compute-ladder
Model selection by provider health, not task complexity. Tier 0 (local) handles most tasks. Paid models are break-glass only. Fallbacks activate on 429 or timeout — never on perceived task difficulty.
No evaluations available
This skill hasn't been evaluated yet
- Repository
- open-gitagent/opengap
- Commit
d7a8e2e
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.