Claude MarketplacesSubmit
shipshitdev avatar

Multi Agent Patterns

shipshitdev/library

This breaks down when and how to split work across multiple Claude instances instead of cramming everything into one context window. The core insight is that multi-agent patterns are mainly about context isolation, not role-playing organizational charts. You get three main architectures: supervisor/orchestrator for centralized control, peer-to-peer swarm for flexible handoffs, and hierarchical for layered work. The token economics are brutal though. Multi-agent systems can burn 15x more tokens than single-agent approaches, so this makes sense when you're actually hitting context limits or need genuine parallelization, not just because it sounds sophisticated. The guide includes specific fixes for common problems like the "telephone game" where supervisors mangle sub-agent responses.

skills.sh installs
129
GitHub stars
24
last updated
Jun 3, 2026
View on GitHub

Install

$ npx -y skills add shipshitdev/library --skill multi-agent-patterns --agent claude-code

Installs into .claude/skills of the current project.

Files

This breaks down when and how to split work across multiple Claude instances instead of cramming everything into one context window. The core insight is that multi-agent patterns are mainly about context isolation, not role-playing organizational charts. You get three main architectures: supervisor/orchestrator for centralized control, peer-to-peer swarm for flexible handoffs, and hierarchical for layered work. The token economics are brutal though. Multi-agent systems can burn 15x more tokens than single-agent approaches, so this makes sense when you're actually hitting context limits or need genuine parallelization, not just because it sounds sophisticated. The guide includes specific fixes for common problems like the "telephone game" where supervisors mangle sub-agent responses.

Browse the repository on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/shipshitdev/library
Category
AI & Agent Building
First seen
Jun 3, 2026

More from shipshitdev/library

All 56

Recommended

More AI & Agent Building
1bankrbot avatarBankr Agent - LLM Gatewaybankrbot/claude-pluginsThis skill should be used when the user asks about "LLM gateway", "Bankr LLM", "LLM credits", "top up credits", "auto top-up", "llm.bankr.bot", "Claude Code gat0skills.sh installs
2jezweb avatarOpenAI Apps MCPjezweb/claude-skillsBuild ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI). Use when: developing ChatGPT e0skills.sh installs
3shinpr avatarmcp-local-ragshinpr/mcp-local-ragSearch, ingest, expand chunk context, or manage local documents via a local RAG MCP server (tools: query_documents, read_chunk_neighbors, ingest_file, ingest_da0skills.sh installs
4syahiidkamil avatardocs-anthropicsyahiidkamil/software-engineer-ai-agent-atlasIndex of official Claude Code / Anthropic docs — fetches the right page on demand0skills.sh installs
5syahiidkamil avatarmcp-buildersyahiidkamil/software-engineer-ai-agent-atlasGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when b0skills.sh installs
6github avatarmcp-deploy-manage-agentsgithub/awesome-copilotSkill converted from mcp-deploy-manage-agents.prompt.md8.8Kskills.sh installs