Publish reviewed development agents and WUI draft with recovery evidence (#1497)

docs/SESSIONS.md

@@ -107,4 +107,35 @@ are never rewritten or removed; corrections are new entries.
 | 2026-09-07 17:37 UTC | darkwing | #1495 closeout | Local-conversion issue closed; Rocko notified, Filbert/Dewey unconfirmed; canonical identity documented; no push |
 | 2026-09-07 17:45 UTC | darkwing | Relocation relaunch handoff | Recorded agents/darkwing/work/RESTART.md and CONTEXT pointer; no launcher/private-session edits; current conversation continuity not assumed |
 
+| 2026-09-08 12:18 UTC | Codex | Executive-update skill sync | Added skills/ms-executive-update/SKILL.md byte-identical to operator local skill: readable timezone timestamp and full three-section updates; structural validation passed using temporary frontmatter-compatible copy; historical parser fixtures preserved; no runtime activation |
+| 2026-09-08 12:48 UTC | Codex | Owner-requested Dewey frontend/UX agent | Added native launcher, SOUL, context, resume validator and usage documentation; parameterized isolated launcher tests pass for Darkwing and Dewey (3 tests total); real Dewey --check passes; no model call, commit or push |
+| 2026-09-08 12:53 UTC | Codex | Owner-requested Rocko/Filbert and Darkwing team lead | Added Claude/Fable Rocko launcher with dedicated UUID resume, Pi Filbert launcher fixed to openai-codex/gpt-6-astra:low, and team roles/docs; five offline launcher tests and both real --check commands pass; no live model session, commit or push |
+| 2026-09-08 | dewey | Jason-assigned WUI branding discovery and five future HTML mockups | Requirements and approval sequence recorded in agents/dewey/work/wui/BRIEF.md; frontend-design skill loaded; branding questions pending; no legacy UI inspection, implementation, or queue change |
+
+- 2026-09-07 — darkwing — owner-authorized commit/push wave: five grouped commits local; A9 accepted and recorded; task/release 90/0 and 14/0 after owner lifted deferral. Independent tmux screen-confirmation candidates rejected; owner selected transport-only contract. Frozen R4 submitted for independent review; transport exit 0 is not ACK. No push or issue closure; registry review follows completed wave.
+- 2026-09-08 | Filbert | Independent frozen tmux transport R4 review | NOT APPROVED: remote session/retry shell injection reproduced with fake ssh/tmux; five isolated suites pass; manifest verified before/after; verdict docs/plans/reviews/2026-09-07_tmux-transport-r4-verdict.md; prior rejections preserved; no live-seat sends, source edits, or commits.
+
+| 2026-09-08 | dewey | Owner-goal WUI brand-board review handoff | agents/dewey/work/wui/index.html and README.md delivered; 3 marks, 3 fonts, 10 palettes x 3 modes; Chromium contrast/layout/keyboard/download/fallback checks pass with VERIFY.md limits; awaits Jason branding review; no v1, dashboard/backend work, integration, deployment, commit or push |
+- 2026-09-08 | Filbert | Independent frozen tmux transport R5 review | APPROVED transport-only at manifest bc6063412ce2dd43bd7e929d7ef41cedcb4c53c7132c8e5d27f9481910e53ae8: R4-F1 remote quoting fixed and independently attacked through /bin/sh stubs; six suites pass isolated; real hidden-draft and cleanup controls pass; R4 rejection preserved; verdict docs/plans/reviews/2026-09-07_tmux-transport-r5-verdict.md; no live-seat sends, source/export edits, or commits.
+
 - darkwing — authorized wave complete: approved R5 transport-only fix 69f10a40, refactor plus 17 tags remotely verified; A9 recorded; #53 published inclusion evidence for Jason closure; registry review next; unrelated relocation work excluded.
+
+- 2026-09-08 — darkwing — #1497 publication/planned-restart trial authorized; inventory and plan recorded, Rocko checkpoint and Dewey author-boundary requests dispatched transport-only; no ACK/restart/recovery/publication claimed. Registry review deferred; C1/ACT-1 held.
+
+- 2026-09-08 — darkwing for PUB-REC-ROCKO-1 — Rocko bounded inventory/checkpoint received; coordinator verified hashes and isolated unexecuted test, owns shared registration due three-artifact task limit. Checkpoint ready for Jason normal restart; recovery not yet tested; runtime identifiers excluded from publication pending curated evidence.
+- 2026-09-08 | Filbert | PUB-REC-FILBERT-WUI-1 independent WUI draft-publication review | APPROVED at manifest a585c1eedb17044962c0419861a1032b23409b769c5d304aceff6ef6089a0e11 (53 files verified before/after); standalone deps closed, no network refs; font OFL provenance verified; author claims reproduced exactly on fresh isolated reruns (840/8220/240, 0 failures); two coordinator-judgment notes (F1 full name, F2 owner quote); visual pixel inspection bounded NOT RUN; verdict docs/plans/reviews/2026-09-08_publication-trial-wui-verdict.md; no source edits, git ops, or live-seat mutation.
+- 2026-09-08 | Filbert | WUI verdict correction appended (terminal-log notice) | Publication-safety section had credited coordinator PNG inspection that actually occurred after the verdict; correction appended to docs/plans/reviews/2026-09-08_publication-trial-wui-verdict.md citing the disposition record; reviewer visual NOT RUN unchanged; no reply sent per sender instruction.
+
+- 2026-09-08 — darkwing for PUB-REC-ROCKO-1 — worker recovery artifact received; recorded one reserved isolated test invocation, 1 pass/0 fail exit 0. Coordinator verified pinned test/launcher and pre/post-send artifact hashes; owner restart/neutral continue reports recorded. Raw runtime identifiers excluded from publication; curated summary and frozen evidence sent to Filbert for independent bounded recovery review. Trial acceptance remains pending.
+- 2026-09-08 | Filbert | PUB-REC-FILBERT-RECOVERY-1 independent recovery-evidence review | Bounded planned-checkpoint recovery SUPPORTED; curated summary APPROVED for publication at 0e17757cfd3af3bfd3003957550d78c37d32c2b11c75c2b10c76fb9bb5a28a07; all ten snapshot hashes verified at manifest b52a6215, pre-send recovery prefix 52778f1a reproduced exactly, reserved-test isolation confirmed by source read without rerun; inference/procedural limits preserved; verdict docs/plans/reviews/2026-09-08_publication-trial-recovery-verdict.md; no execution, private reads, or git ops.
+
+- 2026-09-08 — darkwing — PUB-REC-FILBERT-RECOVERY-1 independently SUPPORTS bounded planned-checkpoint recovery and APPROVES summary 0e17757c; conditions accepted, originals remain local. Inventory fixes: bounded Pi fixture copy (4 tests passed), TOOLS flags, inactive skill compatibility/provenance note. PUB-REC-FILBERT-LAUNCHER-1 sent to Filbert/default at manifest 8900faf1 for exact 23-candidate review; transport exit 0, application acceptance unknown. Return event: declared launcher verdict; follow-up owner Darkwing. No trial acceptance or publication yet.
+- 2026-09-08 | Filbert | PUB-REC-FILBERT-LAUNCHER-1 final launcher candidate review | APPROVED for publication: 23 candidates at manifest 8900faf1 (57/57 hashes verified before/after); fixture reruns 4/4 and 1/1 pass in disposable copy; pinned rocko test/launcher and SKILL.md byte-identical to prior pins; host/container separation, refusals, session validation, docs consistency, and publication-safety scan all verified; two non-blocking notes (cosmetic duplicate assignment, argv observation left documented); verdict docs/plans/reviews/2026-09-08_publication-trial-launcher-verdict.md; no live launches, private reads, or git ops.
+
+- 2026-09-08 — darkwing — Owner Sonnet launcher change reconciled with README and isolated test expectation; 1 pass/0 fail, no model call. PUB-REC-FILBERT-SONNET-1 focused review requested; historical recovery evidence unchanged, revised publication bytes require new approval.
+- 2026-09-08 | Filbert | PUB-REC-FILBERT-SONNET-1 focused sonnet-delta review | REQUEST CHANGES: three-file delta itself correct/minimal (launch.sh, test, README all sonnet-consistent; isolated rerun 1/1 pass; recovery evidence untouched) but agents/rocko/CONTEXT.md in the same snapshot still says Fable at launch injection, and previously approved agents/README.md + agents/darkwing/SOUL.md carry stale Fable references; refreshed narrow delta converts to approval; verdict docs/plans/reviews/2026-09-08_publication-trial-sonnet-verdict.md; no live launches or private reads.
+
+- 2026-09-08 — darkwing — SONNET-F1/F2 fixed after independent REQUEST CHANGES: three context/team model references now match Sonnet; combined isolated launcher tests 5/5 pass. PUB-REC-FILBERT-SONNET-2 frozen delta sent for re-review, transport exit 0 application acceptance unknown; required return is R2 verdict, follow-up Darkwing. Earlier rejected verdict and historical recovery bytes preserved.
+- 2026-09-08 | Filbert | PUB-REC-FILBERT-SONNET-2 focused sonnet-delta round-2 review | APPROVED: three one-line Fable-to-Sonnet repairs verified minimal (rocko CONTEXT.md, agents/README.md, darkwing SOUL.md); no fable references remain in the seven-file snapshot at manifest c5ad6306; combined fixtures rerun independently 5/5 pass in disposable harness over approved dependencies; exactly six changed candidates vs original approval; R1 rejection preserved; verdict docs/plans/reviews/2026-09-08_publication-trial-sonnet-r2-verdict.md; no live launches or private reads.
+
+- 2026-09-08 — darkwing — PUB-REC-FILBERT-SONNET-2 independently APPROVED six revised publication candidates at c5ad6306, combined reviewer fixtures 5/5 passed. Coordinator verified seven frozen/live file hashes, no drift. R1 rejection and historical recovery bytes preserved. Acknowledgement transport exit 0, application acceptance unknown; no reply requested. Final selective publication remains pending.

docs/TOOLS.md

@@ -61,7 +61,7 @@ for the M13 plain governed TUI. `--auth <account>` injects
 For native repository development, opt in with a **leading** `--host-dev`:
 
 ```bash
-scripts/agent.sh --host-dev darkwing [--fresh] [--check] [--soul FILE] [--constitution FILE] [--user FILE]
+scripts/agent.sh --host-dev darkwing [--fresh] [--check] [--soul FILE] [--constitution FILE] [--user FILE] [--provider NAME] [--model ID] [--thinking LEVEL]
 ```
 
 This mode delegates to `scripts/agent-host-dev.sh`, uses host Pi and repository

docs/plans/2026-09-08_publication-recovery-trial.md

@@ -0,0 +1,35 @@
+# Publication and planned-restart trial
+
+Owner: Jason. Coordinator: Darkwing. Authorized by Jason's final `agreed` after ms-grill-me rounds 1–4. Baseline HEAD: 3b7fd19d087226b1887bf017fc10ef16b044f6aa, branch refactor, canonical checkout /mnt/storage/src/mosaic-stack.
+
+## Outcome
+
+Publish the remaining reviewed repository changes and prove a useful development assignment survives one planned participating-agent restart without Jason reconstructing its briefing. The operator performs the restart only after checkpoint readiness is established. This is a planned-checkpoint test, not crash recovery or production orchestration certification.
+
+## Scope and owner decisions
+
+Publish reviewed source, tests, skills, records, agent definitions/launchers and useful design drafts. Exclude credentials, private transcripts, runtime/session state, dependencies and generated caches. Inspect evidence/screenshots for publication safety and license provenance; do not decide from filename alone. Agent relocation to ~/.mosaic-dev is deferred. Existing tracked agents are not removed. C1 and ACT-1 remain held. Registry alignment is deferred behind this owner-prioritized trial, not automatically resumed.
+
+Design drafts may be published with explicit pending-owner-acceptance labels. Publication does not approve WUI branding or authorize implementation/deployment. No force push, next/main merge, agent relocation, live config change or runtime authority expansion. Commit/push authorization is this trial's reviewed refactor changes only.
+
+## Roles and stages
+
+1. Darkwing inventories candidate paths and captures an exact review manifest; original authors retain ownership of their active files.
+2. Rocko is requested for bounded publication inventory/checkpoint work, separate from HELD Archify C1. No source ownership transfer. He reports any conflict rather than absorbing another active assignment.
+3. Dewey is requested to identify his publishable WUI draft boundary, original/license sources, test limits and active writes. Do not freeze or adopt his work without reconciliation.
+4. Filbert independently reviews the exact frozen publication candidate and recovery evidence. He must report any authorship/conflict; no self-approval.
+5. Rocko writes a durable checkpoint covering assignment/authority, decisions, evidence, incomplete work, unknown external outcomes and exact next action. He stops before that next action. Darkwing checks it without injecting an alternate briefing. Jason restarts Rocko when told ready.
+6. After normal resume, Rocko recovers the records without a reconstructed task prompt, states the checkpoint and performs the declared next bounded action once. Verify with artifacts and command/result evidence, not self-reported recall alone. If normal resume fails, record that failure before any assisted recovery; do not manufacture a pass.
+7. Applicable source and isolated launcher suites, publication-safety review and independent candidate approval precede selective commits and push. Verify fresh origin/refactor identity. Present end-to-end evidence to Jason for acceptance.
+
+## Gates and current state
+
+- Authorized plan: confirmed.
+- Initial inventory: 94 untracked candidate paths under agents/scripts/skills plus modified launchers/persona/shared records. Counts are a snapshot, not a safety verdict.
+- Worker assignment and author boundary: complete. WUI exact 53-file draft independently approved at a585c1ee, pending owner design acceptance.
+- Planned checkpoint recovery: independently SUPPORTED; curated summary 0e17757c APPROVED. Operator-reported restart, inferred resume mode and worker-reported execution count remain qualified. Raw runtime records stay local.
+- Source approval: 23 original candidates at 8900faf1, with six Sonnet revisions superseded by approved c5ad6306. Independent isolated tests 5/5 passed.
+- Final publication inventory and candidate-tree verification: in progress. Since approval, the executive-update skill changed, the tracked ms-agent-watch skill was deleted locally, and additional untracked skills appeared. These newer changes have no trial review or ownership handoff; preserve and exclude them, including the executive-update compatibility note. Do not restore deleted files or silently publish stale skill bytes.
+- Publication / remote verification / owner trial acceptance: pending. No live launches or unrelated skill migration is authorized.
+
+No new /goal lifecycle is claimed by this document. Use this task plan and artifacts for tracking; an operator-set goal extension remains sole lifecycle owner.

docs/plans/CURRENT.md

@@ -7,9 +7,33 @@ update this file to the next action). No ambiguity, no re-planning.
 
 ## Next action
 
-Review `docs/plans/2026-09-03_auth-provider-harness-registry.md` and reconcile
-Gate 7 with later owner decisions and #53's workspace/session model. This is
-registry review alignment only; no registry implementation is authorized.
+Execute Jason's approved publication and planned-restart recovery trial (#1497).
+Plan: `docs/plans/2026-09-08_publication-recovery-trial.md`. Publish remaining
+reviewed changes, temporarily including agent definitions and labeled drafts;
+exclude private runtime/session/auth state. Jason performed Rocko's planned restart
+and issued neutral continue; PUB-REC-ROCKO-1 returned its reserved test PASS.
+Filbert independently SUPPORTS bounded checkpoint recovery and APPROVES the pinned
+privacy-safe summary (0e17757c); raw records stay local. No reliability or overall
+trial acceptance inferred. WUI exact 53-file draft publication is independently
+APPROVED with pending-acceptance label; source/default revisions remain unimplemented.
+PUB-REC-FILBERT-LAUNCHER-1 APPROVED 23 source/publication candidates at
+frozen manifest 8900faf1. Jason then changed Rocko's launcher to Sonnet.
+PUB-REC-FILBERT-SONNET-2 APPROVED the six revised candidates at c5ad6306;
+coordinator verified all seven R2 snapshot/live files unchanged. Remaining original
+candidate approvals stand. Independent combined fixtures passed 5/5. Preserve
+R1 REQUEST CHANGES and the historical Fable recovery evidence unchanged.
+Next gate: final tests and exact selective publication inventory with private raw
+records excluded, then commit/push refactor and request Jason's trial acceptance.
+Newer executive-update skill edits, local ms-agent-watch deletion and additional
+untracked skills are outside the pinned trial candidate. Preserve them uncommitted;
+exclude both executive-update files rather than publish unreviewed or stale bytes.
+Verify the prospective publication tree separately; live native launch would refuse
+because its required ms-agent-watch file is now locally absent. No live launch or
+unrelated skill migration is part of this trial.
+No further restart or re-briefing requested. C1 remains HELD.
+
+Registry review alignment is deferred behind this newly prioritized owner trial.
+No registry implementation, agent relocation, main/next merge or deployment authorized.
 
 Completed commit/push wave: R5 transport-only tmux correction independently
 APPROVED by Filbert, published on refactor at
@@ -141,6 +165,10 @@ and unfinished-fixture status.
 
 ## Completed log
 
+- 2026-09-08 — Owner-requested development team: Rocko launches Claude Code with Fable; Filbert launches Pi with `openai-codex/gpt-6-astra:low`; Darkwing is the development team lead and Dewey remains frontend/UX owner. Five offline launcher tests and both new agents’ local configuration checks pass. No model session started; inspector acceptance queue unchanged.
+
+- 2026-09-08 — Owner-requested Dewey frontend/UX agent: `agents/dewey/launch.sh` uses the shared native launcher with its own persona, context and session history. Offline launcher checks pass for both agents and real Dewey `--check` passes; no model session started. Current inspector acceptance queue unchanged.
+
 - 2026-09-07 — Owner-directed concept annexation: [Mosaic concepts](../concepts/README.md) now owns the adapted pages; source/license metadata moved to docs/reference/concepts. Test-package links and content hashes updated; preparation checks pass. Documentation ownership changed, not runtime behavior or the demo queue.
 
 - 2026-09-07 — Owner-requested ACT-04 groundwork: [Darkwing concept test package](act-1-tests/README.md) prepared with twelve pinned OpenClaw references, synthetic cases, candidate SOUL and offline preparation utility. Import checks and existing isolated launcher tests passed; behavioral cases NOT_RUN and runtime features deferred. Current demo queue unchanged.

docs/plans/reviews/2026-09-08_publication-trial-final-inventory.json

@@ -0,0 +1,99 @@
+{
+  "snapshot": "/tmp/pub-rec-final-review-f5br4ch4",
+  "manifestSha256": "3f8e765bded8bbd66d791f7fb761cb6ee3c438b5318a115baa9cc9c0ec75d2e4",
+  "count": 90,
+  "paths": [
+    "BUILD-LOG.md",
+    "agents/README.md",
+    "agents/darkwing/SOUL.md",
+    "agents/dewey/CONTEXT.md",
+    "agents/dewey/README.md",
+    "agents/dewey/SOUL.md",
+    "agents/dewey/launch.sh",
+    "agents/dewey/validate-sessions.mjs",
+    "agents/dewey/work/wui/BRIEF.md",
+    "agents/dewey/work/wui/DECISIONS.md",
+    "agents/dewey/work/wui/HISTORY.md",
+    "agents/dewey/work/wui/PUBLICATION.md",
+    "agents/dewey/work/wui/README.md",
+    "agents/dewey/work/wui/RESEARCH.md",
+    "agents/dewey/work/wui/TASKS.md",
+    "agents/dewey/work/wui/VERIFY.md",
+    "agents/dewey/work/wui/assets/fonts/dm-sans-400.woff2",
+    "agents/dewey/work/wui/assets/fonts/dm-sans-500.woff2",
+    "agents/dewey/work/wui/assets/fonts/dm-sans-600.woff2",
+    "agents/dewey/work/wui/assets/fonts/dm-sans-700.woff2",
+    "agents/dewey/work/wui/assets/fonts/dm-sans-OFL.txt",
+    "agents/dewey/work/wui/assets/fonts/dm-sans-sources.txt",
+    "agents/dewey/work/wui/assets/fonts/ibm-plex-sans-400.woff2",
+    "agents/dewey/work/wui/assets/fonts/ibm-plex-sans-500.woff2",
+    "agents/dewey/work/wui/assets/fonts/ibm-plex-sans-600.woff2",
+    "agents/dewey/work/wui/assets/fonts/ibm-plex-sans-700.woff2",
+    "agents/dewey/work/wui/assets/fonts/ibm-plex-sans-OFL.txt",
+    "agents/dewey/work/wui/assets/fonts/ibm-plex-sans-sources.txt",
+    "agents/dewey/work/wui/assets/fonts/manrope-400.woff2",
+    "agents/dewey/work/wui/assets/fonts/manrope-500.woff2",
+    "agents/dewey/work/wui/assets/fonts/manrope-600.woff2",
+    "agents/dewey/work/wui/assets/fonts/manrope-700.woff2",
+    "agents/dewey/work/wui/assets/fonts/manrope-OFL.txt",
+    "agents/dewey/work/wui/assets/fonts/manrope-sources.txt",
+    "agents/dewey/work/wui/assets/logos/aperture.svg",
+    "agents/dewey/work/wui/assets/logos/assembly.svg",
+    "agents/dewey/work/wui/assets/logos/relay.svg",
+    "agents/dewey/work/wui/assets/palettes.json",
+    "agents/dewey/work/wui/board.js",
+    "agents/dewey/work/wui/brand.js",
+    "agents/dewey/work/wui/checks/assets.mjs",
+    "agents/dewey/work/wui/checks/browser.mjs",
+    "agents/dewey/work/wui/checks/detail-checks.mjs",
+    "agents/dewey/work/wui/checks/fetch-fonts.py",
+    "agents/dewey/work/wui/checks/final-checks.mjs",
+    "agents/dewey/work/wui/checks/references.mjs",
+    "agents/dewey/work/wui/checks/verify.mjs",
+    "agents/dewey/work/wui/evidence/board-dark-1440.png",
+    "agents/dewey/work/wui/evidence/board-dim-1440.png",
+    "agents/dewey/work/wui/evidence/board-light-1440.png",
+    "agents/dewey/work/wui/evidence/board-light-3440.png",
+    "agents/dewey/work/wui/evidence/board-light-390.png",
+    "agents/dewey/work/wui/evidence/detail-verification.json",
+    "agents/dewey/work/wui/evidence/final-verification.json",
+    "agents/dewey/work/wui/evidence/section-color-ultrawide.png",
+    "agents/dewey/work/wui/evidence/section-components-mobile.png",
+    "agents/dewey/work/wui/evidence/section-identity-light.png",
+    "agents/dewey/work/wui/evidence/section-review-light.png",
+    "agents/dewey/work/wui/evidence/section-typography-light.png",
+    "agents/dewey/work/wui/evidence/verification.json",
+    "agents/dewey/work/wui/index.html",
+    "agents/dewey/work/wui/styles.css",
+    "agents/filbert/CONTEXT.md",
+    "agents/filbert/README.md",
+    "agents/filbert/SOUL.md",
+    "agents/filbert/launch.sh",
+    "agents/filbert/validate-sessions.mjs",
+    "agents/rocko/CONTEXT.md",
+    "agents/rocko/README.md",
+    "agents/rocko/SOUL.md",
+    "agents/rocko/launch.sh",
+    "docs/SESSIONS.md",
+    "docs/TOOLS.md",
+    "docs/plans/2026-09-08_publication-recovery-trial.md",
+    "docs/plans/CURRENT.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-inventory-disposition.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-launcher-approval-receipt.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-launcher-verdict.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-launcher.sha256",
+    "docs/plans/reviews/2026-09-08_publication-trial-recovery-summary.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-recovery-verdict.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-sonnet-r2-verdict.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-sonnet-verdict.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-wui-condition-disposition.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-wui-verdict.md",
+    "docs/plans/reviews/2026-09-08_publication-trial-wui.sha256",
+    "scripts/agent-host-dev.sh",
+    "scripts/agent.sh",
+    "scripts/test-darkwing-launch.mjs",
+    "scripts/test-rocko-launch.mjs"
+  ],
+  "baseline": "3b7fd19d087226b1887bf017fc10ef16b044f6aa",
+  "excluded": "all other worktree changes; raw worker records, unreviewed skills and skill deletion, nonallowlisted WUI evidence"
+}

docs/plans/reviews/2026-09-08_publication-trial-final.sha256

@@ -0,0 +1,90 @@
+2b47053a78aa6d9826282cb0d63cda3e05d7311b6b21dff3cab8078b80b15b3e  BUILD-LOG.md
+2e1f5ec05031ab10372443585861b12b9981ab311bd9c815620d22c1718a4483  agents/README.md
+08b93c59b4f9ff427deb8c2e8d88daf75e86bdddf61354f108f61cbf1beb5955  agents/darkwing/SOUL.md
+61d640098d8ad79c9c069ea761c8a50c5f644cb914a253fe037132c61a4c421c  agents/dewey/CONTEXT.md
+908a5e6e9eea2be2b190ba87a7dade4fa6228bea21aec0b09746a5176fdeda06  agents/dewey/README.md
+b156fd7c76dfe7c8eb421aeed9d3fd1b681456ca96961d5a010cbe8e1ecf0e33  agents/dewey/SOUL.md
+b6a21d5ae195664612c1dd3f96670934f92025ea100c0e669fa4f7cacd5974f7  agents/dewey/launch.sh
+d0136b89509edff48aa0e2ee398acb7cc7ccd47255225823e47892c57384e60b  agents/dewey/validate-sessions.mjs
+c71e0c80c5976fbe5048624a7656ed9812164e3969f6ba76c43239e17746d20a  agents/dewey/work/wui/BRIEF.md
+3c86ba0fd6aa894489caf83f6bff8fd94138c3ddd5f5b33858ef21426f8fce65  agents/dewey/work/wui/DECISIONS.md
+a7ad1f585702886de2d338f530ca5d29130c4acf8682c5d391f1b9e53bf86fe8  agents/dewey/work/wui/HISTORY.md
+66d036c238553ea200b0236e8bb965de7634d27869221109cbd506cfe4eefbaf  agents/dewey/work/wui/PUBLICATION.md
+e9cac40fe832d36429f02c4b0fa3e50cf63ccf3457b08e0326b8fc1b6c227b49  agents/dewey/work/wui/README.md
+fcc6d1ec1a35713f1bf765cbe83c9e526a4907d0cd2ce8889a2ef9ed6c54b25d  agents/dewey/work/wui/RESEARCH.md
+04f2624b507109943d5e3ff5732c66d13816313e54a867ac1852341fb90cd309  agents/dewey/work/wui/TASKS.md
+63e96d72b6afd4eb8058c8b5b6846dbaa1c808dec1054ab23bfb3f5871f78801  agents/dewey/work/wui/VERIFY.md
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-400.woff2
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-500.woff2
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-600.woff2
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-700.woff2
+9af36190332437f5ecd09974de43c1f7c77a310a996cdd8ceb25628b458840e1  agents/dewey/work/wui/assets/fonts/dm-sans-OFL.txt
+89947da00bec2cbcacab815b7e36bf07a635dec41e3ca87a6eb2484a605a4e71  agents/dewey/work/wui/assets/fonts/dm-sans-sources.txt
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-400.woff2
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-500.woff2
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-600.woff2
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-700.woff2
+7e6b2818edbd8f6a01ae80641cc8f16a51080d08fb4e532be3a0b6f74adb07da  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-OFL.txt
+a762adc472b0911c4f5d0e3f0dd672c557c4b3debbc9b617488b46c36e10b183  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-sources.txt
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-400.woff2
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-500.woff2
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-600.woff2
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-700.woff2
+e01b637272e0cbdfb240184dd98ea5cc671556d9894dae2668d92ab2c906787c  agents/dewey/work/wui/assets/fonts/manrope-OFL.txt
+0d9aaaaa963b675d94d8fbee0cf47a8ecf03ea412f8b14aba96416375e5a2bb5  agents/dewey/work/wui/assets/fonts/manrope-sources.txt
+a1a047eb0b7f9c8f3e656d97d2292545371f8f0a92b4eb273cfd2fc371bd50ad  agents/dewey/work/wui/assets/logos/aperture.svg
+d3d0eb03872b7336b00186beb95567840e5caf2bef29c2a9599480b29eb2f8da  agents/dewey/work/wui/assets/logos/assembly.svg
+446cb7c0b75bb5cc7e3e08d9feb979c000531adfba0523aec81fb9af77f1ae55  agents/dewey/work/wui/assets/logos/relay.svg
+9efa30b490fa2cde89dcd3c9eafd37ae83a77a84a2a1965c78828e410be2b568  agents/dewey/work/wui/assets/palettes.json
+31222b6c40af7f253cceccc3d3caef5c2b0f9c0e096ea2eb5828b2224c3c47fe  agents/dewey/work/wui/board.js
+d568df6dca14ae336db3b627639c8181c088649a21ffe992f9bfacc20b5b6238  agents/dewey/work/wui/brand.js
+e884333a3191921050c6ab45c7d87d40c6bc3092ba9d55c3c06bc5f0d01d5da3  agents/dewey/work/wui/checks/assets.mjs
+3ff14de07e87cc624433db6425b9d05e40d98f61e40f2bbf1fbee7431f9d73c1  agents/dewey/work/wui/checks/browser.mjs
+16b3cf3f7c8897dddef3b4caf1e9200272078cea8226a6df5e9ea1e7d25fe598  agents/dewey/work/wui/checks/detail-checks.mjs
+af924e53a19e3a639e5bc4c1e6a27253d03adcd935a8e1a847806761b797336c  agents/dewey/work/wui/checks/fetch-fonts.py
+fd7d5baad1eb01c41ae98e1341aa5b16bb22e02f5296951381f48705b42d6855  agents/dewey/work/wui/checks/final-checks.mjs
+df79defbecf1500b6b5abdf7f0568c22ae88b437e841f0c95a7fa16d5d5fd3d2  agents/dewey/work/wui/checks/references.mjs
+bd6cc0c1021401207519e3489105284d120da2d8b85710e8fd51c1939f10e411  agents/dewey/work/wui/checks/verify.mjs
+41d4aababef4fdd5beff4f0b75fcdcd59e9a2fdf408a6a7aaf9f7afd86d1ac02  agents/dewey/work/wui/evidence/board-dark-1440.png
+9599769f4ed18363c3b7c0061823e0fd772d9cd516d3f72ab02e7b74a01de93c  agents/dewey/work/wui/evidence/board-dim-1440.png
+d8097a2896c3c4348f709c1b25609207dad754d051994bc6f4835ed38d2cf290  agents/dewey/work/wui/evidence/board-light-1440.png
+8f5d62c30b8e6694e53608ba69c841024926c47d3934a76101a722856fa1e890  agents/dewey/work/wui/evidence/board-light-3440.png
+9e834a3f97bb446155d07f053adceaaeb1907d0397a44f5b31f8c7553d79931c  agents/dewey/work/wui/evidence/board-light-390.png
+093e79080560bed7fdb0577298726613049830d1294f3515bc394dce7e62bcd2  agents/dewey/work/wui/evidence/detail-verification.json
+769e5e695ddec233323b59d226941edc6d98590b8e896588a92bf3366a2cee65  agents/dewey/work/wui/evidence/final-verification.json
+4b213ba93554d1651679d3d3189b6c25f799d2d6e88106ff09e109c0bf44685c  agents/dewey/work/wui/evidence/section-color-ultrawide.png
+093f94495b5f4363a89ebb16228997e5c495f877f2ad4f621de2ec5e19acdaac  agents/dewey/work/wui/evidence/section-components-mobile.png
+693de8c423cea8775810be8755ffe8a803215725bc8e9e1c9cb367bd905a1161  agents/dewey/work/wui/evidence/section-identity-light.png
+ffecc26d0f2e4f4a9c1d907160ca5a5ef9d85c4802c1aa5fd06304a02c7ea60e  agents/dewey/work/wui/evidence/section-review-light.png
+379a5fea56a84bce71cd88995bae3011239f1990d51c5f5a270d7d47238b7ce3  agents/dewey/work/wui/evidence/section-typography-light.png
+73cd0e1795f2e81d1a5e6ae5068c5dea484dd37410ab233f6e30173a21c93cf7  agents/dewey/work/wui/evidence/verification.json
+ff0b6a8fd4e8cf5a0e8d3361243b730d83a86a8563562ffb62338b6635965235  agents/dewey/work/wui/index.html
+4f1309f4b4aec0d595300da060f49f7feb2b3042a8d73468894965ae83b9a04e  agents/dewey/work/wui/styles.css
+485737e40449a2fbc5215fa11357cd2706c3d90265d472a07aa9644d56230fec  agents/filbert/CONTEXT.md
+d3bd85dd59142ca82d8b8a355921389dd1dd9da880c47b7a4760e85e557687e4  agents/filbert/README.md
+8ab8142d0f118e9635d40e2a44d0497f6a6acf62deb50d5435715644b9c71e01  agents/filbert/SOUL.md
+6e5d04034e73d9dcacc6797a19b4e64c2d2e4575a3ebbab6ab3aadf86592681f  agents/filbert/launch.sh
+8a7dc4a3f368b0a695ac7d0f7da3f360dd12c7a231f5e7dbe6b576b80b409979  agents/filbert/validate-sessions.mjs
+ecb5110aa673adefc2168815bdeec577ce18d979585487475b4a429cde0777ba  agents/rocko/CONTEXT.md
+5a97fdb057a331dfe8d4bc7dbc6ab6b93855fc1e194b1c5f0efef784a0a62c4f  agents/rocko/README.md
+d5917650ad98ce6a9e51091d0758121db26877304491c8c00086675f28ffd26b  agents/rocko/SOUL.md
+550ec63aeac4b4b049bd527c157d922626b38373df37debefda54bed8ec26014  agents/rocko/launch.sh
+bc10acb51bfa92edf6be8ee4cd356690c1614d459288116d4b8e63808a9bc44e  docs/SESSIONS.md
+48c3b026513dc2e4bdcc88f7aac87de5bb6d0fbb8bf45d8b7de60d38a2ed2ffd  docs/TOOLS.md
+a8266a2dde67d71b5e957df78d43a98d0d9308315f5aff8ea3c63f9cdd22fccb  docs/plans/2026-09-08_publication-recovery-trial.md
+0633fd1932ea79c7135acdd20ad00e50ad62b10e9f855f0b38767b6439e53fb3  docs/plans/CURRENT.md
+929c48a9d3900dca2fd83827d7edf021d0c545f821662dd4a66afaa1772d589a  docs/plans/reviews/2026-09-08_publication-trial-inventory-disposition.md
+5a593f966d756a8797bca631f1573959cf51f7858f54fd25e053d8c2f4e28ffa  docs/plans/reviews/2026-09-08_publication-trial-launcher-approval-receipt.md
+6df113b111e94cd051820c3796221ab3c04abf7fa68e09695cd79c33070bba44  docs/plans/reviews/2026-09-08_publication-trial-launcher-verdict.md
+8900faf13b3a95918b9542e4b96a57f3561101be7004d74db7b0bb6a7e0a7a5c  docs/plans/reviews/2026-09-08_publication-trial-launcher.sha256
+0e17757cfd3af3bfd3003957550d78c37d32c2b11c75c2b10c76fb9bb5a28a07  docs/plans/reviews/2026-09-08_publication-trial-recovery-summary.md
+397be934731eb9c2f71f222680a3573dff69d6e37588fc1e8906879a443a7dfc  docs/plans/reviews/2026-09-08_publication-trial-recovery-verdict.md
+f018dd59b184b0d44ae02b83d106ce5b5538b89ceb6297cf7aff2c7093a45453  docs/plans/reviews/2026-09-08_publication-trial-sonnet-r2-verdict.md
+5bfeb73f254e9a2f7aef8e18a50f0c96b09c3446f21a3f121367c40634521b11  docs/plans/reviews/2026-09-08_publication-trial-sonnet-verdict.md
+c5649f66c66b60bfcf9c05999d2bfbdf7b93dafee9f6e7ffb8947386b795eb0f  docs/plans/reviews/2026-09-08_publication-trial-wui-condition-disposition.md
+793b556896483ca58dd875a7914731e36c5d5aa83f4e061ddfeb4d4cbe68c535  docs/plans/reviews/2026-09-08_publication-trial-wui-verdict.md
+a585c1eedb17044962c0419861a1032b23409b769c5d304aceff6ef6089a0e11  docs/plans/reviews/2026-09-08_publication-trial-wui.sha256
+07f4048729c36c57b6546d3776c81ff85dd89af93666a15b7c41805a336d5d1a  scripts/agent-host-dev.sh
+ddfb43d2599a722452376eee52cbc66da250722f0de55be1570eb55c4d920145  scripts/agent.sh
+052ad48498102fac2a89047498500b0a3234a87844415b22a1ea70866df63c87  scripts/test-darkwing-launch.mjs
+7c2395250ca77a841e22099d1bed5800dab594e63c3f29d3cb96f38a1c570788  scripts/test-rocko-launch.mjs

docs/plans/reviews/2026-09-08_publication-trial-inventory-disposition.md

@@ -0,0 +1,10 @@
+# PUB-REC-ROCKO-1 inventory findings — coordinator disposition
+
+1. TOOLS.md host-dev usage now includes provider/model/thinking flags. Source behavior unchanged; correction needs inclusion in final exact candidate review.
+2. Added skills/ms-executive-update/README.md publication/compatibility note. Preserve operator-supplied SKILL.md bytes and Codex attribution without claiming a fresh comparison to an unavailable original. Missing fleet paths are not native authority; actual goal_report schema/injected context prevail. No skill activation or historical fixture edits.
+3. Pi launcher tests now copy only launch.sh, SOUL.md, CONTEXT.md and validate-sessions.mjs instead of recursive agent work/scratch. Assertions verify those subtrees are absent. Fresh coordinator run `node --test scripts/test-darkwing-launch.mjs`: four passed, zero failed, exit 0; log /tmp/pub-rec-pi-launch-tests.log. This is a separate coordinator test, not a repeat of Rocko's reserved post-restart command.
+4. Claude prompt argv-size limit remains a documented observation, not an observed defect at current size. No runtime redesign in this publication trial.
+5. Coordinator owns shared session registration for the bounded three-artifact worker task; append-only entries written. No new owner decision required.
+6. Source review reported no correctness defect; it is not independent final candidate approval. Codex remains recorded author of pending launchers; Jason's newer explicit publication ruling permits reviewed integration without pretending Rocko or Filbert authored them. C1 untouched.
+
+Raw Rocko inventory/checkpoint contain runtime identifiers and are withheld from publication. Use curated, privacy-reviewed derivatives. They are not silently edited or republished. Both the original reserved Rocko test and launcher remain pinned unchanged after coordinator corrections.

docs/plans/reviews/2026-09-08_publication-trial-launcher-approval-receipt.md

@@ -0,0 +1,9 @@
+# Launcher publication review accepted
+
+PUB-REC-FILBERT-LAUNCHER-1 independently APPROVED the exact 23 candidates at manifest 8900faf13b3a95918b9542e4b96a57f3561101be7004d74db7b0bb6a7e0a7a5c. Coordinator read the full verdict and recomputed all 57 frozen file hashes plus all 23 live candidate hashes. No drift.
+
+Filbert independently reports isolated fixture reruns, four Pi tests and one Rocko test passed. These are reviewer fixture executions, not repeats attributed to Rocko's historical recovery invocation. Cosmetic duplicate assignment remains unchanged to preserve approved bytes; argv-size observation remains documented.
+
+Acknowledgement sent to Filbert on default socket, reaction class. Transport exit 0: transport dispatched; application acceptance unknown. No reply requested.
+
+Next gate is final selective publication inventory, including privacy-safe review records and exclusions, followed by authorized integration and remote verification. Review does not grant push authority; the existing owner publication mandate governs that act. No deployment, live restart, automated recovery controller or overall trial acceptance inferred. Jason's question about automating testing remains a scope clarification, not new implementation authority.

docs/plans/reviews/2026-09-08_publication-trial-launcher-verdict.md

@@ -0,0 +1,35 @@
+# PUB-REC-FILBERT-LAUNCHER-1 — final launcher candidate verdict
+
+Reviewer: Filbert (independent). Coordinator: Darkwing. Original launcher authorship: Codex (session history); coordinator corrections: test fixture narrowing, TOOLS.md flags, skill compatibility note.
+
+Independence: I authored none of the 23 candidates; the `agents/filbert/` seat files describe my seat but were written by Codex. No conflict.
+
+## Verdict: APPROVED for publication
+
+Exact candidate: the 23 candidatePaths of snapshot `/tmp/pub-rec-launcher-review-a35yzs12`, manifest SHA-256 `8900faf13b3a95918b9542e4b96a57f3561101be7004d74db7b0bb6a7e0a7a5c` (57 files including dependencies). All 57 hashes verified before and after review; snapshot unchanged. Dependencies supplied context only; this verdict does not publish them. The approved WUI draft and recovery summary are separate approvals and are not folded in here.
+
+This grants no deployment, live-launch, or push authority. Jason retains final trial acceptance.
+
+## Independent checks and results
+
+- Syntax: `bash -n` on five shell candidates and `node --check` on both test files and all three `validate-sessions.mjs` copies: pass. The three validator copies differ only in the agent name in the error string, as claimed.
+- Fixture reruns, in my disposable copy (separate from Rocko's recorded historical recovery action and from the coordinator's run): `node --test scripts/test-darkwing-launch.mjs` — 4 tests, 4 pass, 0 fail, exit 0; `node --test scripts/test-rocko-launch.mjs` — 1 test, 1 pass, 0 fail, exit 0. Logs: `/tmp/filbert-launcher-vkdzSG/`.
+- Pinned continuity: rocko test `13c32cad…`, rocko launcher `b65566e1…`, and `skills/ms-executive-update/SKILL.md` `368a8576…` are byte-identical to the values pinned in the recovery review and inventory. Coordinator corrections did not touch them.
+- Isolation of both fixtures confirmed by full source read: temp roots, fake capture-only `pi`/`claude`, stubbed `common.sh`/`sync-dev-extensions.sh`/`docker`, fixture contracts; the Pi fixture now copies only `launch.sh`, `SOUL.md`, `CONTEXT.md`, `validate-sessions.mjs` per agent and asserts `work/` and `scratch/` absent (the coordinator's narrowing, verified in source and by rerun).
+- Branch separation: `--host-dev` is a leading explicit mode only; container refusals never fall back to host. Container path keeps config gating, fail-closed auth resolution (data-root-managed, non-symlink, 0600), role ceilings, skill enablement, workspace naming.
+- Refusals: host mode rejects container flags (`--auth`/`--mission`/`--tools` land on the unknown-argument refusal; TOOLS.md documents this), invalid names, flag-like values, invalid thinking levels, non-TTY, second concurrent TUI (flock), damaged or foreign-workspace session history, and empty/missing context files. All exercised by the fixtures I reran.
+- Config/auth isolation: host mode uses native Pi authentication and copies no credentials; `--check` creates no `.pi/state` (asserted by the fixture).
+- Session semantics: first launch starts a conversation; resume validates JSONL structure and workspace match before `--continue`; `--fresh` preserves earlier history; every launch writes a hashed private context snapshot.
+- Documentation consistency: TOOLS.md host-dev usage now includes `--provider/--model/--thinking` matching `agent-host-dev.sh`; `agents/README.md` wrapper/override description matches the actual wrappers (Filbert's appends provider/model/thinking); per-seat READMEs match launcher behavior.
+- Skill note: `skills/ms-executive-update/README.md` accurately preserves Codex/operator provenance without claiming a fresh byte comparison, flags the dangling fleet-layout references, defers to the actual goal_report schema, and states the skill is not loaded by the host-dev launcher (confirmed: it is not in the ten-skill list). Publication does not activate it.
+- Publication safety scan of all 23 candidates: no session UUIDs, hosted conversation links, home paths, token/credential shapes, or socket names. `.pi/state` mentions are generic path documentation. The canonical checkout path is already-public posture per the inventory.
+
+## Findings (non-blocking)
+
+1. Cosmetic: `scripts/agent.sh` initializes `AGENT_DEF_SKILLS=""` twice in immediate succession (lines 98–99). Dead assignment, re-initialized before use; no behavioral effect. Fix at leisure in a future reviewed change, not a publication blocker.
+2. Argv observation assessed, not redesigned: `agents/rocko/launch.sh` passes the context snapshot as a single argv value. Current inputs are a few KB against a megabyte-scale argv limit; it stays a documented scalability observation (inventory issue 4) with no unobserved redesign.
+3. Context note: the compatibility-symlink home path appears only in a dependency README (`agents/darkwing/README.md`), not in any candidate; existing published posture already includes such paths.
+
+## Publication boundary
+
+Publish exactly the 23 candidatePaths at the verified manifest. Dependencies (34 paths) supplied review context only. Raw worker records with runtime identifiers remain local per the recovery verdict. Any candidate change requires a new review.

docs/plans/reviews/2026-09-08_publication-trial-launcher.sha256

@@ -0,0 +1,57 @@
+db5bde2f586dc420e16497bb6b441ee7ec366b049a6416fe30c415f81b8d4c13  AGENTS.md
+f1ae5988b04cf1680d2eeefad23c119520ec365491c563237f7488242e10b925  agents/README.md
+31d5783fc47dac85cd0e7549100d0d7a8f8af239ed75852741f1aca9fb2411a9  agents/darkwing/CONTEXT.md
+7b37d7a239ecd44fe6258b6cf966d682901ee35a2f00bdf10b19e6d4fedccec4  agents/darkwing/README.md
+87e6ee7459f705cfb0c354cccade74280feb05408187c52cbf92b9011c370783  agents/darkwing/SOUL.md
+67a4e63d3ca78f80e39d9076443dd24d2a3443ff6075b850d43fb62ccd806c9a  agents/darkwing/launch.sh
+a4172eeb05110e225c716e708a9f1ed72b1d361dc12ac1d7fb4665c00fd4a21f  agents/darkwing/validate-sessions.mjs
+c583a3349025f3220b42fd8eee9281ead67f0755715d5e8d05f8584c8e3ddf73  agents/darkwing/work/RESTART.md
+61d640098d8ad79c9c069ea761c8a50c5f644cb914a253fe037132c61a4c421c  agents/dewey/CONTEXT.md
+908a5e6e9eea2be2b190ba87a7dade4fa6228bea21aec0b09746a5176fdeda06  agents/dewey/README.md
+b156fd7c76dfe7c8eb421aeed9d3fd1b681456ca96961d5a010cbe8e1ecf0e33  agents/dewey/SOUL.md
+b6a21d5ae195664612c1dd3f96670934f92025ea100c0e669fa4f7cacd5974f7  agents/dewey/launch.sh
+d0136b89509edff48aa0e2ee398acb7cc7ccd47255225823e47892c57384e60b  agents/dewey/validate-sessions.mjs
+485737e40449a2fbc5215fa11357cd2706c3d90265d472a07aa9644d56230fec  agents/filbert/CONTEXT.md
+d3bd85dd59142ca82d8b8a355921389dd1dd9da880c47b7a4760e85e557687e4  agents/filbert/README.md
+8ab8142d0f118e9635d40e2a44d0497f6a6acf62deb50d5435715644b9c71e01  agents/filbert/SOUL.md
+6e5d04034e73d9dcacc6797a19b4e64c2d2e4575a3ebbab6ab3aadf86592681f  agents/filbert/launch.sh
+8a7dc4a3f368b0a695ac7d0f7da3f360dd12c7a231f5e7dbe6b576b80b409979  agents/filbert/validate-sessions.mjs
+e31c80e007d8b890c698048feb64c0f1fba9cf77f4836e007b9a9b7538b2d851  agents/rocko/CONTEXT.md
+1576c37d8810231c65d3306c75667a632e5662062ee43f67cb43b01302e10ee5  agents/rocko/README.md
+d5917650ad98ce6a9e51091d0758121db26877304491c8c00086675f28ffd26b  agents/rocko/SOUL.md
+b65566e19fa0fb83409552954a645b8cdc4d2bdb1002df55d27088add6acf65d  agents/rocko/launch.sh
+ca48e94ab814149f7a40f44bb8fce14f29215722f7a09d991186b3780fb2032b  contracts/CONSTITUTION.md
+2bdb3abb4cd6c13e2f1ddcd55b07f19ef69d3528738922c7473d16fc74072a7f  contracts/SOUL.md
+9e383354be38d0ea011b1145b6b3a4f35bfae6ebd856dc7921b8bae2959382e0  contracts/STANDARDS.md
+48c3b026513dc2e4bdcc88f7aac87de5bb6d0fbb8bf45d8b7de60d38a2ed2ffd  docs/TOOLS.md
+6aecf9ea47b99267b7795eeecdedc53845e6834f0d7445481374b808e395ceb0  package.json
+07f4048729c36c57b6546d3776c81ff85dd89af93666a15b7c41805a336d5d1a  scripts/agent-host-dev.sh
+ddfb43d2599a722452376eee52cbc66da250722f0de55be1570eb55c4d920145  scripts/agent.sh
+40213f2c3329ad6985d9915c507f96bada97db720454d603505dc57f2b9d4136  scripts/common.sh
+052ad48498102fac2a89047498500b0a3234a87844415b22a1ea70866df63c87  scripts/test-darkwing-launch.mjs
+13c32cad02587aad85da2f1a2bca8e61d77d9285ffc9e21dc91b7bafa7d0e05d  scripts/test-rocko-launch.mjs
+fd8e77a9f32142d35cfbf4408875ce70d6edbb60888e75c935763883ef853cfb  skills/ms-agent-watch/SKILL.md
+f3ce97bdbd642beb5b2e5b74d3529041d475a5bf42b9a1e0936334c2d1edcf43  skills/ms-agent/SKILL.md
+06991caef7806dfc88cd7cdf02c744475f4397230ed8a2e94e89c0178a5b4bc0  skills/ms-archify/SKILL.md
+4c887c0d207901104eb7f8700158345521dc0b8e088c57ce5f0b19152cb088f5  skills/ms-communications/SKILL.md
+d7aae586ede3ae1e867b60ec0a4040e8d0dad8b128cc9fa8d20228eb512381d1  skills/ms-conductor/SKILL.md
+2b683dd50c07aa472451c080a0f2c7087f1ec08690eac86bed17c8f9fb2878f3  skills/ms-executive-update/README.md
+368a857632dfd118a11a752ae0a775ca13d6837cf05d8f870946c9e7364d127f  skills/ms-executive-update/SKILL.md
+28f9b76bb89f8aadfb3b8933255c54e360af741b050a7738cb0a904f7835a95e  skills/ms-file-read/SKILL.md
+ad9ee2d00b87b2c6fa36b7863c0034b8883f7e1fa2aa5390e67121eda0165e14  skills/ms-file-write/SKILL.md
+885e993a6bd3c4d6ce94b0d95a8c82e212be78c5c727035c81f3dbed39b0ceee  skills/ms-frontend-design/SKILL.md
+b754f2f428bf0107aea4d5dffb0d148d83fa9d71dfc22cee5b31007ede26f884  skills/ms-frontend-design/references/accessibility.md
+9232279ec748ec7076566b57d6e8da6f35d06cb9de58d9080cdea66172b2a41c  skills/ms-frontend-design/references/design-principles.md
+a77c2ecc434a77786985f2a1aa01e5c17c43f566688aeda3909506bd9641690a  skills/ms-frontend-design/references/site-completeness.md
+94782abd9d0834d1b37b2609782405777c65d42fc60f3651e01f46a9c88cfd5c  skills/ms-frontend-design/references/verification.md
+558739ad5d5a22fa35f31049829b5c92971f693d10f91450da2bc381d6c0adaf  skills/ms-frontend-design/references/visual-system.md
+eb9e56cae2647b6553736a87af2f4ed89adb02e0a3220637ff84dce19bea8b3f  skills/ms-goal/SKILL.md
+ea9196042355b08f9e43eaa67d62c82419ad9768666a9f56b815184a3f48997d  skills/ms-goal/references/execution-checks.md
+bfce50bee7c92b15e3edd9399d1646bed8ea77b1a768747dfd185faa0387b114  skills/ms-grill-me/SKILL.md
+9f7bc752825842808b8d206f0386aac89113066474d803de02550f9bb83b09c2  skills/ms-grill-me/upstream-grill-me.md
+6fc326fa6acfb254877812a833fb3b49c6d7b9c5b8246d18f178ef411b60a7e7  skills/ms-grill-me/upstream-grilling.md
+0132ad6508df2bcba0df7fb417e06cbe90c7ea663e334f2176c8973757bb4809  skills/ms-proactive-agent/SKILL.md
+f81aa1adf33f9d46f9783df3eeec9f705c5b65c37d48d7708cdb923eac0c5478  skills/ms-sdlc/SKILL.md
+3b78c1f75d23fd7a17f590c02f570a356fd7cbc5b031eca849bd04a873efe6f7  skills/ms-tools/SKILL.md
+0eace7c537ae711876cc82137aa5e4f84f1a2145676de8cfb2fe963f32efb530  skills/ms-unslop/SKILL.md
+2eae928c488ea9ae752b19cb72fa532ea50f5306653684320d396ab2b0473e8a  skills/ms-user/SKILL.md

docs/plans/reviews/2026-09-08_publication-trial-recovery-summary.md

@@ -0,0 +1,28 @@
+# Planned-restart trial — privacy-safe recovery summary
+
+Task PUB-REC-ROCKO-1, trial #1497. Author of worker evidence: Rocko. Coordinator: Darkwing. Status: worker action complete; independent recovery review and Jason's overall trial acceptance pending.
+
+## Evidence chain
+
+1. Before restart, Rocko declared an unexecuted next action: `node --test scripts/test-rocko-launch.mjs`, inspected as an isolated fixture with fake Claude and temporary state, no real model call. Coordinator independently read the test without running the reserved action.
+2. Coordinator verified checkpoint and inventory hashes, unchanged test/launcher bytes, baseline HEAD and absent recovery artifact before telling Jason the planned restart was ready.
+3. Jason reported `done`, then `continue issued`. Coordinator supplied no reconstructed task prompt after restart and did not read private sessions/panes.
+4. Rocko reports retained task context, re-reading declared shared records, no private-state reads after restart and one reserved test invocation. Launcher resume stdout was unavailable inside his process; exact resume mode is inferred from retained context, not independently observed from that output. Harness compaction occurred and was not treated as the sole task record.
+5. Worker output reports one test, one pass, zero failures, exit 0, empty stderr. No tracked files changed; two additional untracked task records appeared, including the worker recovery file and an unrelated coordinator review disposition. This is not a literally unchanged worktree claim.
+6. The coordinator verified test and launcher hashes still match the pre-restart inventory. The announced recovery hash matches exactly the byte prefix before its appended transport receipt; the full post-send record has a different, recorded identity.
+
+## Exact identities
+
+- Baseline HEAD: 3b7fd19d087226b1887bf017fc10ef16b044f6aa.
+- Checkpoint SHA-256: 30c4e1906b22220a29868c1ef4253676d2e2324d46a1f281543e50347af7fdd8.
+- Inventory SHA-256: 51536b1d4a8fee30caa711527295ed7b860d46ae9b81e5530af6631a53030b5f.
+- Recovery announced pre-send SHA-256: 52778f1a681277335f5d86a1e1fe2b96e9df07303b81c1d833ed674cf44811f7.
+- Recovery full post-send SHA-256: df77133d49d66be72f12f6d742d1f220529a82098efac79117c13d256048abca.
+- Test SHA-256: 13c32cad02587aad85da2f1a2bca8e61d77d9285ffc9e21dc91b7bafa7d0e05d.
+- Launcher SHA-256: b65566e19fa0fb83409552954a645b8cdc4d2bdb1002df55d27088add6acf65d.
+
+Raw worker records remain local pending privacy handling; they contain runtime identifiers and are not publication candidates. This derivative deliberately omits those identifiers and hosted conversation links. Hashes identify evidence without publishing private session state.
+
+## Limits
+
+A planned operator restart with neutral continuation and checkpoint recovery is supported by the owner report and worker execution evidence. No crash-recovery guarantee, authenticated process-incarnation proof, production orchestration, repeated reliability rate or unobserved exactly-once guarantee is claimed. One execution is the worker's recorded run count, not a separate runtime-enforced invariant. Independent review must evaluate the evidence and these limits before publication. C1 remains held. Candidate review, publication and overall user acceptance are separate gates.

docs/plans/reviews/2026-09-08_publication-trial-recovery-verdict.md

@@ -0,0 +1,47 @@
+# PUB-REC-FILBERT-RECOVERY-1 — independent recovery-evidence verdict
+
+Reviewer: Filbert (independent). Worker evidence: Rocko. Coordinator and curated derivative: Darkwing. Trial #1497.
+
+Independence: no authorship or review role in the checkpoint, inventory, restart, or summary; no conflict. This verdict is not the final launcher code review and not Jason's trial acceptance.
+
+## Verdicts
+
+1. Bounded planned-checkpoint recovery criterion (a useful development assignment survives one planned participating-agent restart without the owner reconstructing its briefing): **SUPPORTED**, with the inference and observation limits recorded below.
+2. Publishing the curated privacy-safe summary `docs/plans/reviews/2026-09-08_publication-trial-recovery-summary.md`: **APPROVED** as reviewed, under the conditions in the last section.
+
+## Admission and integrity
+
+Snapshot `/tmp/pub-rec-recovery-review-4em3lt1p`: SHA256SUMS hashes to the declared `b52a621551c9e6390a2ed3bb4d80431acd81e897b90660e60798d33767b0b5b1`; all ten files verify; path set exact; snapshot read-only and left unchanged. Review was reading and hashing only: no launcher/test execution (the reserved action was not rerun as a substitute for historical evidence), no private runtime/pane/transcript reads, no hosted session links followed.
+
+## Independently verified facts
+
+- Hash continuity, recomputed by me inside the snapshot: trial plan `ab908308…`, task `af673b60…`, checkpoint `30c4e190…`, inventory `51536b1d…`, recovery full record `df77133d…`, reserved test `13c32cad…`, launcher `b65566e1…`. All match every place they are quoted (checkpoint sections 1/3, readiness admission, recovery sections 1/3, summary identities).
+- The announced pre-send recovery hash `52778f1a…` reproduces exactly as the byte prefix ending immediately before the appended delivery paragraph in section 6. The summary's prefix-claim is literally true, not rhetorical.
+- The reserved action was declared before the restart and unexecuted at restart time: the checkpoint reserves `node --test scripts/test-rocko-launch.mjs`, and the operator restart receipt independently records the recovery artifact absent and no execution inferred; the coordinator readiness record confirms the test was read but not run before restart.
+- The reserved test is genuinely isolated: I read `scripts/test-rocko-launch.mjs` in full. It builds a `mkdtemp` root, copies only `agents/rocko`, writes fixture contracts/AGENTS/USER and a stub `common.sh`, fronts PATH with a fake capture-only `claude`, drives the launcher under `script(1)`, and removes the temp root in `finally`. It never reads real config, the data root, the checkout's `.pi/state`, or a model. One test function, matching the recorded `# tests 1`.
+- The recovery record's verbatim output (1 pass, 0 fail, exit 0, empty stderr, `ℹ` reporter prefix) is internally consistent with Node 26's reporter and the checkpoint's declared expectation; the record correctly classifies the `ℹ`-versus-`#` difference as formatting, not a count deviation.
+- The curated summary contains no runtime identifiers: no session UUID, hosted link, socket name, or launch-receipt name (scanned). Its hashes-without-contents approach is the right privacy shape.
+
+## Reported facts, correctly not overstated
+
+- The restart and neutral `continue` are owner-reported (`done` per the operator receipt); the coordinator supplied no reconstructed briefing and did not read private state. I did not observe the process.
+- Resume mode is inferred from retained context (same hosted link and prior conversation); launcher stdout is unobservable from inside the resumed process, and post-restart private-state reads were correctly not performed to confirm it. Normal-resume failure: none reported; no assisted recovery used.
+- One execution is the worker's recorded run count, not a runtime-enforced invariant; exactly-once is unobserved. Worktree preservation (HEAD unchanged, index empty, only two new untracked task records, no tracked change) is worker-reported with coordinator-side hash agreement; the summary already refuses to call it a literally unchanged worktree claim.
+- Single planned trial: no crash-recovery, reliability-rate, incarnation-authentication, or orchestration guarantee is claimed, and none may be inferred.
+
+## Procedural deviations and their handling (preserved, not erased)
+
+- Appended hash receipts: both the checkpoint and the recovery record append delivery paragraphs after announcing pre-send hashes; both record pre- and post-send identities explicitly, and the checkpoint carries an appended timestamp correction (send ~18:45 UTC, not 18:53) rather than a rewrite. Handled honestly.
+- Stale A9 statement: the checkpoint's conflict-check paragraph says the inspector package "awaits owner acceptance"; the coordinator ruled that stale (A9 already accepted) rather than an open gate. The stale sentence remains in the raw record with the correction beside it; the derivative does not propagate it.
+- Own-session metadata reads: before restart the worker read its own session pointer, launch-receipt directory name, and hosted link, which a literal "no private state" reading would exclude. The inventory discloses it, the coordinator ruling preserves the honest qualification, and the summary scopes its no-private-read claim to after restart, which is accurate.
+- Registration delegation: the worker followed its three-artifact write boundary and did not append to SESSIONS/BUILD-LOG; the coordinator took registration ownership by ruling. A deviation from the root AGENTS.md default, resolved explicitly rather than silently.
+
+The curated summary accurately reflects the raw evidence on every point I could check, and its limits paragraph matches my own findings. Omissions (checkpoint pre-send hash evolution, A9 note, registration detail) are simplifications that do not misstate anything and remain available in the preserved local raw records.
+
+## Conditions
+
+1. Publish the curated summary byte-as-reviewed, SHA-256 `0e17757cfd3af3bfd3003957550d78c37d32c2b11c75c2b10c76fb9bb5a28a07`; any edit requires re-review. The raw recovery record (`df77133d…`) is evidence, not a publication unit.
+2. Raw checkpoint/inventory/recovery records stay local pending privacy handling; they contain runtime identifiers and are not publication candidates.
+3. Present the outcome as one bounded planned-checkpoint recovery, not trial acceptance, not crash recovery, and not a reliability claim; the final launcher candidate review and Jason's overall trial acceptance remain separate gates.
+
+Evidence: frozen snapshot above; all checks offline and read-only. No git operations, source edits, live-seat mutation, or operator actions performed.

docs/plans/reviews/2026-09-08_publication-trial-sonnet-r2-verdict.md

@@ -0,0 +1,26 @@
+# PUB-REC-FILBERT-SONNET-2 — focused frozen-delta verdict (round 2)
+
+Reviewer: Filbert (independent). Coordinator: Darkwing. Supersedes the round-1 REQUEST CHANGES at `2026-09-08_publication-trial-sonnet-verdict.md`, which remains on record unchanged.
+
+## Verdict: APPROVED
+
+The SONNET-F1/F2 repairs are exactly the three one-line wording replacements requested, and nothing else changed. Model wording is now consistent across every candidate that mentions Rocko's runtime.
+
+## What was verified
+
+- Snapshot `/tmp/pub-rec-sonnet-r2-htbgwodg`: manifest SHA-256 `c5ad630615f67c4480c23f3478123c7c1c5e7c6095bcfa45039650c8213c38bf`, all seven files verify. Structure matches the declaration: four files byte-identical to round 1 (`launch.sh`, rocko `README.md`, rocko `SOUL.md`, test), `CONTEXT.md` further repaired, and the two team files newly included.
+- Repairs confirmed as minimal single-line deltas:
+  - `agents/rocko/CONTEXT.md`: "using the Fable model" → "using the Sonnet model" (the launch-injected line; SONNET-F1 closed).
+  - `agents/README.md`: team table cell "Claude Code, Fable model" → "Claude Code, Sonnet model" (SONNET-F2a closed).
+  - `agents/darkwing/SOUL.md`: "Rocko (Claude Code with Fable)" → "Rocko (Claude Code with Sonnet)" (SONNET-F2b closed).
+- No `fable` reference remains in any of the seven files; `sonnet` wording is consistent with the launcher's `--model sonnet` and the test expectation.
+- Exactly six candidate files differ from the original approved launcher snapshot; `agents/rocko/SOUL.md` is unchanged fixture context.
+- Combined fixture rerun in a disposable harness (seven R2 files over the approved snapshot's dependency set, isolation previously source-verified): `node --test scripts/test-rocko-launch.mjs scripts/test-darkwing-launch.mjs` — 5 tests, 5 pass, 0 fail, exit 0. This reproduces the coordinator's 5/5 independently; fake model fixtures only.
+- Historical evidence preserved: the frozen recovery snapshot still pins the fable-era test/launcher bytes, the round-1 rejected verdict is untouched, and no live session was restarted.
+- All three frozen snapshots re-verified unchanged after review. No private state, live launch, configuration change, source edit, or deployment.
+
+## Publication effect
+
+Publish the six changed candidates as these reviewed bytes, replacing their prior approved versions; the remainder of PUB-REC-FILBERT-LAUNCHER-1's approval stands unchanged. Any further candidate change requires new review. Publication review only — no trial acceptance, deployment, or push authority implied.
+
+Evidence: disposable harness and combined test log under `/tmp/filbert-sonnet-r2-*`.

docs/plans/reviews/2026-09-08_publication-trial-sonnet-verdict.md

@@ -0,0 +1,31 @@
+# PUB-REC-FILBERT-SONNET-1 — focused frozen-delta verdict
+
+Reviewer: Filbert (independent). Coordinator: Darkwing. Owner change: Jason switched Rocko's launcher to Sonnet and authorized matching documentation repairs.
+
+## Verdict: REQUEST CHANGES
+
+The three changed files are correct, minimal, and internally matched, and my isolated test rerun passes. The review criterion was model/docs/test consistency, and that criterion is not met across the candidate set: three stale `Fable` references survive, one of them inside this very snapshot.
+
+## What was verified
+
+- Snapshot `/tmp/pub-rec-sonnet-review-u__t4rsb`: manifest SHA-256 `52a1c408aad20b8c71377db2e456a11450b1d72264adaa679a26f9374c48e263`, all five files verified before and after review.
+- Delta versus the approved launcher snapshot `/tmp/pub-rec-launcher-review-a35yzs12` is confined to exactly three files, each changed only in model wording:
+  - `agents/rocko/launch.sh`: banner echo and `exec claude --model sonnet`.
+  - `scripts/test-rocko-launch.mjs`: test title and expected-model assertion.
+  - `agents/rocko/README.md`: three wording lines.
+- `agents/rocko/SOUL.md` and `agents/rocko/CONTEXT.md` are byte-identical to the approved snapshot (no unrelated changes).
+- `bash -n` and `node --check` pass. Isolated fixture rerun in a disposable copy (isolation re-confirmed by source read; fake capture-only claude, temp root): `Rocko uses Sonnet…` 1 test, 1 pass, 0 fail, exit 0.
+- Original recovery evidence untouched: the frozen recovery snapshot still pins test `13c32cad…` and launcher `b65566e1…`; the historical record keeps its original bytes and meaning.
+- No live launch, private-state read, configuration edit, or deployment.
+
+## Findings
+
+1. **SONNET-F1 (blocking): `agents/rocko/CONTEXT.md` still says Fable.** Line 4: "Stack repository, using the Fable model." This file is in the reviewed five-file snapshot and is injected into Rocko's system context at every launch, so the seat would be told it runs Fable while the launcher now execs `--model sonnet`. A one-line repair in this same file completes the declared docs fix.
+2. **SONNET-F2 (blocking for the combined publication): stale Fable references in two previously approved launcher candidates.** `agents/README.md` team table says "Claude Code, Fable model"; `agents/darkwing/SOUL.md` says "Rocko (Claude Code with Fable)". Those bytes were approved when they matched the fable launcher; publishing them unchanged alongside the sonnet launcher creates factual contradictions in the published team documentation. Each is a small wording repair, but they are revised bytes outside this delta and need their own review coverage (a focused addendum like this one is sufficient).
+3. Non-blocking note: the coordinator's 1/0 test result was independently reproduced rather than trusted.
+
+## Required to convert this to approval
+
+A refreshed delta containing: the same three files as reviewed here plus the `CONTEXT.md` line fix, plus the `agents/README.md` and `agents/darkwing/SOUL.md` wording repairs (or an explicit owner decision to describe Rocko's model generically in team docs). I will re-verify hashes and rerun the isolated test; no other re-review is needed if the delta stays this narrow.
+
+Evidence: disposable-copy test log and diffs under `/tmp/filbert-sonnet-*`; frozen snapshots unchanged after review. This is publication review only; no trial acceptance, deployment, or push authority implied.

docs/plans/reviews/2026-09-08_publication-trial-wui-condition-disposition.md

@@ -0,0 +1,13 @@
+# WUI publication approval conditions — coordinator disposition
+
+Read Filbert's complete PUB-REC-FILBERT-WUI-1 APPROVED verdict for the exact 53-file manifest a585c1ee. Fresh independent browser results are Filbert's measured evidence, not new Darkwing reruns.
+
+WUI-PUB-F1: retain the exact author bytes. BRIEF.md names Jason Woltje as owner; the full name is already public as repository owner. Boundary's first-name-only description was incomplete. This correction does not broaden permission for unrelated personal information.
+
+WUI-PUB-F2: retain the historical design-feedback wording in DECISIONS.md rather than silently paraphrasing the immutable reviewed record. It is ordinary candid feedback on a proposed mark, within the owner-approved curated draft publication scope. Separate publication note explains that working feedback is not product messaging or acceptance. No change to the 53-file pin.
+
+Added coordinator publication label: agents/dewey/work/wui/PUBLICATION.md. It is an explicit additional documentation artifact, not a falsely claimed member of the reviewed 53 files. Names pending owner acceptance, old provisional defaults versus later feedback, font-license limits and excluded historical evidence.
+
+Visual-check correction: the review's statement that prior coordinator visual inspections supported its structural checks was premature. Darkwing had not inspected the PNGs before that verdict. After receipt, Darkwing used image reads to inspect all ten allowlisted screenshots: board-dark-1440, board-dim-1440, board-light-1440, board-light-3440, board-light-390, section-color-ultrawide, section-components-mobile, section-identity-light, section-review-light, section-typography-light. Observed prototype controls, branding proposals and synthetic specimen content; no private application data or browser chrome observed. Ultrawide images were displayed downscaled; this is bounded visible-content inspection, not exhaustive forensic image analysis. Reviewer visual-pixel NOT RUN remains true for Filbert's own review.
+
+Owner reports restart complete and neutral `continue` issued. No assignment facts or checkpoint paths were supplied in that continuation. Rocko recovery result remains pending separately; WUI approval does not establish restart success or overall trial acceptance.

docs/plans/reviews/2026-09-08_publication-trial-wui-verdict.md

@@ -0,0 +1,61 @@
+# PUB-REC-FILBERT-WUI-1 — independent draft-publication verdict
+
+Reviewer: Filbert (independent). Author: Dewey. Coordinator: Darkwing. Trial: #1497.
+
+Verdict: APPROVED for draft publication at manifest SHA-256 `a585c1eedb17044962c0419861a1032b23409b769c5d304aceff6ef6089a0e11`, 53 files, snapshot `/tmp/pub-rec-wui-review-cgfkxmll`.
+
+Independence: no prior authorship or review role in the WUI; no conflict to report. Publication approval only. This approves no branding, product acceptance, license choice, commit, push, or deployment.
+
+## Admission and integrity
+
+- All 53 snapshot hashes verified against SHA256SUMS; the manifest file itself hashes to the declared `a585c1ee...` and matches the durable copy at `docs/plans/reviews/2026-09-08_publication-trial-wui.sha256`.
+- Snapshot path set is exactly the manifest set; no extra files. Snapshot is read-only and re-verified unchanged after review (0 mismatches). All browser checks ran on a disposable copy; no snapshot or author file was mutated.
+
+## Standalone draft usability
+
+- Every runtime dependency resolves inside the manifest: index.html uses styles.css, brand.js, board.js, assets/logos/assembly.svg and RESEARCH.md; styles.css loads the 12 bundled woff2 files. No external URL, CDN, fetch, or network call exists in any HTML/CSS/JS/SVG/palette file.
+- README/VERIFY references to excluded evidence outputs are historical documentation references; the draft needs none of them to function. Nothing excluded was added.
+- Fresh rerun of the final checks confirms the entry page loads only local `file:` resources.
+
+## Publication safety
+
+- Notes contain no credentials, tokens, authentication material, home paths, family/personal data, or private correspondence beyond curated owner feedback (a declared category). The incidental transport identifier and repo-local paths are declared categories.
+- Screenshots: valid PNGs, no metadata or text chunks, no suspicious embedded strings, dimensions match the claimed viewports.
+- Two coordinator-judgment notes, neither blocking:
+  - WUI-PUB-F1: BRIEF.md carries the operator's full name "Jason Woltje"; the boundary declared only the first name. The name is already public as repository owner. Keep or addendum is the coordinator's call.
+  - WUI-PUB-F2: DECISIONS.md quotes the owner's candid logo feedback verbatim. It is declared design feedback and factual, but publication wording is an owner-taste decision; paraphrase via label/addendum is acceptable if preferred.
+- Bounded NOT RUN: independent visual inspection of screenshot pixel content (this reviewer session cannot render images). Structural checks above plus the author's and coordinator's recorded visual inspections stand in; residual risk is low but not zero.
+
+## Font provenance
+
+- Three families, each with its own distinct OFL 1.1 notice carrying the correct copyright line; IBM's declares Reserved Font Name "Plex".
+- Each `*-sources.txt` records the exact Google Fonts CSS/woff2 URLs and upstream license location. Within each family the four weight files are byte-identical variable-font downloads, consistent with the recorded identical URLs and the boundary's statement.
+- CSS uses the original family names; fonts are unmodified downloads kept with their notices, not relabeled under a code license. No license text was copied from v1; no trademark clearance is claimed anywhere.
+
+## Claims versus evidence
+
+Fresh independent reruns on the disposable copy (same Node 26.8.1, installed headless Chromium via CDP, fresh temporary profile) reproduce the author's receipts exactly:
+
+- verify.mjs: 30 contrast sets / 840 pair checks, minimum normal-text ratio 4.503925718129755, 240 layouts, all interaction checks pass, no page errors.
+- detail-checks.mjs: 8,220 rendered-text samples across 30 combinations, minimum 4.504658476260286, zero failures; keyboard focus, accessible names, downloads, doubled text, blocked-fonts/denied-storage fallback all pass.
+- final-checks.mjs: local resources only, links/anchors resolve, breakpoints, 24 px targets, malformed-storage recovery all pass.
+- node --check passed on brand.js and board.js.
+- NOT RUN by reviewer (offline review): checks/references.mjs and checks/fetch-fonts.py, which deliberately use the network when run. Neither is invoked by the board.
+
+## Draft-status preservation
+
+- The board and notes consistently present the Assembly/DM Sans/Harbor recommendation as provisional ("My starting recommendation", "No logo is approved yet", "not cleared trademarks", "Not a working product", "The five dashboard designs have not been built").
+- DECISIONS.md preserves the chronology: intake answers, unapproved proposals, first owner feedback (Manrope/themes liked; logo association objection), and the gate revision. No first-feedback source change was implemented, matching the boundary.
+- Publication must carry the pending-owner-acceptance label (the author's suggested wording in the boundary declaration) at the publishing location. That label is the coordinator's to apply; no author source was edited for this review.
+
+## Conditions of this approval
+
+1. Publish only the exact 53-file candidate at the verified manifest; any change requires a new boundary and re-review.
+2. Apply the pending-owner-acceptance label; do not present the board's provisional recommendation as selected branding.
+3. Coordinator decides WUI-PUB-F1/F2 handling (keep as-is or addendum) before publication.
+
+Evidence: `/tmp/filbert-wui-O0znVK/` (rerun logs verify-rerun.log, detail-rerun.log, final-rerun.log; regenerated reports in copy/evidence/). No git operations, live-seat mutation, source changes, or operator restart were performed.
+
+## Correction, appended 2026-09-08 after coordinator disposition
+
+The publication-safety section above says the author's and the coordinator's visual inspections stand behind the structural PNG checks. That was premature for the coordinator half: at verdict time only the author's inspection existed. The coordinator inspected all ten PNGs after receiving this verdict and recorded bounded visible-content findings (prototype and synthetic content only, ultrawide images viewed downscaled) in `docs/plans/reviews/2026-09-08_publication-trial-wui-condition-disposition.md`. This reviewer's visual NOT RUN limit stands unchanged. The approval's structural evidence and fresh reruns are unaffected.

docs/plans/reviews/2026-09-08_publication-trial-wui.sha256

@@ -0,0 +1,53 @@
+c71e0c80c5976fbe5048624a7656ed9812164e3969f6ba76c43239e17746d20a  agents/dewey/work/wui/BRIEF.md
+3c86ba0fd6aa894489caf83f6bff8fd94138c3ddd5f5b33858ef21426f8fce65  agents/dewey/work/wui/DECISIONS.md
+a7ad1f585702886de2d338f530ca5d29130c4acf8682c5d391f1b9e53bf86fe8  agents/dewey/work/wui/HISTORY.md
+e9cac40fe832d36429f02c4b0fa3e50cf63ccf3457b08e0326b8fc1b6c227b49  agents/dewey/work/wui/README.md
+fcc6d1ec1a35713f1bf765cbe83c9e526a4907d0cd2ce8889a2ef9ed6c54b25d  agents/dewey/work/wui/RESEARCH.md
+04f2624b507109943d5e3ff5732c66d13816313e54a867ac1852341fb90cd309  agents/dewey/work/wui/TASKS.md
+63e96d72b6afd4eb8058c8b5b6846dbaa1c808dec1054ab23bfb3f5871f78801  agents/dewey/work/wui/VERIFY.md
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-400.woff2
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-500.woff2
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-600.woff2
+9fea608a947e67020c33cad9a6fe3d60c54119dfb8cff87768a8117a15ed7543  agents/dewey/work/wui/assets/fonts/dm-sans-700.woff2
+9af36190332437f5ecd09974de43c1f7c77a310a996cdd8ceb25628b458840e1  agents/dewey/work/wui/assets/fonts/dm-sans-OFL.txt
+89947da00bec2cbcacab815b7e36bf07a635dec41e3ca87a6eb2484a605a4e71  agents/dewey/work/wui/assets/fonts/dm-sans-sources.txt
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-400.woff2
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-500.woff2
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-600.woff2
+e2291e842cf5af167122a22881a740c7f2dda7716f1e8cd76680264f4a859470  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-700.woff2
+7e6b2818edbd8f6a01ae80641cc8f16a51080d08fb4e532be3a0b6f74adb07da  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-OFL.txt
+a762adc472b0911c4f5d0e3f0dd672c557c4b3debbc9b617488b46c36e10b183  agents/dewey/work/wui/assets/fonts/ibm-plex-sans-sources.txt
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-400.woff2
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-500.woff2
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-600.woff2
+a30ddcd349703aff7464c34bef3fffdff405ee50c113440d7c8693c02d210972  agents/dewey/work/wui/assets/fonts/manrope-700.woff2
+e01b637272e0cbdfb240184dd98ea5cc671556d9894dae2668d92ab2c906787c  agents/dewey/work/wui/assets/fonts/manrope-OFL.txt
+0d9aaaaa963b675d94d8fbee0cf47a8ecf03ea412f8b14aba96416375e5a2bb5  agents/dewey/work/wui/assets/fonts/manrope-sources.txt
+a1a047eb0b7f9c8f3e656d97d2292545371f8f0a92b4eb273cfd2fc371bd50ad  agents/dewey/work/wui/assets/logos/aperture.svg
+d3d0eb03872b7336b00186beb95567840e5caf2bef29c2a9599480b29eb2f8da  agents/dewey/work/wui/assets/logos/assembly.svg
+446cb7c0b75bb5cc7e3e08d9feb979c000531adfba0523aec81fb9af77f1ae55  agents/dewey/work/wui/assets/logos/relay.svg
+9efa30b490fa2cde89dcd3c9eafd37ae83a77a84a2a1965c78828e410be2b568  agents/dewey/work/wui/assets/palettes.json
+31222b6c40af7f253cceccc3d3caef5c2b0f9c0e096ea2eb5828b2224c3c47fe  agents/dewey/work/wui/board.js
+d568df6dca14ae336db3b627639c8181c088649a21ffe992f9bfacc20b5b6238  agents/dewey/work/wui/brand.js
+e884333a3191921050c6ab45c7d87d40c6bc3092ba9d55c3c06bc5f0d01d5da3  agents/dewey/work/wui/checks/assets.mjs
+3ff14de07e87cc624433db6425b9d05e40d98f61e40f2bbf1fbee7431f9d73c1  agents/dewey/work/wui/checks/browser.mjs
+16b3cf3f7c8897dddef3b4caf1e9200272078cea8226a6df5e9ea1e7d25fe598  agents/dewey/work/wui/checks/detail-checks.mjs
+af924e53a19e3a639e5bc4c1e6a27253d03adcd935a8e1a847806761b797336c  agents/dewey/work/wui/checks/fetch-fonts.py
+fd7d5baad1eb01c41ae98e1341aa5b16bb22e02f5296951381f48705b42d6855  agents/dewey/work/wui/checks/final-checks.mjs
+df79defbecf1500b6b5abdf7f0568c22ae88b437e841f0c95a7fa16d5d5fd3d2  agents/dewey/work/wui/checks/references.mjs
+bd6cc0c1021401207519e3489105284d120da2d8b85710e8fd51c1939f10e411  agents/dewey/work/wui/checks/verify.mjs
+41d4aababef4fdd5beff4f0b75fcdcd59e9a2fdf408a6a7aaf9f7afd86d1ac02  agents/dewey/work/wui/evidence/board-dark-1440.png
+9599769f4ed18363c3b7c0061823e0fd772d9cd516d3f72ab02e7b74a01de93c  agents/dewey/work/wui/evidence/board-dim-1440.png
+d8097a2896c3c4348f709c1b25609207dad754d051994bc6f4835ed38d2cf290  agents/dewey/work/wui/evidence/board-light-1440.png
+8f5d62c30b8e6694e53608ba69c841024926c47d3934a76101a722856fa1e890  agents/dewey/work/wui/evidence/board-light-3440.png
+9e834a3f97bb446155d07f053adceaaeb1907d0397a44f5b31f8c7553d79931c  agents/dewey/work/wui/evidence/board-light-390.png
+093e79080560bed7fdb0577298726613049830d1294f3515bc394dce7e62bcd2  agents/dewey/work/wui/evidence/detail-verification.json
+769e5e695ddec233323b59d226941edc6d98590b8e896588a92bf3366a2cee65  agents/dewey/work/wui/evidence/final-verification.json
+4b213ba93554d1651679d3d3189b6c25f799d2d6e88106ff09e109c0bf44685c  agents/dewey/work/wui/evidence/section-color-ultrawide.png
+093f94495b5f4363a89ebb16228997e5c495f877f2ad4f621de2ec5e19acdaac  agents/dewey/work/wui/evidence/section-components-mobile.png
+693de8c423cea8775810be8755ffe8a803215725bc8e9e1c9cb367bd905a1161  agents/dewey/work/wui/evidence/section-identity-light.png
+ffecc26d0f2e4f4a9c1d907160ca5a5ef9d85c4802c1aa5fd06304a02c7ea60e  agents/dewey/work/wui/evidence/section-review-light.png
+379a5fea56a84bce71cd88995bae3011239f1990d51c5f5a270d7d47238b7ce3  agents/dewey/work/wui/evidence/section-typography-light.png
+73cd0e1795f2e81d1a5e6ae5068c5dea484dd37410ab233f6e30173a21c93cf7  agents/dewey/work/wui/evidence/verification.json
+ff0b6a8fd4e8cf5a0e8d3361243b730d83a86a8563562ffb62338b6635965235  agents/dewey/work/wui/index.html
+4f1309f4b4aec0d595300da060f49f7feb2b3042a8d73468894965ae83b9a04e  agents/dewey/work/wui/styles.css