Engineering Blueprint
Safety checkedClaude Opus + Managing multiple AI coding agents... Playbook
Multi-agent orchestration system for coordinating specialized AI coding assistants across parallel projects with persistent context and hierarchical task routing.
1 File Included
pasted-prompt.md
16 KB
What problem does this solve?
Managing multiple AI coding agents across parallel projects, coordinating specialized AI reasoning for complex development tasks, and maintaining context across long-running coding sessions.
How does it work?
Three-layer system: (1) Agent of Empires (AoE) - Rust TUI that manages multiple tmux-based OpenCode sessions, allowing parallel agents across different projects with persistent state. (2) OpenCode - terminal AI coding agent routed through LiteLLM proxy to Claude models (Opus for reasoning, Sonnet for execution, Haiku for quick tasks), connected to MCP servers (Atlassian, Amplitude, Metabase) for live data access. (3) Oh My OpenAgent (OMO) - plugin providing 11 specialized agents with hierarchical routing: Sisyphus (primary orchestrator) classifies intent and delegates to specialists (Oracle for hard problems, Explore for search, Librarian for research, Sisyphus Junior for execution, Metis/Prometheus/Momus for planning). Tasks are routed to category-specific models and load domain skills (jira-board (custom), metabase (custom), git-master, frontend-ui-ux, etc). Custom slash commands (/review-pr, /address-pr, /agentnews, /refactor) launch parallel agent swarms for specific workflows.
What's the biggest win?
Ability to run multiple specialized AI agents in parallel across projects while maintaining persistent context, with automatic task routing and delegation reducing manual coordination overhead. Parallel agent swarms for code review (7 agents), planning, and research accelerate complex tasks. Session persistence across terminal disconnects and sleep cycles enables long-running development without losing state.
What's required to run this?
Four MCP servers provide live tool access: Atlassian (Jira/Confluence at g2crowd.atlassian.net, project UW/10204), Amplitude (selective tools: search, query_chart, query_amplitude_data, get_event_properties), Metabase (v0.50 at metrics.g2.com with 19 connected databases including Snowflake, PostgreSQL, BigQuery). Model hierarchy: claude-opus-4-6 (reasoning variants: max/high/xhigh) for orchestration/planning/security, claude-sonnet-4-6 for execution/research, claude-haiku-4-5 for quick tasks. Temperature 0.1, max 200 steps for Abed agent. Custom skills defined in ~/.config/opencode/commands/.
What are the constraints?
Metabase accessible only via custom skill, not direct MCP. Jira-board skill limited: cannot transition statuses, edit fields, link issues, or create Epics. Amplitude tools selectively disabled. Oracle consultant is expensive and used only after 2+ failed attempts. Requires macOS for AoE/tmux setup.
Tools in this Blueprint
About This Blueprint
- Industry
- Computer Software
More Blueprints to explore
ICP-Filtered Outreach Lists from G2 Buyer Intent
Stop wasting rep time on weak intent signals and mismatched accounts. The workflow ranks ICP-fit buyers by readiness, finds the right contact, and supplies tailored outreach angles for the strongest opportunities.
Ishani D.
Account Manager at G2
Answer pre-purchase questions to convert hesitant shoppers with AI
Shoppers get accurate answers about fit, compatibility, ingredients, and delivery even when your team is offline, so fewer leave before checkout. Conversation insights also reveal which product-page details could prevent the next unanswered question.
Urska B.
GTM Lead at Yuma AI (YC W23)
Find the root cause behind repeat support tickets with AI
Catch a few unusual tickets before a product or fulfillment issue turns into hundreds of refunds, chargebacks, and bad reviews. Cluster transcript evidence by SKU, order date, location, and carrier so operations can trace the cause and support can reach affected customers early.
Urska B.
GTM Lead at Yuma AI (YC W23)