High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.
Use when estimating how long a task will take: coding, writing, research, analysis, design, data work, or anything else AI can contribute to. Estimate for a human working with AI, not a human working alone, and separate AI-speed work from human and external…
Use when a request includes examples, samples, templates, or reference outputs. Treat them as evidence of intent, not as something to copy: infer the principle behind them and produce something original at that level.
Use when a task keeps growing through patches: repeated fixes, workarounds, compatibility shims, or a new path built beside an old one. Pause, reassess the direction, and propose a cleaner alternative before continuing.
Use before implementing a feature, bug fix, refactor, or cross-system change to plan a credible project-specific verification path.
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt…
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug…
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable…