website-build-skill 0.1.4 → 0.1.5

package/docs/bundles/team.md

@@ -29,6 +29,7 @@ Never ask the user for the date or infer it from model knowledge. Apply the
 same source, two-date, freshness, reuse, and blocked-gate rules to this stage.
 
 Run option 2, Give me the team, using the human's recorded install choice.
+TEAM: one command installs the seven workers' files; you open each session yourself and carry the handoffs between them. Researcher goes first.
 Needs Claude Code, Codex, Hermes, Antigravity, or Grok Bot. Follow the setup line for that host.
 
 Every agent runs its own research pass before it touches your site, so it works from what is
@@ -41,22 +42,21 @@ SET UP
 - Read roles/researcher.md first, then roles/coordinator.md, roles/designer.md,
   roles/graphics.md, roles/builder.md, roles/optimizer.md, roles/reviewer.md,
   and templates/handoff.yaml. Use each complete body, not these short summaries.
-- Create or identify Website Researcher first, then Website Coordinator,
+- The human opens Website Researcher first, then Website Coordinator,
   Website Designer, Website Graphics, Website Builder, Website Optimizer, and
-  Website Reviewer as separate sessions, Bots, or terminals. Parent may coordinate
-  only after the research gate. Use supported setup mechanisms, not invented imports.
-- Installer or human checks routes and obtains seven setup acknowledgements.
+  Website Reviewer as separate sessions, Bots, or terminals. Coordinator works
+  only after the research gate. Use available session controls and complete role files.
+- The human checks each session reference and obtains seven setup acknowledgements.
   These confirm receipt of instructions, not permission to start downstream work.
 - A role label in one conversation is option 1. Record SOLO and use prompts/00-start.md
   if separate workers cannot be reached. A same-family team remains a team but
   cannot pass independent review. Respect host concurrency limits.
-- Antigravity setup uses generated agent definitions and per-role tool declarations;
-  Hermes setup uses the verified definition branch or generated session packets and
-  bundle alias. Read the host adapter and receipt; pending discovery, trust, tools,
-  or independent review checks cannot be reported as a ready team.
+- Read the host adapter and receipt. The installer supplies role files and bundles;
+  the human opens sessions, checks trust and tools, and supplies each worker's files.
+  Pending discovery, trust, tools or independent review checks remain explicit limits.
 - Supply the request, authorized workspace, source assets, and tools to Researcher.
-  All other roles wait. Use the manual fallback in the team bundle if setup cannot
-  be automated; actual package integration remains UNVERIFIED until tested.
+  All other roles wait. Carry the complete packets using the manual setup below;
+  actual host loading remains UNVERIFIED until tested.
 
 RESEARCHER
 - Own site-work/research/library/ and handoffs/researcher/; own both research resources.
@@ -139,9 +139,9 @@ Never report a measured, saved, installed, or deployed result without evidence.
 Apply checklists/research.md before downstream dispatch and checklists/ship.md before release.
 
 PORTABLE MANUAL SETUP
-Use this fallback when native adapters or generated bundles are not supplied.
-Native loading, automatic worker creation, routing, tool enforcement and different-family
-availability are UNVERIFIED until the actual host/session checks succeed.
+Use this setup for TEAM on every host. You open each session and carry every handoff.
+Host loading, file access, tool enforcement and different-family availability remain
+UNVERIFIED until the actual host/session checks succeed.
 A missing host adapter does not authorize inventing a native file format or import API.
 
 1. Open the host's verified worker/session creation surface, if available.
@@ -153,8 +153,8 @@ A missing host adapter does not authorize inventing a native file format or impo
    with evidence, tools, inaccessible files, and owned paths. Keep downstream work pending.
 5. Give Reviewer a read-only candidate packet or verified read-only session. Broad
    inherited tools do not become restricted because role prose says read-only.
-6. Verify a bounded setup message reaches each intended route through supported controls.
-   When group automation is absent, the human can relay addressed packets and attachments.
+6. Deliver a bounded setup message to each session yourself. Relay addressed packets
+   and attachments, and verify each receiving worker can open them.
 7. Give the user's actual request, authorized workspace, assets and constraints to
    Researcher alone. It establishes ASK DATE and completes the library and gate first.
 8. Relay its complete passing receipt and readable library to Coordinator. Coordinator
@@ -163,7 +163,7 @@ A missing host adapter does not authorize inventing a native file format or impo
 Preserve seven acknowledgements separately from research and work-readiness receipts.
 A text-only group requires direct image attachments to each receiving visual reviewer.
 Inaccessible files or routes keep the relevant handoff BLOCKED.
-No automatic creation support means a manual setup limit, not a claimed ready team.
+Completed file installation means the files are available; session setup is the human's next step.
 No separate workers means SOLO; no independent family means independent review BLOCKED.
 Never invent a platform capability to fill a setup gap.
 
@@ -1681,6 +1681,8 @@ Never report a measured, saved, installed, or deployed result without evidence.
 
 ## Manual fallback
 
+TEAM: one command installs the seven workers' files; you open each session yourself and carry the handoffs between them. Researcher goes first. This manual relay is the TEAM workflow.
+
 **Prepare the files and workspace**
 
 - Get the complete `docs/bundles/team.md`, `method.md`, `prompts.md`, `playbooks.md`, and `checklists.md` from the same release. The team bundle contains the seven complete role bodies and this guide; the prompts bundle contains active prompts.
@@ -1703,7 +1705,7 @@ Never report a measured, saved, installed, or deployed result without evidence.
 **Connect the group and verify its routes**
 
 - If your account exposes group creation, create `Website Design` and add the seven saved Bots in the same order, Researcher first. Record the actual route for each. Verify one bounded setup message reaches the intended recipient using the host's documented addressing controls.
-- If group routing or automated handoff is unavailable, use separate Bot chats and relay each handoff and its attachments manually. Keep distinct workers on separate routes; separate workers need separate routes, and labels inside one chat stay one worker. Ordinary single-chat work uses SOLO.
+- Use separate Bot chats and relay each handoff and its attachments manually, including when the account offers a group view. Keep distinct workers on separate routes; separate workers need separate routes, and labels inside one chat stay one worker. Ordinary single-chat work uses SOLO.
 - If group messages are text-only, attach mockups and assets directly to the receiving Bot. Image review needs the Bot to open the image itself; a text path alone gives it only the path, so confirm the receiving Bot can inspect the image directly.
 - Give Coordinator this complete contract after replacing each angle-bracket route with the real saved Bot/chat reference. Unresolved placeholders keep setup incomplete.
 
@@ -1735,7 +1737,7 @@ with Builder's route/content inputs. Send the fixed final candidate to Reviewer
 only after pre-review gates pass. Different-family review remains mandatory.
 Read every returned artifact. Preserve Reviewer returns unchanged. Use every field
 in templates/handoff.yaml and record gate acceptance only in site-work/status.md.
-If routing fails, return the complete addressed packet for me to relay manually.
+Return every complete addressed packet for me to relay manually.
 ```
 
 **Trigger the first work handoff**
@@ -1756,11 +1758,11 @@ leave the research gate BLOCKED. If you cannot save files, return named file bod
 for me to save and reattach; wait for read-back before passing the disk gate.
 Pass only when the saved library covers every touched domain and every claim we
 will act on has an opened source URL, a publication/update date or explicit unknown, and an access date on or after the ASK DATE. Read back the actual saved files before confirming persistence.
-Then send research-to-coordinator to <actual Coordinator route> using all handoff
-fields and readable artifacts. No other role starts before this research gate.
+Then return research-to-coordinator addressed to <actual Coordinator route> for me
+to relay, using all handoff fields and readable artifacts. No other role starts before this research gate.
 ```
 
-- First receipt: Researcher supplies `site-work/handoffs/researcher/research-<revision>.yaml` and its library. If automatic delivery fails, copy the whole receipt and attach the library to Coordinator yourself.
+- First receipt: Researcher supplies `site-work/handoffs/researcher/research-<revision>.yaml` and its library. Copy the whole receipt and attach the library to Coordinator yourself.
 - First acceptance: Coordinator opens the files, checks coverage and source dates, and writes PASS or BLOCKED in `site-work/status.md`. Only PASS releases downstream scope handoffs.
 - First design: Designer and Graphics read their named library files, return learning/top-up receipts, and apply their domain checklists. They open the evidence behind the research summary before starting.
 - Persistence: preserve the files and receipts, and reattach the current revision in each new session. Carry state in the saved files, since a Bot may not remember a group chat. A durable-memory proposal remains pending until an actual supported save is read back.
@@ -1769,6 +1771,8 @@ fields and readable artifacts. No other role starts before this research gate.
 ## Artifact ownership roster
 
 ```yaml
+# TEAM: one command installs the seven workers' files; you open each session yourself and carry the handoffs between them. Researcher goes first.
+# This roster records ownership and handoff fields for the human to relay.
 schema_version: 1
 team: website-design-team
 coordinator: coordinator

package/docs/evaluation/host-gate.md

@@ -0,0 +1,129 @@
+# Manual host gate
+
+Status: NOT RUN. This document defines the work behind the explicit live-host skips.
+Live host behaviour is verified by receipts, not by `npm test`. The suite reports these
+items as skipped until a contributor supplies the required observations.
+
+## Automated distribution boundary
+
+Run from the package checkout:
+
+```sh
+node --test test/packed-artifact.test.mjs
+npm run check
+npm test
+```
+
+The packed-artifact test packs this revision, installs the tarball into a temporary
+consumer's `node_modules`, resolves the installed bin there, and runs SOLO and TEAM
+against empty destinations. It checks file trees, bytes, receipts and uninstall.
+The repository check workflow schedules it on `ubuntu-latest`, `macos-latest` and
+`windows-latest`. A configured matrix is a check to run; its results require CI evidence.
+The stable Repository checks job requires every matrix entry to succeed.
+
+Host discovery, upload controls, model behaviour and session permissions need the manual
+checks below. The repository currently builds bundles and an npm tarball; it has no ZIP
+production step. GitHub source archives and manually prepared skill ZIPs use the ZIP gate.
+
+## Hosts and operating systems
+
+Run each applicable item on the exact host, client version and OS whose compatibility
+claim you intend to make. Use Linux, macOS and Windows for any claim covering all three;
+keep unavailable host/OS combinations UNVERIFIED with a reason. A browser trial also
+records browser version and account controls available during that trial.
+
+| Host | Setup and loading instructions | Modes to observe |
+| --- | --- | --- |
+| Claude Code | [Adapter](../../adapters/claude-code.md) | SOLO and separately TEAM |
+| Codex | [Adapter](../../adapters/codex.md) | SOLO and separately TEAM |
+| Hermes | [Adapter](../../adapters/hermes.md), including explicit alias and trust checks | SOLO and separately TEAM |
+| Antigravity | [Adapter](../../adapters/antigravity.md) | SOLO and separately TEAM |
+| Grok Bot | [Adapter](../../adapters/grok.md), including attachment and manual relay controls | SOLO and separately TEAM |
+| Claude Desktop | [Adapter](../../adapters/claude-desktop.md), including skill ZIP upload where exposed | SOLO; record any separate-session TEAM trial separately |
+| ChatGPT Project | [Adapter](../../adapters/chatgpt-project.md) | SOLO; record any separate-session TEAM trial separately |
+| Custom GPT | [Adapter](../../adapters/custom-gpt.md) | SOLO; record any separate-session TEAM trial separately |
+| Generic file-reading agent | [Adapter](../../adapters/agents-md.md); name the actual client | SOLO; record any separate-session TEAM trial separately |
+
+TEAM installs seven workers' files in one command; you open each session yourself and
+carry the handoffs between them. Researcher goes first. Retain all seven setup
+acknowledgements separately from the research receipt and later work receipts.
+
+## Skipped item: live AD01-AD09 behaviour
+
+Test title: `Live AD01-AD09 behavior: ladder evidence, clock override, no-search blockage, stale claims, derived floors and multi-day expiry`.
+
+1. Use a fresh synthetic project on each claimed host/OS above. Follow the
+   [host trial](host-trial.md) to install, explicitly load the skill and record tool access.
+2. Run every case in `test/fixtures/ask-date-cases.md` from the matching source checkout
+   (test fixtures are checkout-only files).
+   Follow [AD01-AD09](../../skills/website-build-skill/checklists/research.md) and the
+   [ASK DATE rule](../../skills/website-build-skill/playbooks/research-and-memory.md#ask-date-rule)
+   for the expected boundary, including the independent AD09 review.
+3. Record the supplied input, actual tool evidence and observed response for each case.
+   Retain date ladder failures, conflicting clock evidence, absent search, stale claims,
+   derived floors and multi-day expiry observations. A fixture's expected answer is a
+   criterion, not an observation. Identify simulated tools separately from live tools;
+   a simulation cannot establish the live capability it replaces.
+4. Save scope, library, source receipts, gate output and transcript excerpts. Mark each
+   AD check PASS, FAIL, BLOCKED or NOT APPLICABLE with its evidence and reason. A missing
+   different-family Reviewer leaves AD09 BLOCKED.
+
+## Skipped item: per-host npm and ZIP distribution
+
+Test title: `Planned distribution: fresh npm tarball and ZIP installation on each claimed operating system and host`.
+The npm file-install portion is automated above; this skip covers actual host loading
+from that installation and ZIP extraction/upload on the host/OS combinations claimed.
+
+1. From the revision being evaluated, run `npm pack --json --ignore-scripts --pack-destination <existing-temp-directory>`.
+   Save the JSON report and the tarball digest. In a separate empty consumer, run
+   `npm init -y`, then `npm install --ignore-scripts --no-audit --no-fund <absolute-tarball-path>`.
+2. Run the consumer's installed bin, substituting the adapter target and a fresh absolute
+   trial directory. Repeat with `--team` in another empty trial directory:
+
+   ```sh
+   node node_modules/website-build-skill/bin/website-build-skill.mjs --solo --target codex --dir <trial-directory> --yes
+   ```
+
+   Compare receipt paths and hashes with the disk. Open the actual host in the trial
+   directory and follow its loading check. Record explicit file reads separately from
+   native discovery. Verify accessible assets, preserved existing instructions and
+   error/conflict behaviour in separate synthetic fixtures.
+3. For a GitHub source ZIP, download the archive for that exact commit, record its URL
+   and digest, extract it into an empty directory and follow the adapter's manual copy
+   or bundle-attachment steps. Verify manifest hashes and loaded resources.
+4. For a skill-upload ZIP, create an archive containing one complete
+   `website-build-skill/` directory from `skills/website-build-skill/`, with manifest and
+   relative assets. Record the packaging command/tool version, layout and digest.
+   Upload using the actual account controls described by the adapter and confirm each
+   loaded resource. Record absent upload controls as BLOCKED for that route. Source
+   archives and skill-upload ZIPs are distinct artifacts and need separate results.
+5. Save installer output, receipt, installed file/digest inventory, exact invocation,
+   host transcript and observed limits. Use the [full trial](host-trial.md) separately
+   before making a website-outcome claim.
+
+## Receipt and acceptance
+
+Copy [receipt-template.json](receipt-template.json) into the private trial workspace.
+Fill its fields from observations, including:
+
+- Identity: trial ID, package commit, artifact filename and SHA-256, host/client version,
+  OS/version, runtime and actual model family, mode, invocation and start/end times.
+- Commands: exact commands, working-directory roles, exit codes and relevant output.
+- Boundaries: each skipped item and AD check attempted, expected and observed behaviour,
+  status, and links to transcript excerpts, installed receipts and supporting files.
+- Negative trials: missing tools, conflicts and other failures actually exercised.
+- Review: candidate digest, actual reviewer family, findings and reproduced dispositions.
+- Limits: untested host/OS/mode combinations and unavailable controls; reproduction steps.
+
+Add artifact metadata to `artifacts` and per-case observations to `boundaries`; preserve
+unknown values as null. Sanitize private paths, account identifiers and credentials.
+Save the receipt as `docs/evidence/host-gate-<trial-id>.json` and its supporting artifacts
+under `docs/evidence/host-gate-<trial-id>/`. A reviewer reopens those artifacts before
+accepting the result. Keep failed and blocked receipts alongside successful ones.
+
+Each skipped item advances to either a real executable test for the behaviour it can
+assert, or a linked, reviewed receipt for the exact host/OS/mode observed. A receipt may
+be linked beside a retained skip for combinations still awaiting trials. A skipped test
+is never converted to a pass by editing its label, removing `skip`, or adding an empty
+passing body. `npm test` alone establishes no live-host result. Promote compatibility
+only for the observed scope under the [host-trial evidence rules](host-trial.md#publish-evidence-and-promote-narrowly).

package/docs/evaluation/host-trial.md

@@ -2,6 +2,8 @@
 
 Status: NOT RUN. This protocol is an acceptance test, not evidence of host support.
 A passing repository test suite or a copied skill folder cannot promote this status.
+Use the [manual host gate](host-gate.md) for the suite's live-host skips, per-OS loading
+checks, ZIP trials and required receipts.
 
 ## Scope and authority
 
@@ -14,7 +16,8 @@ Use a local preview. Production release and live-host checks remain BLOCKED.
 The operator supplies the visual selection and a separate model family for review.
 If either is unavailable, record the exact boundary reached; do not manufacture a PASS.
 The first useful milestone is one complete SOLO local-preview trial on one named host.
-TEAM requires a separate trial with seven observed routes and cannot inherit that result.
+TEAM requires a separate trial with seven sessions the human opens and handoffs they
+carry, with Researcher first; it cannot inherit the SOLO result.
 
 ## Prepare and invoke
 

package/docs/evidence/content-review.json

@@ -10,30 +10,52 @@
       "disposition": "instructions-and-qualified-status-only"
     },
     "CHANGELOG.md": {
-      "sha256": "e4416113d528ffd9f11ff703ed5f1a7645032ef592f22e72f0a82aa9d6ef4f97",
+      "sha256": "4e1c9fd46f9f759efa2f1bb8d782d7110985a485194b4214716cae9d94a5a5c5",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the added 0.1.1 framing note against the presentation copy changes; publication is a separate release action. Implementation-agent editorial review; independent review remains pending. Reviewed the copied-install checker ladder fix against the canonical instructions and regression test. Live host retrial remains pending release. Reviewed for the ROUND 1 audit: added Fixed/Added/Changed lines for the restored positive-and-accurate adapter, SKILL.md, designer.md, grok.md and validate.mjs fixes. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed the #13 description check and #14 Hermes path documentation entries against the implementation and regression tests; publication remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the added 0.1.1 framing note against the presentation copy changes; publication is a separate release action. Implementation-agent editorial review; independent review remains pending. Reviewed the copied-install checker ladder fix against the canonical instructions and regression test. Live host retrial remains pending release. Reviewed for the ROUND 1 audit: added Fixed/Added/Changed lines for the restored positive-and-accurate adapter, SKILL.md, designer.md, grok.md and validate.mjs fixes. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed the #13 description check and #14 Hermes path documentation entries against the implementation and regression tests; publication remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. Reviewed the #15 Fixed line for the symlinked-parent receipt path against src/install.mjs and installer tests 7e-7g, and the #15 Added line against the two receipts. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. 0.1.5 release heading moved the Unreleased lines under [0.1.5] - 2026-09-24 unchanged."
     },
     "CLAUDE.md": {
-      "sha256": "502ce6fb03a6032d4a03198288e10906d38c73124937950e34176d44a7f52440",
-      "disposition": "instructions-and-qualified-status-only"
+      "sha256": "983dd28a6ba815adef9201351d7845f6cf5567e0be92be975ee74d98b4ee346a",
+      "disposition": "status-claims-bound-to-receipts",
+      "claims": [
+        {
+          "text": "Native SOLO loading is tested on Claude Code and Codex",
+          "evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
+        },
+        {
+          "text": "(one run each, receipts in docs/evidence/)",
+          "evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
+        }
+      ],
+      "review": "0.1.5 (#15): status line narrowed to the two SOLO loading receipts; other hosts, TEAM, account tools and independent review stay UNVERIFIED. Claude editorial review."
     },
     "CODE_OF_CONDUCT.md": {
       "sha256": "9b32964f09663dbcf16e5ce39b4522928ba4c74d13c49f3fe6a9fb131b8ddd31",
       "disposition": "instructions-and-qualified-status-only"
     },
     "CONTRIBUTING.md": {
-      "sha256": "d77f293d947f4b60569f4dff4b9eb410c214d20107a0c7049f7ec63ebd4ba860",
-      "disposition": "instructions-and-qualified-status-only"
+      "sha256": "f72ebfa07c6a23bb06778c708633b31b2628f2d287b3d02e3248f72ce88fe1e7",
+      "disposition": "instructions-and-qualified-status-only",
+      "review": "Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "MAINTAINERS.md": {
       "sha256": "8632008661d5ad3d60300ea2028715217c298d24d3d66af7224c52b6e0e24552",
       "disposition": "instructions-and-qualified-status-only"
     },
     "README.md": {
-      "sha256": "d4886bebd3d73a9545466fdfce1cac7a7ff0464ee14151cb6adb4ab1dd76df98",
-      "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the requested skill-pack framing and each learning-table sentence against its linked canonical instructions; preserved the twelve stages, starter, setup card and sibling links. Demo URL awaits the separately recorded artifact. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending."
+      "sha256": "362773785e80e089e8311429cc045243747e0943bdad9601e54f882314ca6777",
+      "disposition": "status-claims-bound-to-receipts",
+      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the requested skill-pack framing and each learning-table sentence against its linked canonical instructions; preserved the twelve stages, starter, setup card and sibling links. Demo URL awaits the separately recorded artifact. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding.",
+      "claims": [
+        {
+          "text": "Native loading is tested",
+          "evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
+        },
+        {
+          "text": "on Claude Code and Codex with dated receipts",
+          "evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
+        }
+      ]
     },
     "RELEASING.md": {
       "sha256": "7e89b30d20fef7570fc0485f80844c651a861a18956efd43e1555967f3e8dde4",
@@ -50,49 +72,61 @@
       "disposition": "instructions-and-qualified-status-only"
     },
     "adapters/agents-md.md": {
-      "sha256": "fc2d939ab3a278742410f181894d083e8bfe95504cd8829b78341e5fdb0bba3d",
+      "sha256": "c00b15550493055d21c44cccc213a9315514649f45df0ac42b3370d470b661af",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/antigravity.md": {
-      "sha256": "9da29d296864f9ddeeb3e0504c0f9146310e7cfbfae1b790a96d2f53c2807d38",
+      "sha256": "3cef0375be38e6c587c9175463f2e94424244f66e423555cf8819a6ca266269e",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/chatgpt-project.md": {
-      "sha256": "3838b3b56471a5d89edf55c388c139557e6914c2ff9b030759340ac715d85292",
+      "sha256": "e8faa8762cd4501f3400d81cd90bca91d09b43e51ad74d8b03a7e1a0a6cdfa30",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/claude-code.md": {
-      "sha256": "301a022d230fdb324bb35c3ca278bf11b8abdd34bb4081463217764095809938",
-      "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "sha256": "1a811ad3ca4520f1a87f1d66a09d7d21456eb9d9fbbf1697146410e223d3d5c1",
+      "disposition": "status-claims-bound-to-receipts",
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding.",
+      "claims": [
+        {
+          "text": "Native loading was tested on Claude Code 2.1.281 (macOS, SOLO, 2026-09-24;",
+          "evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
+        }
+      ]
     },
     "adapters/claude-desktop.md": {
-      "sha256": "500a21b58ae56e4a07b6505ea858787a417aab1fd37bd01b7484b1110742e680",
+      "sha256": "d2164e37eea26dad680a63d7f534ea588fd40500b9e1af858de3b86a5a8e6793",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/codex.md": {
-      "sha256": "fdbc2c38b1ff2542518c6f9ccaac289d768857cef1b139c25219d0face9b258a",
-      "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "sha256": "005d05bfec4d1765e5d7e1048f086b344fa9ea6e50321ad8fd154001cc0f47fe",
+      "disposition": "status-claims-bound-to-receipts",
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding.",
+      "claims": [
+        {
+          "text": "Native loading was tested on Codex CLI 0.154.0 (macOS, SOLO, 2026-09-24;",
+          "evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
+        }
+      ]
     },
     "adapters/custom-gpt.md": {
-      "sha256": "2a918b423b3ae322644ff2e7c014f97d2e02deedb0838ec73e7023d2b5a6c435",
+      "sha256": "c7fa5fc40413d2803a6e682e81bd1d39a5b24dbf1d21e41c7f401788d44cee51",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/grok.md": {
-      "sha256": "a139a99650ca2a4d16fd862a184a6ea736ad72999ef4947fd3701b1d6d6e69a6",
+      "sha256": "66e869b434ec1857b3abcda064f2e4162e41bdd5f9765496095caafeadd4bdaa",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending."
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/hermes.md": {
-      "sha256": "eeba94a78d84587d8a5fefea75692ff9ae4c2efaeb119a8672b22e18b5ad8724",
+      "sha256": "bfb7624ce627d7a59328a16a663ed71aa96dbe24ede160bc349f13dd08cd1578",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed team-aliases placement and the destination boundary against src/install.mjs plan/safePath and the extended installer regression; native loading status is unchanged. Implementation-agent editorial review; independent review remains pending."
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed team-aliases placement and the destination boundary against src/install.mjs plan/safePath and the extended installer regression; native loading status is unchanged. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/zero-install.md": {
       "sha256": "7ac8fb37969ecbc321be6e74f6193d04d61ed4760ca7951975ab6d636d227699",
@@ -100,15 +134,19 @@
       "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
     },
     "docs/COMPATIBILITY.md": {
-      "sha256": "09f802f0be36b0938389f455fcb5f3e6fd1b78193d5781b48998cbe12c62c268",
-      "disposition": "evidence-backed",
+      "sha256": "3b7fa6f4e1c0576beb6ec6cc6af7365318affc41fe162066936f9332d998eaf8",
+      "disposition": "status-claims-bound-to-receipts",
       "claims": [
         {
-          "text": "Hosted repository checks have a [revision-bound baseline receipt](evidence/audit-baseline.json).",
-          "evidence": "docs/evidence/audit-baseline.json"
+          "text": "| Claude Code | 2.1.281, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 |",
+          "evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
+        },
+        {
+          "text": "| Codex CLI | 0.154.0, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 |",
+          "evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
         }
       ],
-      "review": "Reviewed documented setup routes and required trial evidence; retained the existing revision-bound hosted-check claim and receipt. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
+      "review": "Reviewed documented setup routes and required trial evidence; retained the existing revision-bound hosted-check claim and receipt. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding."
     },
     "docs/EVALUATION.md": {
       "sha256": "cb34b13e24b906496d0f05ef20187695bd51defe75b25abb7df8d5ad2935c32d",
@@ -122,14 +160,14 @@
       "review": "Reviewed the exact two-sibling allowlist against production privacy rules and rejection regressions. Implementation-agent editorial review; independent review remains pending."
     },
     "docs/INSTALLER.md": {
-      "sha256": "85944c760b696080cb2ba8b6d381af13da3aeafa517965c7c7e28dd4625b10c6",
+      "sha256": "4a6c7c35729d0031a9c26bc7610ad6b0de9ae1ff7cc7da4c3a7fcf05d96e3e1f",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed npm commands and loading instructions against the CLI contract and existing installer tests; flags and exit policy preserved. Implementation-agent editorial review; independent review remains pending. 0.1.3: reviewed the installed skill folder resolution root, exit 3 and Path escapes destination root message against src/install.mjs and the installer regression. Implementation-agent editorial review; independent review remains pending."
+      "review": "Reviewed npm commands and loading instructions against the CLI contract and existing installer tests; flags and exit policy preserved. Implementation-agent editorial review; independent review remains pending. 0.1.3: reviewed the installed skill folder resolution root, exit 3 and Path escapes destination root message against src/install.mjs and the installer regression. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "docs/METHOD.md": {
-      "sha256": "fe97181fb1be0ea37223fa792c2949832082cd9054e6c9c4bc87cfe4b11706ee",
+      "sha256": "3b45db282de20f327c903e86f6d7da9440b5913907dfb75cadedf5e6b7210f95",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "docs/PROVENANCE.md": {
       "sha256": "a4d8039968d64163c78997e15b1a9dc8cc5b1e7aa6995a0f07e789758b2e7cb4",
@@ -151,13 +189,14 @@
       "review": "Self-attested by the implementation agent for this change; independent editorial review remains pending."
     },
     "docs/evaluation/host-trial.md": {
-      "sha256": "770b5663a7c0bfe71919a4c4d9a53df31cbe8a9aac54b193ae7ba092cec23b41",
-      "disposition": "instructions-and-qualified-status-only"
+      "sha256": "0f45d1e9d2a118990a9f5ac724ea8383ba70f6e3d823c5117388d1ffc5daf9d8",
+      "disposition": "instructions-and-qualified-status-only",
+      "review": "Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "docs/README.md": {
-      "sha256": "2d3511777a1fdf7a42821b7644d4d018c2b4250c6567f07dfecc218f4062a772",
+      "sha256": "eee5835dc95cd0d757ef6e011160d404368e7b0168b9fd2fd92c9bc67a84c92d",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed guide descriptions and relative links against existing documentation and bundle membership. Implementation-agent editorial review; independent review remains pending."
+      "review": "Reviewed guide descriptions and relative links against existing documentation and bundle membership. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "docs/bundles/checklists.md": {
       "sha256": "901f259236bdcd29b9ced21be9a195708d38bef4c186783bed3f193285e573ea",
@@ -165,9 +204,9 @@
       "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending."
     },
     "docs/bundles/method.md": {
-      "sha256": "a704e2e73cac7b7b080cbc1e3cf33df6561a205334b39c453241fbe353606db1",
+      "sha256": "a069bba587b980223ff84ba7f1eb0f9c6b3183ac4690cba34a61deb93d7e7dc0",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "docs/bundles/playbooks.md": {
       "sha256": "88fa3ac16eaa736bca4580e820748197a64c75aac2c96745b673c283349078dc",
@@ -175,19 +214,19 @@
       "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending."
     },
     "docs/bundles/prompts.md": {
-      "sha256": "4a2cdc64c6773d153f32e20e611945f0500350cede2a438864075e5dce7cec24",
+      "sha256": "a140f44d194b1b62108877344fe67b490c4f253ec0c5a64a19f341ef2bbfd2fe",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "docs/bundles/team.md": {
-      "sha256": "ae64ddac5ff331d7e304f0e4372cd8d4d0c17e92955b345ebb433490ad5b0fbb",
+      "sha256": "020e009e1cb6404468a749802ceb33da6485019dd42a33007e77138d9d9ef62e",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.4: reviewed generated content against the canonical manifest, fourteen-domain coverage, coding-research prompt, code-quality gate and team ownership roster; generated copies carry the source instructions. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "skills/website-build-skill/SKILL.md": {
-      "sha256": "ed1c909f9946de0fa7a43364c84efc837b6644c0dc8334b81ddfaf031db156e1",
+      "sha256": "71cb5b229d68ae1b91a11d4168c6093a88d0c0f7da2dbcab0c933cb6a333c81b",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "skills/website-build-skill/checklists/build.md": {
       "sha256": "4492d1576d276f73dcab9be83e525acf690984bb058f2139c1c703967fe1eccf",
@@ -220,9 +259,9 @@
       "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending."
     },
     "skills/website-build-skill/prompts/00-start.md": {
-      "sha256": "d5ed2a92d5bd7071895658ebbf4d7d696aeddb3735aa8d9153d0405c517f7b9c",
+      "sha256": "9de537723108ad71b608c467d78c7ba6edb54880d0429f5321d490cba9c900cb",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "skills/website-build-skill/prompts/01-website-deep-research.md": {
       "sha256": "6289264065a504551c0f6d20f7cfecc6a916880df8d91f1b4f5b04684c481cab",
@@ -235,9 +274,9 @@
       "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending."
     },
     "skills/website-build-skill/prompts/12-web-design-team.md": {
-      "sha256": "58a53b49b1da1039195d0ecaa24dff296668d9c4c4a52545d40836ddf8d6d388",
+      "sha256": "a1b1460deea3520d25245d805521019f758b905b97e73ac97e7020cead861837",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending."
+      "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "skills/website-build-skill/prompts/13-coding-research.md": {
       "sha256": "d1de4c7ed85b4109a35b60d5d2aedd2db5178ed6d198cbdca0c31250cf469ed4",
@@ -268,6 +307,11 @@
       "sha256": "2b3476d038ee0b067ea38006bcad6819ab219b5751de92f911820abe53ab501f",
       "disposition": "instructions-and-qualified-status-only",
       "review": "0.1.4: reviewed against the coding-research task specification for fourteen-domain coverage, selected-stack standards before implementation, freshness, evidence and role ownership; no current language version or feature status is asserted. Implementation-agent editorial review; independent review remains pending."
+    },
+    "docs/evaluation/host-gate.md": {
+      "disposition": "instructions-and-qualified-status-only",
+      "sha256": "9b3655277a8ed181310247e2536888b221547590537715393d88ea0cc4c7af3f",
+      "review": "Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     }
   }
 }