8 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 8 plugins that match these filters. Clear filters
karpathy-skillsswarmclawai/andrej-karpathy-skills1
claude-code-skillsalirezarezvani/claude-skills1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceYour coding agent already plans and swarms — Wicked Garden is the curated toolkit for what it can't: proof-not-claims gates, code links grep can't see, deterministic refactor, cross-session memory, multi-model second opinions (fallback seats labelled). Don't fight the harness; fill its gaps. The gate needs wicked-vault (a self-contained infra peer, installed directly) and re-derives through garden's built-in engine; estate/bus are opt-in layers (wicked-testing and wicked-brain are retired — QE ships in-catalog as the qe domain, memory lives in wicked-estate).
Multi-agent orchestration for Claude Code, Codex and Cursor: parallel coding agents that settle shared files before the merge, QA agents that test the running app, clickable prototypes, workbenches and live plans in aiview. On your own subscription.
GABBE coordination skills (7): multi-agent coordination: interop and protocols, workflow patterns, orchestration and swarm consensus.
Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. Covers supervisor, swarm, and hierarchical multi-agent patterns; subgraph composition; state management (checkpointers/stores); persistence; evals; and production debugging. Reach for this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns. Do not use this skill for unrelated requests; route to the nearest named specialist.
Design, diagnose, and evaluate coordination across multiple AI agents and heterogeneous harnesses: decomposition, topology, ownership, communication, distributed context, shared memory, integration, recovery, and collective failure patterns. Use for persistent agent teams, fleets, swarms, agent handoffs, coordination loops, or extracting portable lessons from OpenRig, HERDR and Block/Buzz. Do not use for a single agent's runtime, a named tool's installation or command manual, debate alone, or operating an evaluated production agent; route those to harness-engineering, the tool's documentation, agent-council, or agent-production-operations.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
workflowOpt-in, outside every domain bundle: orchestrate opencode workers from Claude Code to cut token costs, with single workers or parallel scout/coder/tester swarms on free or open-source models and worktree isolation. Requires the third-party opencode CLI and an opencode account; by default worker prompts and code go to opencode's hosted service (point --model at a local model to keep code on your machine), so install it only if you accept that data flow.
Message other agents over swarmbus: the MCP sidecar (send_message, read_inbox, agent_state) and the using-swarmbus skill
