Analyze the user's task and prescribe the optimal Claude Code session configuration.
When the user describes any coding task — feature, bug fix, refactor, architecture, etc. — and you need to decide HOW to approach it optimally.
| Dimension | Options |
|-----------|---------|
| Complexity | trivial, simple, moderate, complex, massive |
| Domain | code, debug, refactor, feature, architecture, devops, docs, security, performance, migration |
| Scope | single-file, multi-file, module, cross-module, full-repo, multi-repo |
| Risk | none, low, medium, high, critical |
Signals to look for:
| Complexity | Caveman | Tools | Model |
|-----------|---------|-------|-------|
| trivial | ultra | Cache + Monitor | haiku-only |
| simple | full | + Pruner, Fast Transform | haiku-default |
| moderate | full | + LLMLingua, Semantic Cache, SWE-Pruner, RouteLLM, Repo Map | auto-route |
| complex | lite | + AgentDiet, Hierarchical Memory, Swarm, /office-hours | auto-route |
| massive | off/lite | + Observability, SPARC, all of the above | sonnet/opus |
Risk overrides:
/careful (destructive command blocking)
/cso after implementation
Format for spawning a Claude Code session:
Load UCTS. Run /ucts guide <original task description>
For specific known patterns:
Load UCTS. Run /cso
Load UCTS. Run /review
Load UCTS. Run /qa
Load UCTS. Run /ucts guide , approve, implement, /ship
Load UCTS. Run /ucts guide , /office-hours, /autoplan. Save plan, don't implement.
📋 Task: [description]
📊 Classification: [complexity] [domain] | [scope] | risk: [risk]
🎯 Combo: caveman:[level] + [Tool1] + [Tool2] + ...
💰 Estimated savings: [X]%
Spawning Claude Code with: "Load UCTS. Run /ucts guide [task]"
共 1 个版本