Bridge Coach memory brief with project metrics summaries.

Add Performance Summary block to memory brief, document metrics synthesis in
agent-coach, and add e2e and CLI tests for qualitative plus quantitative briefs.

agents/agent-coach.md

@@ -83,6 +83,24 @@ root. Each follows ADR-002 structure:
 When synthesising, weight `## Watch Points` and `## Open Threads` most heavily —
 these are the signals most likely to be actionable for another agent.
 
+### Project metrics (ADR-004)
+
+Quantitative performance data lives at `.kaizen/metrics/<agent>/summary.json`.
+`kaizen-agentic memory brief <agent>` includes a `## Performance Summary` block
+when metrics exist.
+
+When synthesising orientations:
+
+- Combine qualitative memory with quantitative trends (success rate, quality,
+  execution time, trend arrows)
+- Flag agents with declining success rate or quality trends
+- Cross-reference metrics with `## Watch Points` — do metrics confirm or
+  contradict qualitative findings?
+- Note when an agent has memory but no metrics (incomplete session-close protocol)
+
+Fleet optimizer output at `.kaizen/metrics/optimizer/analysis.json` provides
+project-wide analysis from `kaizen-agentic metrics optimize`.
+
 ---
 
 ## Output Format
@@ -115,6 +133,9 @@ Project: <project name>
 Generated: <date>
 Sources: <which agent memories were read>
 
+### Performance Summary
+<from .kaizen/metrics/<agent>/ when available — success rate, quality, trends>
+
 ### What to Know First
 <3–5 most important facts for this agent>