docs: consolidate agent execution and custody

registry/capabilities/capability.agents.kaizen-framework.md

@@ -1,8 +1,8 @@
 ---
 id: capability.agents.kaizen-framework
 name: Kaizen Agentic Framework
-summary: AI agency framework providing 20 specialized deployable agent instruction sets plus persistent,
-  project-scoped memory and cross-agent coordination via a Coach meta-agent.
+summary: AI agency framework providing 20 deployable agent instruction sets, project memory,
+  metrics, role and engagement contracts, and scheduled preparation for governed execution.
 owner: kaizen-agentic
 status: draft
 domain: agents
@@ -10,13 +10,16 @@ tags:
 - agents
 - memory
 - coordination
+- metrics
+- scheduling
+- engagements
 maturity:
   discovery:
     current: D3
     target: D5
     confidence: medium
-    rationale: README documents the agent library, the agency framework (persistent memory, Coach meta-agent
-      synthesising fleet-wide patterns), and a versioned release (v1.4.0); has .forgejo/workflows CI.
+    rationale: README, SCOPE, ADRs, and integration contracts document the agent library, memory,
+      metrics, scheduling, role and engagement surfaces, and versioned release v1.4.0; CI is present.
   availability:
     current: A2
     target: A3
@@ -32,6 +35,9 @@ external_evidence:
     - 20 specialized agent instruction sets
     - persistent project-scoped agent memory
     - Coach meta-agent for fleet-wide pattern synthesis
+    - project metrics and optimizer workflow
+    - role packages and file-backed client engagements
+    - schedule validation and offline execution-bundle preparation
     broken_expectations: []
     out_of_scope_expectations: []
   reliability:
@@ -39,14 +45,17 @@ external_evidence:
     confidence: low
     basis: consumer_quality_signals
     known_reliability_risks:
-    - no external reuse evidence yet outside the originating project
+    - downstream execution depends on activity-core and rein-aharness contracts outside this repository
 discovery:
-  intent: Let agents arrive in a project already informed and improve over time through persistent, project-scoped
-    memory and fleet-wide coordination via a Coach meta-agent.
+  intent: Let agents arrive informed, work within explicit roles and engagement boundaries,
+    and improve through project memory, execution evidence, and governed scheduling contracts.
   includes:
   - 20 specialized agent instruction sets
   - persistent memory and coordination framework
   - Coach meta-agent pattern synthesis
+  - project execution metrics and optimizer artifacts
+  - role packages and forward-deployed engagement lifecycle helpers
+  - repo-local schedule manifests and offline preparation bundles
   excludes:
   - the underlying LLM inference itself (agents are instruction sets, not a model)
   assumptions: []
@@ -57,11 +66,13 @@ availability:
   target_level: A3
   current_artifacts:
   - Python package (`kaizen-agentic`) v1.4.0
-  - CLI (`agents-install-cli`)
+  - CLI (`kaizen-agentic`)
+  - versioned role, engagement, metrics, protocol, and schedule contracts
   target_artifacts: []
   consumption_modes:
   - cli
   - library import
+  - file contracts
 relations:
   depends_on: []
   supports: []
@@ -78,10 +89,12 @@ evidence:
 consumer_guidance:
   recommended_for:
   - projects wanting a deployable, memory-persistent agent fleet with cross-agent coordination
+  - governed runtimes needing offline agent orientation and schedule preparation contracts
   not_recommended_for:
   - needs for a single stateless agent (framework overhead not justified)
   known_limitations:
-  - no cross-project reuse evidence recorded yet
+  - this package prepares work but does not schedule, authorize, or invoke an LLM
+  - production reliability telemetry is not yet sufficient for a higher reliability rating
 promotion_history: []
 ---