What problem does it solve?
Recommends the appropriate Claude model tier for Salesforce development tasks to balance reasoning capability, cost, and deployment risk so engineers route work to the right model and avoid overpaying or under-serving a task.
Core Features & Use Cases
- Tiered Recommendations: Maps tasks to haiku for deterministic, low-risk edits; sonnet for standard implementation and refactors; and opus for architecture, deep reviews, and security-sensitive analysis.
- Budget-aware Routing: Accepts low, med, or high budget hints to favor cheaper or higher-capability tiers when appropriate.
- Practical Examples: Use opus for governor limit audits and complex sharing model reviews, sonnet for code reviews and test generation, and haiku for pure formatting or small mechanical fixes.
Quick Start
Ask the assistant to recommend a model with a short task description and optional budget, for example: /model-route Audit all SOQL queries in force-app for governor limit risks --budget high