diff --git a/registry/NO_CAPABILITIES.md b/registry/NO_CAPABILITIES.md
deleted file mode 100644
index 60aa001..0000000
--- a/registry/NO_CAPABILITIES.md
+++ /dev/null
@@ -1,15 +0,0 @@
----
-repo: agentic-resources
-reason: >
-  INTENT/SCOPE are aspirational HR-for-agents vision prose; no src/, no package manifest — vision-stage only, nothing implemented to reuse.
-reviewed: "2026-07-06"
-reviewed_by: claude-code
-revisit: >
-  Revisit once an implementation exists (src/ or package manifest lands).
----
-
-# No reusable capability
-
-This repo was reviewed for the `reuse-surface` capability registry
-(REUSE-WP-0017 coverage campaign) and has no capability to register at this
-time. See the `reason` field above.
diff --git a/registry/capabilities/capability.agents.performance-learning.md b/registry/capabilities/capability.agents.performance-learning.md
new file mode 100644
index 0000000..be286a9
--- /dev/null
+++ b/registry/capabilities/capability.agents.performance-learning.md
@@ -0,0 +1,93 @@
+---
+id: capability.agents.performance-learning
+owner: agentic-resources
+status: draft
+domain: infotech
+maturity:
+  discovery:
+    current: D3
+    target: D5
+    confidence: medium
+    rationale: Owner scope, neighboring responsibilities, concrete use cases and limitations
+      are documented; no exhaustive or generalized maturity claim.
+  availability:
+    current: A2
+    target: A2
+    confidence: medium
+    rationale: 'Source interface assessed 2026-10-14: Capture sessions, curate patterns,
+      distribute lessons and measure outcomes. Availability describes the delivery
+      form, not production acceptance. Workforce assignments and broader authority
+      contracts remain proposed.'
+external_evidence:
+  completeness:
+    level: C1
+    confidence: low
+    basis: Source artifacts establish a bounded capability; no independent consumer-completeness
+      assessment in this review.
+  reliability:
+    level: R0
+    confidence: low
+    basis: No longitudinal consumer reliability measurement established by this review.
+name: Agent performance learning
+summary: Capture sessions, curate patterns, distribute lessons and measure outcomes.
+tags:
+- security
+- netkingdom
+- framework-reuse
+discovery:
+  intent: Capture sessions, curate patterns, distribute lessons and measure outcomes
+  includes:
+  - Capture sessions, curate patterns, distribute lessons and measure outcomes
+  excludes:
+  - Workforce assignments and broader authority contracts remain proposed
+  use_cases:
+  - 'U09: Maintainer observes posture, prioritizes findings, coordinates work and
+    verifies outcomes'
+  - 'U11: Agent executes an attributable bounded task and supplies supervision evidence'
+availability:
+  current_level: A2
+  target_level: A2
+  current_artifacts:
+  - SCOPE.md
+  consumption_modes:
+  - CLI
+  - source
+relations:
+  related_to:
+  - capability.execution.profile-harness
+  - capability.activity.event-coordinate
+  - capability.finance.security-budget-evidence
+evidence:
+  documentation:
+  - SCOPE.md
+consumer_guidance:
+  recommended_for:
+  - Maintainer observes posture, prioritizes findings, coordinates work and verifies
+    outcomes
+  - Agent executes an attributable bounded task and supplies supervision evidence
+  not_recommended_for:
+  - Workforce assignments and broader authority contracts remain proposed
+  known_limitations:
+  - Workforce assignments and broader authority contracts remain proposed
+  - 2026-10-14 architecture review estimates operational maturity separately; a registry
+    entry does not authorize execution or establish deployment.
+---
+
+# Agent performance learning
+
+Capture sessions, curate patterns, distribute lessons and measure outcomes.
+
+## Reuse boundary
+
+Workforce assignments and broader authority contracts remain proposed.
+
+## Supported use cases
+
+- U09: Maintainer observes posture, prioritizes findings, coordinates work and verifies outcomes
+- U11: Agent executes an attributable bounded task and supplies supervision evidence
+
+## Evidence and integration
+
+- [SCOPE.md](../../SCOPE.md)
+
+Assessment: CUST-WP-0081, 2026-10-14. Relations identify interfaces to compose; they do not certify native integration. Existing external evidence levels are retained where present. New entries use conservative C1/R0 until consumer assessment exists.
diff --git a/registry/indexes/capabilities.yaml b/registry/indexes/capabilities.yaml
index f944e47..a13c88b 100644
--- a/registry/indexes/capabilities.yaml
+++ b/registry/indexes/capabilities.yaml
@@ -1,4 +1,19 @@
 version: 1
-updated: '2026-06-16'
+updated: '2026-10-14'
 domain: helix_forge
-capabilities: []
+capabilities:
+- id: capability.agents.performance-learning
+  name: Agent performance learning
+  summary: Capture sessions, curate patterns, distribute lessons and measure outcomes.
+  domain: infotech
+  status: draft
+  owner: agentic-resources
+  tags:
+  - security
+  - netkingdom
+  - framework-reuse
+  vector: D3 / A2 / C1 / R0
+  path: registry/capabilities/capability.agents.performance-learning.md
+  consumption_modes:
+  - CLI
+  - source