Draft capability entry (reuse-surface REUSE-WP-0017-T04, cohort 2)

Honest first-pass maturity vector grounded in README/docs/tests present
in this repo; no invented evidence. Flagged for human review before
publish. See reuse-surface history/2026-07-06-coverage-classification.md.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

registry/capabilities/capability.communication.context-engine.md

@@ -0,0 +1,121 @@
+---
+id: capability.communication.context-engine
+name: Kontextual Engine (Knowledge Operations Runtime)
+summary: Headless knowledge-operations engine turning heterogeneous information assets into persistent,
+  contextual, governed, retrievable, transformable, and agent-operable knowledge.
+owner: kontextual-engine
+status: draft
+domain: communication
+tags:
+- knowledge
+- context
+- runtime
+maturity:
+  discovery:
+    current: D4
+    target: D5
+    confidence: medium
+    rationale: INTENT.md, wiki/ProductRequirementsDocument.md, wiki/FunctionalRequirementsSpecification.md,
+      a scope-research bundle, and multiple architecture/implementation docs (architecture-blueprint,
+      architecture-core-implementation, asset-registry-implementation, stack-decision) document scope
+      and boundaries in real depth, including explicit boundary docs vs markitect-tool.
+  availability:
+    current: A1
+    target: A3
+    confidence: medium
+    rationale: Python package (`kontextual-engine`), pip-installable/importable; no packaged distribution
+      or hosted service documented yet.
+external_evidence:
+  completeness:
+    level: C1
+    confidence: low
+    basis: scope_vs_intent_and_consumer_expectations
+    satisfied_expectations:
+    - asset registry implementation documented
+    - explicit reuse-boundary docs vs markitect-tool
+    broken_expectations: []
+    out_of_scope_expectations: []
+  reliability:
+    level: R0
+    confidence: low
+    basis: consumer_quality_signals
+    known_reliability_risks:
+    - large surface area (persistent/contextual/governed/retrievable/transformable/agent-operable) with
+      implementation maturity not independently verified this sweep
+discovery:
+  intent: Turn heterogeneous information assets into persistent, contextual, governed, retrievable, transformable,
+    agent-operable knowledge as a headless runtime.
+  includes:
+  - asset registry and knowledge-operations runtime
+  - architecture documented in docs/architecture-blueprint.md and docs/architecture-core-implementation.md
+  excludes:
+  - markdown syntax-layer tooling (owned by markitect-tool, see docs/markitect-tool-reuse-boundary.md)
+  assumptions: []
+  use_cases: []
+  research_memos: []
+availability:
+  current_level: A1
+  target_level: A3
+  current_artifacts:
+  - Python package (`kontextual-engine`)
+  target_artifacts: []
+  consumption_modes:
+  - library import
+relations:
+  depends_on: []
+  supports: []
+  related_to: []
+evidence:
+  documentation:
+  - INTENT.md
+  - wiki/ProductRequirementsDocument.md
+  - docs/architecture-blueprint.md
+  tests:
+  - tests/
+  consumer_feedback: []
+  bug_reports: []
+  incidents: []
+consumer_guidance:
+  recommended_for:
+  - consumers needing a headless knowledge-operations runtime distinct from markdown-syntax tooling
+  not_recommended_for:
+  - needs for markdown-syntax transformation itself (see markitect-tool)
+  known_limitations:
+  - large documented scope; implementation maturity not independently re-verified this sweep
+promotion_history: []
+---
+
+# Kontextual Engine (Knowledge Operations Runtime)
+
+## Overview
+
+`kontextual-engine` is a headless knowledge-operations engine that turns heterogeneous information assets into persistent, contextual, governed, retrievable, transformable, and agent-operable knowledge, with an explicit boundary against the markdown-syntax layer owned by `markitect-tool`.
+
+## Assessment notes
+
+### Discovery
+
+INTENT.md, wiki/ProductRequirementsDocument.md, wiki/FunctionalRequirementsSpecification.md, a scope-research bundle, and multiple architecture/implementation docs (architecture-blueprint, architecture-core-implementation, asset-registry-implementation, stack-decision) document scope and boundaries in real depth, including explicit boundary docs vs markitect-tool.
+
+### Availability
+
+Python package (`kontextual-engine`), pip-installable/importable; no packaged distribution or hosted service documented yet.
+
+### Completeness
+
+First-pass honest assessment from the REUSE-WP-0017 coverage campaign
+(reuse-surface). No external consumer feedback exists yet; levels reflect
+scope-vs-intent documentation quality, not internal code quality.
+
+### Reliability
+
+No production consumer telemetry exists yet; reliability level is
+intentionally conservative pending REUSE-WP-0019 reuse-telemetry evidence.
+
+## Promotion checklist
+
+- [x] ID follows `capability.<domain>.<name>` pattern
+- [x] Maturity enums match `specs/CapabilityMaturityStandard.md`
+- [x] `external_evidence` is populated separately from `maturity`
+- [ ] Relations reference valid capability IDs (none yet)
+- [x] Index entry added in `registry/indexes/capabilities.yaml`

registry/indexes/capabilities.yaml

@@ -1,4 +1,19 @@
 version: 1
-updated: '2026-06-16'
+updated: '2026-07-06'
 domain: helix_forge
-capabilities: []
+capabilities:
+- id: capability.communication.context-engine
+  name: Kontextual Engine (Knowledge Operations Runtime)
+  summary: Headless knowledge-operations engine turning heterogeneous information assets into persistent,
+    contextual, governed, retrievable, transformable, and agent-operable knowledge.
+  vector: D4 / A1 / C1 / R0
+  domain: communication
+  status: draft
+  owner: kontextual-engine
+  path: registry/capabilities/capability.communication.context-engine.md
+  tags:
+  - knowledge
+  - context
+  - runtime
+  consumption_modes:
+  - library import