advisor
01Agent
Strictly non-mutating commitment-boundary advisor. Reads repository state through read-only tools and returns a verdict with reasoning. Never edits.
Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.
Agent
Strictly non-mutating commitment-boundary advisor. Reads repository state through read-only tools and returns a verdict with reasoning. Never edits.
Agent
Second-opinion advisor running Claude's most capable model (Fable 5). Consult at commitment boundaries — before architectural decisions, data migrations, big refactors, or API designs, and whenever the same problem has resisted two attempts. Pass it the decision, the constraints, and the options considered; it returns…
Agent
Runs ONE claude-architect delegation lane (produce + verify only) so it surfaces as a native subagent. Input is a laneId, checkoutPath, protocolVersion, and a complete Delegation Spec; output is the structured lane report. Never reviews, decides, or integrates.