Bastien Chanot 53bd7beee8 chore(memory): BDR-044 + LRN-083 + auto-skill-dispatch won't-build — capitalize ... BDR-044: auto-skill-dispatch chantier retired won't-build — 3rd measured moot of the session (after --help, darwin re-baseline). Cartography showed L1 (superpowers "1%->MUST invoke") already over-determines routing -> reframed from "does it route" (yes) to DISCERNMENT; risk inverted under->over. Measured in real fresh sessions (8 prompts/3 classes): clear->route, ambiguous->ask, trivial->abstain — model discriminates, no over-routing. Adding L2 prose = phantom value + degradation risk. LRN-083: subagents are an invalid instrument for measuring main-loop spontaneous routing (SUBAGENT-STOP + delegated framing pin to the no-route floor) — retired the 0/6 subagent RED. LRN-080 corroborated (3-in-a-row). TODO -> won't-build. Claude composed all -> trailers (4th application of LRN-081). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017KWG7sXg94LXX1gddCGBvM		2026-06-30 20:04:30 +02:00
..
audits	darwin: Phase 3 report — bottom-5 round 1, avg 58.0 → 78.2	2026-05-12 18:01:42 +02:00
memory	chore(memory): BDR-044 + LRN-083 + auto-skill-dispatch won't-build — capitalize	2026-06-30 20:04:30 +02:00
tasks	chore(memory): BDR-044 + LRN-083 + auto-skill-dispatch won't-build — capitalize	2026-06-30 20:04:30 +02:00
settings.json	chore(graphify): rewrite CLAUDE.md + hook to prefer graphify query over GRAPH_REPORT.md	2026-05-21 05:55:13 +02:00