orchestrating-fusion
FeaturedCoordinates a strong read-only lead with a cheaper implementation executor. Use for non-trivial coding tasks that benefit from separate planning, execution, and independent verification.
Install
Quality Score: 89/100
Skill Content
Details
- Author
- jellydn
- Repository
- jellydn/my-ai-tools
- Created
- 8 months ago
- Last Updated
- today
- Language
- Shell
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
fusion-setup
Use when a user wants to set up, configure, install, or reconfigure the opencode Fusion agent team - a strong main/build agent that plans and reviews but cannot edit files, delegating all edits to a cheaper sidekick subagent, plus an explore search agent and optional research/design/reviewer/vision specialists. Triggers include "set up fusion", "configure fusion", "install fusion", "fusion setup", "undo fusion" / "remove fusion", changing which models the main, sidekick, or explore agents use, or naming a subscription to start from a ready-made profile - e.g. "set up fusion with my OpenCode Go subscription" (also OpenCode Zen, ChatGPT Plus/Pro, GitHub Copilot). Writes the global opencode config under ~/.config/opencode/.
fusion-advisor
Use when you want two different frontier models fused into one advisor brain for a high-leverage decision — "fuse", "fusion advisor", "get a second/peer model on this", "have Grok weigh in", "advisor fusion", "am I sure — bring in another model". This session reasons, consults a second frontier model (Grok) as a context-isolated peer, reconciles by verifying (not voting), then delegates execution via the `armory` launcher. NOT for routine steps (cost gate), and NOT for execution dispatch (that is the `armory` launcher).
orchestrate
Orchestrate complex work from an active gpt-6-astra or gpt-5.6-sol Codex session. The detected lead owns decomposition, integration, and verification; Astra keeps the hardest reasoning in the lead, while Sol escalates unusually difficult units to Astra. Both route bounded work to cheaper GPT-5.6 tiers and can use a cross-vendor Claude peer. Not for routine single-context work. Use when the user explicitly asks to orchestrate, delegate, fan out, parallelize, assign subagents, obtain independent checks, or have Codex act as tech lead.