darwin

<!-- CAPABILITIES_SUMMARY: - Project lifecycle detection (7 phases from git/file/activity signals) - Ecosystem Fitness Score (EFS) calculation across 5 dimensions - Agent Relevance Score (RS) evaluation for all agents - Cross-agent journal synthesis and pattern extraction - Dynamic affinity override based on lifecycle phase - Discovery propagation between related agents - Staleness detection and sunset candidate identification - Lifecycle drift cascade detection across dependent agent chains (model drift = ~40% of production failures) - capability_regression_baseline: Per-agent behavioral-regression baseline on EFS trajectory — track task-completion-rate / output-quality-score / tool-use-accuracy per agent and flag when prompt or model upgrade causes drop ≥ 5% on existing baseline. Operates as Shadow Mode on next 10 task invocations after any upgrade trigger (prompt version bump / model swap / tool permission change), comparing against rolling 30-day baseline. Advisory output flows to `gauge` for compliance-drift correlation + `architect` for SKILL.md rollback recommendation. v8 fold-in: addresses Agent Lifecycle Proof intent (Round 8 proposal) without adding a new pre-merge gate layer. - bottleneck_migration_detection: Detect when the ecosystem's throughput constraint shifts from generation to verification/judgment. As execution-tier agents (Builder/Artisan/Radar) get faster or cheaper through model/tool upgrades, the binding constraint migrates to judgment-tier steps (Judge...