Link security knowledge to human decisions and guided runbooks

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a101af-e240-7882-a1e3-e37720cbdbea

workplans/EMERGENT-WP-0002-agent-security-knowledge-and-netkingdom-integration.md

@@ -387,3 +387,55 @@ remains active; a local pilot is not the completion contract.
 Evidence index: `docs/evidence/2026-10-03-implementation.md`. The remaining work
 is held by these live task IDs, not abandoned as prose. No DoD-Ok is claimed for
 EMERGENT-WP-0002, and no outside owner assent has been fabricated.
+
+
+## T11 — Link human decisions and guided procedures
+
+```task
+id: EMERGENT-WP-0002-T11
+title: Integrate informed-decision and runbook-tutorials as knowledge and offline handoffs
+status: done
+priority: high
+```
+
+User-directed follow-through (2026-10-03). Implement the existing owner split:
+Emergent Security orients, informed-decision presents/binds human decisions,
+approval-engine owns approval facts, access-engine decides, procedure owners
+execute with runbook-tutorials guidance. Do not create another PDP or assume
+unfinished automated intake/execution capabilities.
+
+Delivered: release 0.2.0, `decisions`/`runbooks` cards and startup discovery;
+24 owners/69 source files; `docs/decision-runbook-integration.md`; native v0.2
+orientation pack; concrete unsigned adoption draft checked with the real
+informed-decision validator. The proposed memo class/group is not an admitted
+grant. Nine real owner-contract tests cover accepted unsigned format, missing
+admission, forged binding/content and runbook prerequisites/manual-only behavior.
+Two additional retrieval tests verify owner withdrawal invalidates the relevant
+journey/startup without withholding unrelated guidance. The corpus now has
+28 scenarios; new provider evidence stays separately scoped to release 0.2.0.
+
+Acceptance: actual owner validators accept the local artifacts; negative
+contract tests pass; knowledge remains read-only and preserves owner limits.
+This task is complete for the local knowledge/offline handoff scope only.
+
+## Follow-through checkpoint — decision and runbook links, 2026-10-03
+
+T01/T03/T04/T06 remain delivered and are extended by T11. The earlier 0.1.1
+checkpoint and provider reports are historical evidence, not current-release
+claims. Current index: `docs/evidence/2026-10-03-decision-runbook-integration.md`.
+
+- T02: a concrete unsigned memo now targets the existing adoption question.
+  Decision `d20a9750-2b29-534e-8227-fb866581a6ca` remains open; no owner assent.
+- T05/T07: new scenarios exercise human/approval/engine evidence boundaries.
+  Actual compaction/harness proof, full Grok validation and independent review
+  remain open; an implementing agent's review cannot replace them.
+- T08/T09: existing pilot pointers discover the new release without instruction
+  rewrites. The preparation pack is schema/contract-tested; no attended real
+  run, fleet acknowledgment or owner feedback is claimed.
+- T09: automation dependencies are explicitly linked to INFD-WP-0005 and
+  RBT-WP-0006, including the existing runbook decision
+  `1e517449-2114-4a8f-9c6b-fcdbe977378e`. No duplicate owner task or invented
+  live integration is created. These optional automation features do not block
+  using the knowledge cards and offline preparation pack.
+- T10 stays waiting for the original completion contract. Independent review,
+  human adoption and external readiness cannot be asserted from local tests.