Alignment dialogues now use custom `alignment-expert` subagents with max_turns: 10, tool restrictions (Read/Grep/Glob), and hard 400-word output limits. Judge protocol injects as prose via RFC 0023. Moved Blue voice patterns from CLAUDE.md to MCP server instructions field for cross-repo portability. Includes RFCs 0017-0026, spikes, and alignment dialogues from 2026-01-25/26 sessions. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
421 B
421 B
Spike: Alignment Dialogue Protocol Not Followed From External Repos
| Status | Complete |
| Date | 2026-01-26 |
| Time Box | 1 hour |
Question
Why do alignment dialogues from external repos (fungal-image-analysis) spawn Tasks but agents don't follow the Judge Protocol? Is the protocol being injected, and if so, why isn't Claude following it?
Investigation notes by Blue