diff --git a/docs/ECC-2.0-GA-ROADMAP.md b/docs/ECC-2.0-GA-ROADMAP.md
index 35cf697d..7bcb3c4a 100644
--- a/docs/ECC-2.0-GA-ROADMAP.md
+++ b/docs/ECC-2.0-GA-ROADMAP.md
@@ -14,7 +14,7 @@ execution truth is split across:
 
 ## Current Evidence
 
-As of 2026-05-15:
+As of 2026-05-16:
 
 - GitHub queues are clean across `affaan-m/everything-claude-code`,
   `affaan-m/agentshield`, `affaan-m/JARVIS`, `ECC-Tools/ECC-Tools`, and
@@ -31,12 +31,14 @@ As of 2026-05-15:
   `ITO-59`) and five milestones: Security and Access Baseline, ECC 2.0 Preview
   and Publication, AgentShield Enterprise Iteration, ECC Tools Next-Level
   Platform, and Legacy Audit and Salvage.
-- `docs/releases/2.0.0-rc.1/publication-evidence-2026-05-15.md` records the
+- `docs/releases/2.0.0-rc.1/publication-evidence-2026-05-16.md` records the
   queue, discussion, Linear roadmap, ECC Tools access, Mini Shai-Hulud/TanStack
   full-campaign follow-up, scheduled supply-chain watch coverage, no-lifecycle
   CI install hardening, GitHub Actions cache purge, AgentShield #85
   registry-signature verification, AgentShield #86 evidence-pack CI provenance,
-  ECC-Tools #75 billing-gate tightening, and PR #1941 release-evidence refresh.
+  AgentShield #87 plugin-cache runtime-confidence classification, ECC-Tools #75
+  billing-gate tightening, PR #1947 supply-chain protection, and May 16
+  release-evidence refresh.
 - `npm run harness:audit -- --format json` reports 70/70 on current `main`.
 - `npm run observability:ready` reports 21/21 readiness on current `main`,
   including the GitHub/Linear/handoff/roadmap progress-sync contract.
@@ -86,6 +88,12 @@ As of 2026-05-15:
   and expanded the built-in attack corpus with an env proxy hijack scenario
   covering proxy/runtime mutation, env-token exfiltration, DNS exfiltration,
   credential-store access, and clipboard access.
+- AgentShield PR #87 merged as `26bb44650663816d07180e0d20c1895e431a326c`
+  and added installed Claude plugin-cache runtime confidence. Cached plugin
+  findings now emit `runtimeConfidence: plugin-cache`, non-secret score impact
+  stays at the intended `0.5x`, repository-local non-Claude `plugins/cache`
+  paths are not downgraded, and cached hook implementations no longer appear as
+  active top-level `hook-code`.
 - JARVIS PR #13 merged as `127efabbfb5033ae53d7a53e1546aa3c33d6f962`
   and hardened CI/deploy workflows with npm registry signature verification,
   disabled persisted checkout credentials in write-permission jobs, and pinned
@@ -506,11 +514,11 @@ is not complete unless the evidence column exists and has been freshly verified.
 | Naming and rename readiness | Naming matrix across package/plugin/docs/social surfaces | `docs/releases/2.0.0-rc.1/naming-and-publication-matrix.md` records current package, repo, Claude plugin, Codex plugin, OpenCode, and npm availability evidence | Complete for rc.1; post-rc rename remains future work |
 | Claude and Codex plugin publication | Contact/submission path with required artifacts and status | Publication readiness, naming matrix, and May 12 dry-run evidence document plugin validation, clean-checkout Claude tag/install smoke, and Codex marketplace CLI shape | Needs explicit approval for real tag/push and marketplace submission |
 | Articles, tweets, and announcements | X thread, LinkedIn copy, GitHub release copy, push checklist | Draft launch collateral exists under rc.1 release docs | Needs URL-backed refresh |
-| AgentShield enterprise iteration | Policy gates, SARIF, packs, provenance, corpus, HTML reports, exception lifecycle audit, baseline drift Action/CLI surfaces, evidence-pack redaction, harness adapter registry, enterprise research roadmap, supply-chain hardened release path, CI-safe baseline fingerprints, corpus accuracy recommendations, remediation workflow phases, env proxy hijack corpus coverage, Mini Shai-Hulud full-campaign package IOCs, and CI-provenance evidence packs | PRs #53, #55-#64, #67-#69, and #78-#86 landed with test evidence; native PDF export deferred in favor of self-contained HTML plus print-to-PDF until explicit enterprise demand appears; `docs/architecture/agentshield-enterprise-research-roadmap.md` now has baseline drift, evidence-pack bundle, redaction, adapter-registry, supply-chain hardening, hashed baseline fingerprints, corpus accuracy recommendation, remediation workflow, env proxy hijack corpus, Mini Shai-Hulud full-campaign package-table, and `ci-context.json` provenance slices landed | Next evidence-pack consumer/readback workflow depth |
+| AgentShield enterprise iteration | Policy gates, SARIF, packs, provenance, corpus, HTML reports, exception lifecycle audit, baseline drift Action/CLI surfaces, evidence-pack redaction, harness adapter registry, enterprise research roadmap, supply-chain hardened release path, CI-safe baseline fingerprints, corpus accuracy recommendations, remediation workflow phases, env proxy hijack corpus coverage, Mini Shai-Hulud full-campaign package IOCs, CI-provenance evidence packs, and plugin-cache runtime-confidence triage | PRs #53, #55-#64, #67-#69, and #78-#87 landed with test evidence; native PDF export deferred in favor of self-contained HTML plus print-to-PDF until explicit enterprise demand appears; `docs/architecture/agentshield-enterprise-research-roadmap.md` now has baseline drift, evidence-pack bundle, redaction, adapter-registry, supply-chain hardening, hashed baseline fingerprints, corpus accuracy recommendation, remediation workflow, env proxy hijack corpus, Mini Shai-Hulud full-campaign package-table, `ci-context.json` provenance, and `plugin-cache` confidence slices landed | Next evidence-pack consumer/readback workflow depth |
 | ECC Tools next-level app | Billing audit, PR checks, deep analyzer, sync backlog, evaluator/RAG corpus, analysis-depth readiness, hosted execution planning, hosted CI diagnostics, hosted security evidence review, hosted harness compatibility audit, hosted reference-set evaluation, hosted AI routing/cost review, hosted team backlog routing, hosted depth-plan check-run, PR-comment hosted job dispatch, hosted job result history/check-runs, hosted result status command, status-aware depth-plan recommendations, hosted promotion readiness, hosted promotion output scoring, hosted promotion retrieval planning, hosted promotion judge contract, gated hosted promotion judge execution, payment-announcement readiness | PRs #26-#43 plus #53-#74 landed with test evidence, including AgentShield evidence-pack gap routing, canonical bundle recognition, supply-chain signature gates, PR draft follow-up Linear tracking, evidence-backed/deep-ready repository classification, the `/api/analysis/depth-plan` hosted job plan, `/api/analysis/jobs/ci-diagnostics`, `/api/analysis/jobs/security-evidence-review`, `/api/analysis/jobs/harness-compatibility-audit`, `/api/analysis/jobs/reference-set-evaluation`, `/api/analysis/jobs/ai-routing-cost-review`, `/api/analysis/jobs/team-backlog-routing`, the `ECC Tools / Hosted Depth Plan` check-run, `/ecc-tools analyze --job ...` PR-comment dispatch, non-blocking per-hosted-job result check-runs backed by 30-day result cache records, `/ecc-tools analyze --job status` cache lookup, cache-aware next-job recommendations in the depth-plan check-run, the `ECC Tools / Hosted Promotion Readiness` corpus-backed PR check-run, deterministic hosted-output scoring against cached completed job artifacts/findings, ranked retrieval/model-prompt planning, the fail-closed `hosted-promotion-judge.v1` request contract, opt-in live model-judge execution behind hosted evidence, entitlement, budget, provider, executor, strict JSON, and citation gates, a fail-closed `/api/billing/readiness` `announcementGate` for native GitHub payments claims, and `npm run billing:announcement-gate` as the non-secret operator verifier | Next work is hosted promotion telemetry, operator review UX, and live Marketplace test-account readback |
 | GitGuardian/Dependabot/CodeRabbit-style checks | Non-blocking taxonomy, deterministic follow-up checks, and local supply-chain gates | ECC-Tools risk taxonomy check plus follow-up signals landed, including Skill Quality, Deep Analyzer Evidence, Analyzer Corpus Evidence, RAG/Evaluator Evidence, PR Review/Salvage Evidence, and AgentShield evidence-pack evidence; #1846 added npm registry signature gates; #1848 added the supply-chain incident-response playbook and `pull_request_target` cache-poisoning validator guard; #1851 added the privileged checkout credential-persistence guard; AgentShield #78, JARVIS #13, and ECC-Tools #53 applied the same hardening outside trunk | Current supply-chain gate complete; deeper hosted review features remain future |
 | Harness-agnostic learning system | Audit, adapter matrix, observability, traces, promotion loop | Audit/adapters/observability gates plus `docs/architecture/evaluator-rag-prototype.md`, `examples/evaluator-rag-prototype/`, and ECC-Tools PR #40 define read-only stale-salvage, billing-readiness, CI-failure-diagnosis, harness-config-quality, AgentShield policy-exception, skill-quality evidence, deep-analyzer evidence, and RAG/evaluator comparison scenarios with trace, report, playbook, verifier, and predictive-check artifacts; ECC-Tools PRs #68-#72 now turn that corpus into a deterministic PR check-run gate with cached hosted-output scoring, ranked retrieval candidates, a model prompt seed, a fail-closed hosted model-judge request contract, and opt-in live model execution behind strict hosted-evidence gates | Deterministic hosted PR check, cached output scoring, retrieval planning, judge contract, and gated model execution integrated |
-| Linear roadmap is detailed | Linear project status plus repo mirror | Repo mirror exists; issue creation was retried on 2026-05-12 and remains blocked by the workspace free issue limit; this May 15 sync adds ECC #1860, AgentShield #78-#86, JARVIS #13, ECC-Tools #53-#74, resolved queue/discussion counts, and a generated `operator:dashboard` prompt-to-artifact audit for recurring status updates | Needs recurring status updates after connector recovery |
+| Linear roadmap is detailed | Linear project status plus repo mirror | Repo mirror exists; issue creation was retried on 2026-05-12 and remains blocked by the workspace free issue limit; this May 16 sync adds ECC #1860, AgentShield #78-#87, JARVIS #13, ECC-Tools #53-#74, resolved queue/discussion counts, and a generated `operator:dashboard` prompt-to-artifact audit for recurring status updates | Needs recurring status updates after each significant merge batch |
 | Flow separation and progress tracking | Flow lanes with owner artifacts and update cadence | This roadmap defines lanes below and `docs/architecture/progress-sync-contract.md` makes GitHub/Linear/handoff/roadmap sync part of the readiness gate | Active |
 | Realtime Linear sync | Project updates while issue limit is blocked; issues later | ECC-Tools #39 implements opt-in Linear API sync for deferred follow-up backlog items, and ECC-Tools #54 adds copy-ready PR drafts to that backlog when draft PR shells are not opened; `docs/architecture/progress-sync-contract.md` defines the local file-backed realtime boundary while issue capacity is blocked | Needs workspace capacity/config rollout |
 | Observability for self-use | Local readiness gate, traces, status snapshots, HUD/status contract, risk ledger, progress-sync contract | `npm run observability:ready` reports 21/21 | Complete for local gate |
@@ -530,7 +538,7 @@ repo evidence and merge commits.
 | Release and publication | rc.1 release docs, publication readiness doc | Naming matrix and plugin submission/contact checklist | Before any tag |
 | Harness OS core | Audit, adapter matrix, observability docs, `ecc2/` | HUD/session-control acceptance spec | Weekly until GA |
 | Evaluation and RAG | Reference-set validation, harness audit, traces, ECC-Tools corpus | Read-only evaluator/RAG prototype plus stale-salvage, billing-readiness, CI-failure-diagnosis, harness-config-quality, AgentShield policy-exception, skill-quality evidence, deep-analyzer evidence, and RAG/evaluator comparison fixtures; ECC-Tools #68 publishes the corpus as a hosted promotion readiness check-run, #69 scores cached hosted job outputs against the same corpus, #70 emits ranked retrieval candidates plus a model prompt seed, #71 adds a fail-closed hosted model-judge request contract, and #72 executes that judge only when explicitly enabled and backed by hosted retrieval citations | Hosted promotion telemetry and operator review UX |
-| AgentShield enterprise | AgentShield PR evidence and roadmap notes | Remediation workflow depth or corpus expansion follow-up | Next implementation batch |
+| AgentShield enterprise | AgentShield PR evidence and roadmap notes | Evidence-pack consumer/readback workflow depth after plugin-cache confidence shipped in #87 | Next implementation batch |
 | ECC Tools app | ECC-Tools PR evidence, billing audit, risk taxonomy, evaluator/RAG corpus | ECC-Tools #53 published the supply-chain workflow hardening branch, #54 tracks copy-ready PR drafts in the Linear/project backlog, #55 classifies analysis-depth readiness, #56 exposes the hosted execution plan, #57 executes the first hosted CI diagnostics job, #58 executes the hosted security evidence review job, #59 executes the hosted harness compatibility audit, #60 executes the hosted reference-set evaluation, #61 executes the hosted AI routing/cost review, #62 executes hosted team backlog routing, #63 publishes the hosted depth-plan check-run, #64 dispatches hosted jobs from PR comments, #65 persists hosted result history/check-runs, #66 exposes hosted job status from PR comments, #67 makes depth-plan recommendations cache-aware, #68 publishes hosted promotion readiness from the evaluator/RAG corpus, #69 scores cached hosted job outputs against that corpus, #70 emits ranked retrieval candidates plus a model prompt seed, #71 emits the gated `hosted-promotion-judge.v1` contract without live model calls, #72 adds opt-in live model-judge execution behind hosted-evidence and strict JSON/citation gates, #73 adds a fail-closed native-payments `announcementGate` to billing readiness, and #74 adds `npm run billing:announcement-gate` for operator verification | Live Marketplace test-account readback and hosted promotion telemetry |
 | Linear progress | Linear project status updates, `docs/architecture/progress-sync-contract.md`, generated `operator:dashboard` output, and this mirror | Status update with queue/evidence/missing gates | Every significant merge batch |
 
@@ -749,7 +757,9 @@ Acceptance:
    exfiltration; PRs #83-#85 hardened Mini Shai-Hulud IOC coverage and
    release-path supply-chain verification; PR #86 added whitelisted
    `ci-context.json` workflow, commit, run, and runtime provenance to evidence
-   packs; and ECC-Tools PRs #42/#43 now route and recognize evidence packs.
+   packs; PR #87 classified installed Claude plugin caches separately from
+   active top-level runtime config, including cached hook implementations; and
+   ECC-Tools PRs #42/#43 now route and recognize evidence packs.
    The next slice is evidence-pack consumer/readback workflow depth.
 2. Run ECC-Tools `/api/billing/readiness` against a Marketplace-managed test
    account and require `announcementGate.ready === true` before any native
diff --git a/docs/architecture/agentshield-enterprise-research-roadmap.md b/docs/architecture/agentshield-enterprise-research-roadmap.md
index d47442fd..a861317f 100644
--- a/docs/architecture/agentshield-enterprise-research-roadmap.md
+++ b/docs/architecture/agentshield-enterprise-research-roadmap.md
@@ -1,6 +1,6 @@
 # AgentShield Enterprise Research Roadmap
 
-Generated: 2026-05-12
+Generated: 2026-05-12; refreshed with May 16 AgentShield PR #87 evidence.
 
 This is a planning artifact for the next AgentShield enterprise iteration. It
 does not modify AgentShield code. The goal is to turn the current scanner,
@@ -84,8 +84,15 @@ AgentShield is already more than a static lint tool:
 - Enterprise hooks exist: policy packs, exception metadata, expiring/expired
   exception reporting, SARIF code scanning, and job-summary output.
 - Accuracy work is active: `runtimeConfidence`, template/example weighting,
-  docs-example downgrades, hook-manifest resolution, false-positive audit
-  guidance, and corpus readiness.
+  docs-example downgrades, installed Claude plugin-cache confidence,
+  hook-manifest resolution, false-positive audit guidance, and corpus readiness.
+
+May 16 update: AgentShield PR #87 merged as
+`26bb44650663816d07180e0d20c1895e431a326c`. It classifies installed Claude
+plugin cache content as `runtimeConfidence: plugin-cache`, keeps non-secret
+plugin-cache score impact at `0.5x`, avoids downgrading repository-local
+non-Claude `plugins/cache` paths, and makes plugin-cache classification win
+before cached hook implementations would otherwise appear as active `hook-code`.
 
 The next iteration should not be "add more regex rules" by default. The higher
 leverage move is to make AgentShield remember, compare, route, and enforce
@@ -323,6 +330,8 @@ The AgentShield enterprise iteration is not complete until these are true:
 - Built CLI smoke tests cover the new flags or report modes.
 - GitHub Action self-test covers the new CI-visible output.
 - Documentation names the free/local path and the paid/team path separately.
+- Runtime-confidence changes include live scan evidence proving lower-confidence
+  plugin/package surfaces stay visible instead of being suppressed.
 - Evidence produced by the feature is deterministic enough for CI diffing.
 - ECC-Tools can consume the finding fingerprints or backlog export without
   exceeding GitHub/Linear object caps.
diff --git a/docs/releases/2.0.0-rc.1/preview-pack-manifest.md b/docs/releases/2.0.0-rc.1/preview-pack-manifest.md
index f9eb717b..9b792d2c 100644
--- a/docs/releases/2.0.0-rc.1/preview-pack-manifest.md
+++ b/docs/releases/2.0.0-rc.1/preview-pack-manifest.md
@@ -21,7 +21,7 @@ surfaces, or posting announcements.
 | `docs/releases/2.0.0-rc.1/launch-checklist.md` | Operator launch checklist | Must remain approval-gated for release, package, plugin, and announcement actions |
 | `docs/releases/2.0.0-rc.1/publication-readiness.md` | Release gate | Requires fresh evidence from the exact release commit |
 | `docs/releases/2.0.0-rc.1/publication-evidence-2026-05-15.md` | Current May 15 queue, roadmap, security, supply-chain watch, no-lifecycle CI install hardening, AgentShield #86 evidence-pack provenance, ECC Tools billing-gate, Actions cache purge, and `ecc2` test evidence through PR #1941 | Must be superseded by a final clean-checkout evidence file before real publication |
-| `docs/releases/2.0.0-rc.1/publication-evidence-2026-05-16.md` | Current May 16 queue cleanup, recsys skill merge, GateGuard triage, dashboard refresh, and combined Node/Rust/release-surface gate evidence through `cecab597` | Must still be repeated from a strict clean checkout before real publication |
+| `docs/releases/2.0.0-rc.1/publication-evidence-2026-05-16.md` | Current May 16 queue cleanup, recsys skill merge, GateGuard triage, PR #1947 supply-chain protection, AgentShield #87 plugin-cache confidence evidence, dashboard refresh, and combined Node/Rust/release-surface gate evidence through `6c8e909d` | Must still be repeated from a strict clean checkout before real publication |
 | `docs/releases/2.0.0-rc.1/naming-and-publication-matrix.md` | Naming, slug, and publication-path decision record | Keeps `Everything Claude Code / ECC`, npm `ecc-universal`, and plugin slug `ecc` for rc.1 |
 | `docs/releases/2.0.0-rc.1/x-thread.md` | X launch draft | Must replace placeholders with live URLs after release/package/plugin publication |
 | `docs/releases/2.0.0-rc.1/linkedin-post.md` | LinkedIn launch draft | Must replace placeholders with live URLs after release/package/plugin publication |
diff --git a/docs/releases/2.0.0-rc.1/publication-evidence-2026-05-16.md b/docs/releases/2.0.0-rc.1/publication-evidence-2026-05-16.md
index 75a7c8fc..fe92b618 100644
--- a/docs/releases/2.0.0-rc.1/publication-evidence-2026-05-16.md
+++ b/docs/releases/2.0.0-rc.1/publication-evidence-2026-05-16.md
@@ -7,9 +7,9 @@ npm publication, plugin tag, marketplace submission, or announcement post.
 
 | Field | Evidence |
 | --- | --- |
-| Upstream main | `cecab59747346ef3988305e5178b00652cb6d042` |
+| Upstream main | `6c8e909d630d233370160c10dad113b82002102c` |
 | Git remote | `https://github.com/affaan-m/everything-claude-code.git` |
-| Evidence scope | Current `main` after PR #1944, PR #1945, issue #1946 triage, ITO-57 sync, and operator dashboard refresh |
+| Evidence scope | Current `main` after PR #1944, PR #1945, issue #1946 triage, PR #1947 supply-chain protection, AgentShield PR #87, ITO-57 sync, and operator dashboard refresh |
 | Local status caveat | `git status --short --branch` showed `## main...origin/main` plus unrelated untracked `docs/drafts/` |
 
 The actual release operator should repeat all publish-facing checks from the
@@ -22,7 +22,7 @@ final release commit with a strictly clean checkout before publishing.
 | Trunk PRs | `gh pr list --state open --json number,title,url --limit 20` | `[]` |
 | Trunk issues | `gh issue list --state open --json number,title,url --limit 20` | `[]` |
 | Platform audit | `node scripts/platform-audit.js --json --allow-untracked docs/drafts/` | Ready; open PRs 0, open issues 0, discussion maintainer-touch gaps 0, discussion missing-answer gaps 0, blocking dirty files 0 |
-| Operator dashboard | `npm run operator:dashboard -- --json --allow-untracked docs/drafts/` | `dashboardReady: true`, `platformReady: true`, head `cecab59747346ef3988305e5178b00652cb6d042` |
+| Operator dashboard | `npm run operator:dashboard -- --json --allow-untracked docs/drafts/` | `dashboardReady: true`, `platformReady: true`, head `6c8e909d630d233370160c10dad113b82002102c` |
 
 ## Merge And Triage Batch
 
@@ -31,7 +31,10 @@ final release commit with a strictly clean checkout before publishing.
 | PR #1944 | Merged statusline ANSI palette update as `50ac061f9e72d7daa137f1bd08760cf74e9b577d`; targeted `node tests/hooks/ecc-statusline.test.js` and `node scripts/ci/validate-hooks.js` passed before merge |
 | PR #1945 | Merged `recsys-pipeline-architect` community skill as `9e973b29fb1a2a0aeb9e6980017b67c3ddb05201`; maintainer patches synced catalog counts and removed emoji blocked by Unicode safety |
 | Issue #1946 | Closed as triaged with a corrected maintainer comment; Linear `ITO-60` now tracks GateGuard proactive fact-forcing preflight UX |
+| PR #1947 | Merged scheduled supply-chain watch/advisory-source evidence as `4093d1bb7a14db1b4d4ea5bd00f2073baf94bfb0`; trunk now has the TanStack/Mini Shai-Hulud/node-ipc IOC scan plus advisory-source report surfaces wired into scheduled watch evidence |
+| AgentShield PR #87 | Merged plugin-cache runtime-confidence classification as `26bb44650663816d07180e0d20c1895e431a326c`; installed Claude plugin cache findings now emit `runtimeConfidence: plugin-cache`, `plugins/cache` only maps to Claude cache under `.claude`, and cached hook implementations are no longer mislabeled as active `hook-code` |
 | ITO-57 | Updated with PR #1947 advisory-source evidence, post-merge source refresh, IOC scan, npm audit/signature checks, and OpenAI app update caveat |
+| ITO-49 | Updated with AgentShield PR #87 merge, local test evidence, CI status, and live `~/.claude` scan classification counts |
 | ITO-44 | Updated with queue cleanup, dashboard refresh, and remaining macro gaps |
 
 ## Release Gate Commands
@@ -45,6 +48,7 @@ final release commit with a strictly clean checkout before publishing.
 | Harness audit | `npm run harness:audit -- --format json` | 70/70, no top actions |
 | Observability readiness | `npm run observability:ready` | 21/21, ready yes |
 | Supply-chain IOC scan | `npm run security:ioc-scan` | Passed; 227 files inspected |
+| Advisory source refresh | `npm run security:advisory-sources -- --refresh --json` | Ready; 9 active sources; Linear payload still points at `ITO-57` for sync |
 | npm audit | `npm audit --audit-level=moderate` | 0 vulnerabilities |
 | npm signatures | `npm audit signatures` | 241 verified registry signatures; 30 verified attestations |
 | Dashboard renderer | `node tests/scripts/operator-readiness-dashboard.test.js` | 7 passed, 0 failed |
diff --git a/docs/releases/2.0.0-rc.1/publication-readiness.md b/docs/releases/2.0.0-rc.1/publication-readiness.md
index 841084f5..40459c84 100644
--- a/docs/releases/2.0.0-rc.1/publication-readiness.md
+++ b/docs/releases/2.0.0-rc.1/publication-readiness.md
@@ -21,7 +21,8 @@ AgentShield #86 evidence-pack provenance, and `ecc2` current-dir guard evidence
 refresh through PR #1941, see
 [`publication-evidence-2026-05-15.md`](publication-evidence-2026-05-15.md).
 For the May 16 queue cleanup, recsys skill merge, GateGuard issue triage,
-operator dashboard refresh, and combined final-gate rerun on current `main`, see
+AgentShield #87 plugin-cache runtime-confidence evidence, operator dashboard
+refresh, and combined final-gate rerun on current `main`, see
 [`publication-evidence-2026-05-16.md`](publication-evidence-2026-05-16.md).
 For the operator-facing prompt-to-artifact readiness dashboard from the same
 May 16 pass, see
@@ -78,7 +79,7 @@ Record the exact commit SHA and command output before any publication action:
 | Queue baseline | `gh pr list` / `gh issue list` across trunk, AgentShield, JARVIS, ECC Tools, and ECC website | Under 20 open PRs and under 20 open issues | `publication-evidence-2026-05-16.md`: platform audit ready, 0 open PRs and 0 open issues across checked repos |
 | Discussion baseline | `node scripts/discussion-audit.js --json` | No unmanaged active discussion queue and no answerable Q&A missing an accepted answer | `publication-evidence-2026-05-15.md`: 58 trunk discussions, 0 without maintainer touch; other tracked repos disabled or 0 |
 | Linear roadmap | Linear project and issue readback | Detailed roadmap exists with release, security, AgentShield, ECC Tools, legacy, and observability lanes | `publication-evidence-2026-05-15.md`: project and 16 issue lanes recorded |
-| Operator readiness dashboard | `npm run operator:dashboard -- --allow-untracked docs/drafts/ --write docs/releases/2.0.0-rc.1/operator-readiness-dashboard-2026-05-15.md` | Current queue state mapped to macro-goal deliverables and incomplete gaps | `operator-readiness-dashboard-2026-05-15.md`: regenerated from `cecab597`, 0 open PRs, 0 open issues, 0 discussion gaps |
+| Operator readiness dashboard | `npm run operator:dashboard -- --allow-untracked docs/drafts/ --write docs/releases/2.0.0-rc.1/operator-readiness-dashboard-2026-05-15.md` | Current queue state mapped to macro-goal deliverables and incomplete gaps | `operator-readiness-dashboard-2026-05-15.md`: regenerated from `6c8e909d`, 0 open PRs, 0 open issues, 0 discussion gaps |
 
 ## Do Not Publish If
 
diff --git a/scripts/operator-readiness-dashboard.js b/scripts/operator-readiness-dashboard.js
index 54ced767..24e9c551 100644
--- a/scripts/operator-readiness-dashboard.js
+++ b/scripts/operator-readiness-dashboard.js
@@ -392,11 +392,11 @@ function buildRequirements(rootDir, platformReport) {
       'agentshield-enterprise-iteration',
       'Advance AgentShield enterprise iteration',
       'AgentShield PR evidence plus enterprise roadmap',
-      roadmap.includes('AgentShield Enterprise Iteration') && roadmap.includes('#78-#86')
+      roadmap.includes('AgentShield Enterprise Iteration') && roadmap.includes('#78-#87')
         ? 'in_progress'
         : 'not_complete',
       'AgentShield enterprise PR evidence is mirrored in the GA roadmap',
-      'live IOC update loop and cross-harness depth remain pending'
+      'cross-harness depth and evidence-pack consumer/readback workflow remain pending'
     ),
     buildRequirement(
       'ecc-tools-next-level',
diff --git a/tests/scripts/operator-readiness-dashboard.test.js b/tests/scripts/operator-readiness-dashboard.test.js
index d20d4400..353c8d41 100644
--- a/tests/scripts/operator-readiness-dashboard.test.js
+++ b/tests/scripts/operator-readiness-dashboard.test.js
@@ -47,7 +47,7 @@ function seedRepo(rootDir, overrides = {}) {
     'docs/ECC-2.0-GA-ROADMAP.md': [
       'https://linear.app/itomarkets/project/ecc-platform-roadmap-52b328ee03e1',
       'Linear ITO-44 ITO-59',
-      'AgentShield PR #86 #78-#86',
+      'AgentShield PR #87 #78-#87',
       'AgentShield Enterprise Iteration',
       'ECC-Tools PR #73',
       'hosted promotion',