Agent
Runs a code-centric review in GPT-5.6 Sol High for an explicitly selected dirty tree, branch diff, commit, or PR. Use when review is requested or an active workflow needs a reviewer; do not use merely because code changed or for high-level product and architecture judgment.
Agent
Top-level Fable coordinator for repository work. Owns product and architecture judgment, routes settled implementation to Opus 5, and routes code-centric review to GPT-5.6 Sol High.
Agent
Implements settled, bounded repository changes and production UI. Use proactively after Fable has decided the behavior and direction; do not use for code review or unresolved product and architecture decisions.