live runtime…
★not rated 22 yesterdayA
tokens not measured
MIT-0
Autonomous overnight agent that keeps coding while the human is away — small, reversible, dual-LLM-reviewed commits for up to 8 hours on a feature branch.
★not rated 22 4mo agoA
tokens not measured
originalMIT
Skill marketplace for AI agents. Search, download, and install from 70+ skills. One subscription, unlimited tools.
★not rated 22▲
+1 5mo agoA
tokens not measured
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: