diff --git a/README.md b/README.md
index 0e6ac75d..5bd64eb7 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@ remains opaque content for the calling agent to interpret.
 
 This public repository's current source is **agent-collab** (v7.0.6).
 
-Current published release: **7.0.5** ([`v7.0.5`](https://github.com/sumitake/agent-collab/releases/tag/v7.0.5)).
+Current published release: **7.0.6** ([`v7.0.6`](https://github.com/sumitake/agent-collab/releases/tag/v7.0.6)).
 It carries signed provider runtime `5.0.7`. Host installation, readiness, and
 provider availability remain separate evidence planes.
 
@@ -20,17 +20,20 @@ installation, and readiness claims separate.
 
 ## What's new - v7.0.6
 
-Review skills now make reviewer independence a caller responsibility. Before
-dispatch, the caller establishes the primary and artifact-author families and
-checks the proposed reviewer. Afterward, it verifies the observed reviewer
+When independent review is required, the skills make reviewer independence a
+caller responsibility. Before dispatch, the caller establishes the primary and
+artifact-author families and checks the proposed reviewer. Afterward, it verifies the observed reviewer
 family and source before accepting independent evidence. Unknown lineage stays
 unknown; a routing result alone does not establish independence.
 Ordinary code review can still use available Gemini when no eligible independent
 reviewer exists, with an explicit advisory label and no independent-approval claim.
 
 This content update retains the signed runtime `5.0.7` and wire schema 12
-unchanged. Publication and host refresh for 7.0.6 are pending; the dated status
-snapshot remains the verified 7.0.5 release record.
+unchanged. The release is published, and all 178 released files match each of
+the four observed local installations. Provider-free planning and migration
+checks passed from the control session against those roots; existing tasks
+still need a fresh session to load updated skills. The dated status snapshot
+records those limits and the unresolved Claude subscription-access denial.
 
 For earlier release history, see the full [CHANGELOG](CHANGELOG.md).
 
@@ -189,7 +192,7 @@ Dependabot for dependency update review.
 
 After every other release task finishes, complete the
 [documentation closeout](docs/architecture/repository-and-release.md#final-documentation-closeout).
-The v7.0.5 closeout is recorded in the
+The v7.0.6 closeout is recorded in the
 [status and evidence snapshot](docs/architecture/status-and-evidence.md). Each
 future closeout must likewise align the architecture handbook, this README,
 and generated changelog evidence with the exact release without exposing
diff --git a/changelog.d/2026-09-08-706-documentation-closeout.md b/changelog.d/2026-09-08-706-documentation-closeout.md
new file mode 100644
index 00000000..3b3e5248
--- /dev/null
+++ b/changelog.d/2026-09-08-706-documentation-closeout.md
@@ -0,0 +1,4 @@
+### Changed
+
+- Record the published agent-collab 7.0.6 release and verified assets, separating installation and provider-free readiness from fresh-session loading and Claude inference access.
+- Align the handbook and release narratives with caller-owned independent review, ordinary Gemini advisory review, bounded source delegation and compatible caller sandbox execution. The signed runtime and release history remain unchanged.
diff --git a/docs/architecture/README.md b/docs/architecture/README.md
index 7538b457..960f205d 100644
--- a/docs/architecture/README.md
+++ b/docs/architecture/README.md
@@ -10,7 +10,7 @@ the contribution contract remain authoritative for their respective claims.
 When two generations differ, use the status vocabulary below instead of
 silently treating them as the same thing.
 
-The current published release is v7.0.5 with signed provider runtime 5.0.7,
+The current published release is v7.0.6 with signed provider runtime 5.0.7,
 manifest schema 4, runtime protocol 5, native contract 4, and wire schema 12.
 
 ## Read this handbook in order
@@ -105,7 +105,7 @@ not a public issue or pull request.
 | --- | --- | --- |
 | What does the package install? | [System context](system-context.md) | Host manifests, generated marketplaces, package tree, and distribution tests. |
 | Which workflows exist? | [Capabilities and workflows](capabilities-and-workflows.md) | `skill-specs/`, generated skills, package reference, and skill-contract tests. |
-| How are agent projects estimated? | [Project estimation](project-estimation.md) | Public request/result schemas, deterministic helper, released v7.0.5 maintenance evidence, skill checkpoints, maintenance verifier, producer-byte compatibility fixtures, and focused tests. |
+| How are agent projects estimated? | [Project estimation](project-estimation.md) | Public request/result schemas, deterministic helper, released v7.0.6 maintenance evidence, skill checkpoints, maintenance verifier, producer-byte compatibility fixtures, and focused tests. |
 | Who may review, write, or merge? | [Governance and authority](governance-and-authority.md) | Host policy, coordinator, public governance contract, PR template, and compliance checks. |
 | Is a route usable now? | [Status and evidence](status-and-evidence.md) | Installed version plus provider-free readiness on that host. Repository presence alone is insufficient. |
 | How do I install or recover? | [Lifecycle and operations](lifecycle-and-operations.md) | Current host CLI, migration doctor, runtime-management surface, and migration policy. |
diff --git a/docs/architecture/capabilities-and-workflows.md b/docs/architecture/capabilities-and-workflows.md
index 59598d72..a4bf0c77 100644
--- a/docs/architecture/capabilities-and-workflows.md
+++ b/docs/architecture/capabilities-and-workflows.md
@@ -20,7 +20,7 @@ organizes that inventory by user outcome.
 | Planning, architecture, and estimation | `architect`, `brainstorm`, `compose-skills`, `intent-check`, `project-estimation`, `second-opinion` | Clarify a design, widen options, select workflows, obtain an independent read, or forecast agent-led delivery. |
 | Governance and assurance | `autonomy-readiness`, `code-review`, `governance-review`, `logic-check`, `qa-verify`, `red-team`, `untrusted-audit` | Test correctness, independence, security, provenance, and completion evidence. |
 | Deliberation and stakeholder lenses | `debate`, `simulate-user` | Expose conflicting arguments or test a proposal against a persona. |
-| Delegation and implementation | `delegate`, `dev-delegate`, `worker` | Return bounded research or output for the primary to integrate. |
+| Delegation and implementation | `delegate`, `dev-delegate`, `worker` | Analyze supplied sources or return a development artifact for the primary to integrate. |
 | Context and knowledge work | `context`, `knowledge-compile`, `project-knowledge` | Extract or synthesize bounded documents/repositories, or maintain an explicit project knowledge layer, with provenance. |
 | Reproducible workflows | `chain`, `chain-configurator`, `orchestrate` | Define and execute repeatable multi-step coordination. |
 | Integration and conflict handling | `merge-resolve` | Analyze and resolve a bounded merge conflict while preserving intent. |
@@ -86,34 +86,43 @@ the primary for integration.
 
 ## Common workflows
 
-### Independent review
+### Code review and independent approval
 
-1. Identify the exact artifact and its author lineage.
-2. Invoke `second-opinion`, `code-review`, `governance-review`, `red-team`, or
-   `qa-verify` according to the risk.
-3. The skill/repository workflow requires a reviewer outside the primary and
-   artifact-author families. The primary verifies that independence; the
-   current routing request does not dynamically enforce those lineages.
-4. Preserve the raw finding and typed status.
-5. The primary adjudicates, changes the artifact if needed, and re-verifies the
-   exact head.
+1. Identify the artifact, primary, authors and whether the task requires
+   independent approval.
+2. Use the appropriate review skill. For required independence, verify a
+   reviewer outside the primary and author families and bind that selection to
+   the live call. Verify observed reviewer lineage and exact source afterward.
+3. For ordinary code review, an available Gemini reviewer can still help when
+   no distinct-family reviewer is available. Label same-family or unknown
+   lineage as advisory; leave any independent approval requirement unmet.
+4. Preserve and adjudicate the raw findings. Do not infer independence from
+   routing, role names or a subscription, repeatedly attempt an unavailable
+   provider, or replay a consumed request to repair formatting or evidence.
+
+This is caller-owned behavior in the [released code-review
+skill](../../skill-specs/code-review.md). The routing request has no dynamic
+primary/artifact-author lineage exclusion fields.
 
 ### Bounded delegation
 
-1. The primary keeps objective interpretation and integration ownership.
-2. A worker receives a bounded scope, authority, evidence contract, and stop
-   condition.
-3. Read-heavy work can use a cheaper capable tier; judgment and landing stay
-   with the primary.
-4. The caller supplies a disposable repository or copy, captures any patch,
-   and verifies it before application; the runtime does not apply output.
-5. The primary reviews and tests all delegated output before it becomes source.
+The primary keeps objective interpretation and integration ownership. Ordinary
+`delegate` work analyzes supplied bounded documents or an exact sealed
+repository through an admitted context action. A list of names, links or topics
+alone is not a document corpus, and this route does not promise source discovery.
+Each worker receives the relevant sources, scope and stop condition. Results
+remain advisory; multiple workers do not imply multiple model families.
+
+Development delegation uses the separate admitted code-generation actions.
+The caller supplies a disposable repository or copy, captures any returned
+patch, and reviews and tests it before application. A worker does not gain
+permission to apply output or make landing decisions through successful routing.
 
 ### Architecture and planning
 
-Use `brainstorm` to widen the option space, `architect` for an independent
+Use `brainstorm` to widen the option space, `architect` for an additional
 read-only architecture consultation, `architecture-review` for a primary-led
-codebase sweep, `intent-check` to validate task interpretation, and
+codebase sweep, `intent-check` for an advisory task-interpretation comparison, and
 `decision-map` when the effort is too large for one session.
 
 `project-estimation` adds a deterministic delivery forecast once a formal
@@ -124,7 +133,7 @@ workflows explicitly compose the checkpoint before final presentation. A host
 without contextual skill selection uses explicit invocation and reports that
 the automatic checkpoint was unavailable. See
 [Project estimation](project-estimation.md) for modes, examples, output
-semantics, and the published v7.0.5 maintenance evidence.
+semantics, and the published v7.0.6 maintenance evidence.
 
 The packaged prior is currently an explicit bootstrap: enhancement duration is
 descriptive, bootstrap confidence cannot be high, and unsupported greenfield,
@@ -145,7 +154,7 @@ authority.
 | --- | --- | --- |
 | Claude Code | Claude-compatible plugin manifest and marketplace metadata. | Native package install and `/agent-collab:*` skills. The official native CLI may serve read-only document intent when action-scoped readiness passes; Claude is not eligible for managed review, governance, repository, or code-generation actions (see [Claude participation](claude-participation.md)). |
 | Codex CLI/app | Codex-native manifest and generated Codex marketplace. | Native package install and the same skill namespace. Start a new task after install/update. |
-| Antigravity | Dynamic host policy and async target model; no separate package. | Use only through a compatible package host and observed async readiness. It is not a coordinator `target_agent` unless the current signed descriptor explicitly admits it. |
+| Antigravity | Compatible plugin import, logical Gemini managed routes, and separate host-owned async coordination; no separate package. | Gemini repository review uses the co-packaged coordinator and action-scoped readiness. Async readiness is a different surface; neither host name nor reviewer role proves independence. |
 | OpenCode and ZCode | Dynamic host/model policy and managed OpenCode routes; no separate package. | A compatible host/plugin surface is required. OpenCode is a transport; the selected model supplies family lineage. |
 | Custom host | Explicit primary identity fields and the closed package contract. | If the host cannot load the package safely, it is unsupported; do not recreate provider-specific shims. |
 
@@ -161,9 +170,11 @@ A capability is usable only when all applicable gates pass:
 - the native boundary and provider-free readiness checks pass; and
 - provider authentication, quota, and request execution succeed.
 
-Failing one gate produces a typed result such as `unavailable`,
-`same_family_blocked`, `unknown_family`, or a runtime error category. Do not
-turn that result into a raw-provider fallback or broader authority.
+Runtime and planning diagnostics describe the attempted route; they do not
+perform the caller's family-exclusion check or establish provider-wide failure.
+Missing independent-review evidence leaves that requirement unmet. Preserve
+available advisory content without claiming broader authority, silently
+substituting an operator-named target, or replaying a consumed request.
 
 For installation and recovery, continue to
 [Lifecycle and operations](lifecycle-and-operations.md).
diff --git a/docs/architecture/claude-participation.md b/docs/architecture/claude-participation.md
index 98268759..b15a8a43 100644
--- a/docs/architecture/claude-participation.md
+++ b/docs/architecture/claude-participation.md
@@ -52,6 +52,12 @@ The 7.0.5 host qualification explicitly deferred restoration of local Claude
 subscription access and live Claude intent qualification. That deferral does
 not enable another Claude action and is not a passed native inference check.
 
+During the 7.0.6 follow-up, one fresh admitted document-intent attempt returned
+an organization subscription-access denial. Package installation and
+provider-free readiness did not establish inference access. Omitted Claude
+profiles remain unqualified in [#162](https://github.com/sumitake/agent-collab/issues/162);
+the attempt was not replayed, and no billing or credential change was made.
+
 ## Host and resident-primary role
 
 Claude Code remains a fully supported host: the package installs natively,
diff --git a/docs/architecture/governance-and-authority.md b/docs/architecture/governance-and-authority.md
index 254f5932..b11b4e12 100644
--- a/docs/architecture/governance-and-authority.md
+++ b/docs/architecture/governance-and-authority.md
@@ -20,12 +20,31 @@ field. It does not dynamically perform this exclusion. The skill and repository
 workflow require it, and the primary verifies the selected reviewer and the
 substance of the exact-head review.
 
+For an authorized independent review, the caller binds its verified reviewer
+selection to the actual request, honors an operator-named provider, and checks
+observed native lineage afterward. Planning an untargeted call does not reserve
+that selection for a later call. Role names, receipts and routing success do
+not establish independence, and a consumed request is not replayed to improve
+its evidence. The [released review skill](../../skill-specs/code-review.md)
+contains the caller procedure.
+
+Ordinary code review remains useful when no independent reviewer is available.
+For example, a Gemini primary with only Gemini available can receive a
+same-family advisory review. Unknown lineage is labeled unverified advisory.
+Neither clears an independent approval required by the task or repository, and
+the caller does not repeatedly try an absent Grok installation. An OpenCode or
+ZCode subscription name alone establishes no model lineage.
+
+Intent comparison, creative ideation, persona simulation and bounded context
+delegation are advisory work. They need no family difference to proceed and
+cannot become governance evidence through a role assignment or successful call.
+
 ```mermaid
 flowchart LR
-    Artifact["Artifact plus author lineage"] --> Eligibility["Eligibility policy"]
+    Artifact["Artifact plus author lineage"] --> Eligibility["Caller verifies required lineages"]
     Primary["Active primary lineage"] --> Eligibility
-    Eligibility --> Exclude["Exclude primary and author families"]
-    Exclude --> Reviewer["Eligible independent reviewer"]
+    Eligibility --> Exclude["Caller excludes primary and author families"]
+    Exclude --> Reviewer["Caller selects an independent reviewer"]
     Reviewer --> Evidence["Review artifact or governance verdict"]
     Evidence --> PrimaryGate["Primary integration and repository gates"]
 ```
diff --git a/docs/architecture/lifecycle-and-operations.md b/docs/architecture/lifecycle-and-operations.md
index 8e32089b..77af4a0c 100644
--- a/docs/architecture/lifecycle-and-operations.md
+++ b/docs/architecture/lifecycle-and-operations.md
@@ -72,7 +72,7 @@ Installation, selection, and readiness are separate checks.
    snapshot. A listed route is not proof of readiness.
 5. **Bounded smoke test:** invoke one low-risk read-only workflow, such as a
    second opinion on a short draft, and verify the returned family is eligible
-   and independent.
+   and independent where the task requires independent approval.
 
 For an activation package, inspect the provider-free migration report:
 
@@ -99,7 +99,7 @@ Invoke the skills in normal language or by their host command. Examples:
 /agent-collab:second-opinion Review this architecture decision.
 /agent-collab:code-review Review the current diff against the task.
 /agent-collab:qa-verify Verify the completed work against these acceptance criteria.
-/agent-collab:delegate Split this read-only research list with an independent reviewer.
+/agent-collab:delegate Extract comparable facts from these supplied reports in parallel.
 /agent-collab:agent-runtime-status
 ```
 
@@ -119,7 +119,7 @@ Preserve the typed coordinator response. Any later issue report is an explicit,
 separately authorized action and never grants governance authority or licenses
 replay of the provider request.
 
-`project-estimation` is offline and read-only by default. The packaged v7.0.5
+`project-estimation` is offline and read-only by default. The packaged v7.0.6
 source contains an explicit bootstrap prior: enhancement duration is
 descriptive, greenfield may return `no_compatible_prior`, and absent token
 evidence returns `unavailable_no_token_prior` rather than zero. Persist an
@@ -217,6 +217,18 @@ a fresh session only after the host reports the intended package version. Do
 not reconstruct a lifecycle path, copy a runtime out of another package, or
 fall back to a retired provider-specific plugin.
 
+## Caller sandbox compatibility
+
+A caller's macOS sandbox can prevent a native provider from initializing its
+own command sandbox, even though file reads work. Once this composition problem
+is established, use the host's approved execution path for the normal
+coordinator while preserving native sandboxing and permission decisions. Treat
+it as a caller invocation constraint, not a provider failure. If approval is
+unavailable, stop the dependent action; do not disable native protections or
+replay a consumed request under different permissions. The
+[package reference](../../plugins/agent-collab/README.md#routing-request)
+contains the invocation guidance.
+
 ## Troubleshoot
 
 | Symptom or status | Meaning | Safe response |
@@ -224,7 +236,7 @@ fall back to a retired provider-specific plugin.
 | Skill is missing | The package may not be installed, enabled, or loaded in this session. | Check host plugin inventory, then start a new session/task. |
 | `duplicate_blocked` or migration conflict | A retired package remains active or installed. | Run migration doctor, apply only its host-specific removal actions, and run it again. |
 | `unavailable` | The route, runtime, provider prerequisite, or observed readiness is not currently usable. | Run runtime status and migration doctor; check supported vendor authentication separately. Do not use a raw-provider fallback. |
-| Reviewer shares a required excluded family | The primary cannot count that output as independent governance evidence. | Select an eligible different family before dispatch or record the existing review as non-independent; the current routing wire does not enforce lineage exclusion. |
+| Reviewer shares a required excluded family | The primary cannot count that output as independent governance evidence. | Where independence is required, select an eligible different family before dispatch. Ordinary review may retain the output as advisory; the current routing wire does not enforce lineage exclusion. |
 | Reviewer or author lineage is unknown | The primary cannot establish governance independence. | Verify the actual model lineage and authorship; do not guess from a host nickname or installation path. |
 | `config_error` | Request fields, host identity, or route/action pairing violate the closed schema. | Use the installed skill/package reference; remove unsupported fields rather than widening the schema. |
 | `auth_error` or `quota_error` | The managed provider prerequisite failed after routing. | Use the provider's supported login/account interface or wait for quota. Keep the same authority. |
diff --git a/docs/architecture/project-estimation.md b/docs/architecture/project-estimation.md
index 3cdd2e05..a8aa58ab 100644
--- a/docs/architecture/project-estimation.md
+++ b/docs/architecture/project-estimation.md
@@ -19,7 +19,7 @@ consents to an output path.
 ## Current status
 
 The skill, helper, schemas, planning checkpoints, and release-verification
-source ship in the published v7.0.5 release. A governed, content-addressed
+source ship in the published v7.0.6 release. A governed, content-addressed
 bootstrap handoff is admitted from the frozen producer. It contains a supported
 enhancement duration hierarchy but no greenfield root and no published token,
 wait, rework, quota-delay, or marginal-cash metrics.
@@ -27,7 +27,7 @@ wait, rework, quota-delay, or marginal-cash metrics.
 This is production maintenance evidence in the explicit `bootstrap` state, not
 a promoted calibration claim. Its estimates are descriptive and never high
 confidence. The refreshed maintenance evidence is receipt-bound to the
-published 7.0.5 source; v6.2.0 remains the historical release that introduced
+published 7.0.6 source; v6.2.0 remains the historical release that introduced
 the bootstrap.
 
 ## Mental model
diff --git a/docs/architecture/repository-and-release.md b/docs/architecture/repository-and-release.md
index df0dad22..0d48f1c9 100644
--- a/docs/architecture/repository-and-release.md
+++ b/docs/architecture/repository-and-release.md
@@ -101,11 +101,11 @@ operator notification if still unsuccessful. Expired pricing becomes
 `unpriced`; expired quota becomes `unknown`. Structural, privacy, provenance,
 integrity, schema, and material-regression failures always block.
 
-The published v7.0.5 release admits the governed bootstrap aggregate,
+The published v7.0.6 release admits the governed bootstrap aggregate,
 pricing/quota snapshots, notification, and schema-3 receipt introduced in
 v6.2.0. The enhancement duration prior is descriptive; greenfield and
 unsupported metric families remain unavailable. The bootstrap is not promoted
-calibration; the refreshed maintenance evidence is receipt-bound to 7.0.5. See
+calibration; the refreshed maintenance evidence is receipt-bound to 7.0.6. See
 [Project estimation](project-estimation.md).
 
 ### Policy-only
diff --git a/docs/architecture/status-and-evidence.md b/docs/architecture/status-and-evidence.md
index ff02b8e0..3aa123f3 100644
--- a/docs/architecture/status-and-evidence.md
+++ b/docs/architecture/status-and-evidence.md
@@ -17,7 +17,47 @@ runtime. Each has a different evidence source.
 | Runtime readiness | Provider-free evidence that the selected package and managed boundary are callable for the reported contracts. | A guarantee that provider authentication, quota, or a future request will succeed. |
 | Invocation result | The typed outcome of one bounded request. | General availability, permission to retry with wider authority, or merge approval. |
 
-## Current snapshot — v7.0.5
+## Current snapshot — v7.0.6
+
+The [`v7.0.6` release](https://github.com/sumitake/agent-collab/releases/tag/v7.0.6) was published on
+2026-09-08 at 13:54:44 UTC.
+The signed annotated v7.0.6 tag object `849599dd73911635bc19bb58ed7a0c32a46d79b6` identifies public commit `fc8d66b3978dc1f2a177e9447b45915bb3486f84`.
+The [exact release workflow](https://github.com/sumitake/agent-collab/actions/runs/34234609927)
+succeeded; the release command compared all three published assets with its
+locally built canonical archive, checksum and SPDX evidence.
+
+| Published asset | Verified SHA-256 |
+| --- | --- |
+| `agent-collab.v7.0.6.plugin` | `b7928573b1e2e38af10baeadb97fdeb3fbab3b883e56be9cdbd3e7b12b3c4e4c` |
+| `agent-collab-v7.0.6.spdx.json` | `862607efcc0e33ed4c116e9e2b0b54eb65e7baff60c2fc2869b153ada3bf4a72` |
+| `agent-collab.v7.0.6.plugin.sha256` | `7d393dcec7042252a43a132c499e17469790066ab8dd36bad62f7872ef4be7a0` |
+
+| Observation | Status | Interpretation |
+| --- | --- | --- |
+| Package 7.0.6 retains signed runtime 5.0.7, manifest schema 4, protocol 5, native contract 4 and wire schema 12. All 86 runtime/manifest files are unchanged from 7.0.5. | verified release identity | No runtime rebuild or new provider capability is claimed. Both shipped macOS architectures passed release signature/notarization verification. |
+| The released manifest lists 12 logical actions, eight logical agents and two macOS architecture artifacts; the released package contains 53 generated skills. | verified current inventory | Legacy transport-action/source-pair counts in older snapshots describe those older protocols, not this routing-only interface. |
+| All released files match the observed supported local installations. | verified installed bytes | Supported managers performed the updates; no released file was excluded from comparison. Host-created metadata is outside the release inventory. |
+| Each observed installation returned provider-free planning decisions for all advertised intents with no dispatch results. JSON and text migration doctor reported READY, with no inventory errors or active legacy packages. Gemini was selected for repository-review planning. | verified planning from one control session | These checks used each installation from one current session. They do not prove fresh desktop-session loading, authentication or model inference on each host. |
+| Ordinary Gemini code review can proceed with same-family or unverified advisory labels when no eligible independent reviewer is available. Independent approval remains a caller-verified requirement where applicable. | released skill behavior | [PR #204](https://github.com/sumitake/agent-collab/pull/204) corrects the full generated instruction path. Gemini repository review was already admitted in 7.0.5; this is a caller-guidance correction. |
+| The source task obtained fresh Gemini repository-review and exact-commit governance results, with observed Google lineage and retained raw findings. | bounded prepublication execution evidence | These calls exercised the unchanged installed runtime before the content release; they are not new post-install carrier qualifications or permission to replay earlier attempts. |
+| Caller sandbox composition guidance preserves native permissions and normal capabilities. | released operational guidance | The demonstrated nested-sandbox problem is a caller invocation constraint, not a provider failure. |
+| One fresh Claude document-intent attempt returned an organization subscription-access denial; [#162](https://github.com/sumitake/agent-collab/issues/162) remains unresolved. | blocked inference qualification | No omitted Claude profile was qualified, no consumed case was replayed, and no billing or credential change was made. |
+
+The unchanged runtime retains its prior qualification history, recorded below.
+This content release did not repeat that matrix. Existing host conversations
+can retain an earlier skill catalog until a fresh session loads the update.
+
+### v7.0.6 closeout determinations
+
+| Surface | Determination | Evidence basis |
+| --- | --- | --- |
+| Root and package README | **updated** | One 7.0.6 showcase, published state, advisory-review behavior and installed-versus-loaded limits match the release evidence. |
+| Architecture handbook | **updated** | Current-release references, review/intent/delegation explanations, Antigravity support, caller sandbox guidance and Claude access status align with released source. |
+| Runtime and inventory | **verified current** | Runtime 5.0.7, schemas/protocol, 12 actions, eight agents, two architectures and 53 skills come from the released manifest/package. Older snapshot counts remain historical. |
+| Project-estimation maintenance | **updated** | The verified receipt is bound to 7.0.6; the prior remains bootstrap/last-good and unknown quotas remain unknown. No promoted calibration is claimed. |
+| Generated changelog | **verified current at the signed tag** | [PR #206](https://github.com/sumitake/agent-collab/pull/206) compiled the exact version section; the published notes contain it unchanged after the workflow's standard preamble. This closeout adds a fragment without editing signed history. |
+
+## Historical snapshot — v7.0.5
 
 The [`v7.0.5` release](https://github.com/sumitake/agent-collab/releases/tag/v7.0.5)
 was published on 2026-09-08 UTC.
@@ -86,7 +126,7 @@ readiness remain host-specific evidence planes.
 
 The public [`v7.0.1` release](https://github.com/sumitake/agent-collab/releases/tag/v7.0.1)
 is published and its immutable release workflow succeeded. It is retained as a
-dated snapshot; v7.0.5 is the current published release.
+dated snapshot; see the current snapshot above for the latest published release.
 
 | Observation | Status | Interpretation |
 | --- | --- | --- |
diff --git a/plugins/agent-collab/README.md b/plugins/agent-collab/README.md
index a4909e7f..154e10f1 100644
--- a/plugins/agent-collab/README.md
+++ b/plugins/agent-collab/README.md
@@ -8,8 +8,8 @@ interpreted by the calling agent with ordinary reasoning.
 
 Current repository source: **7.0.6**
 
-Current published release: **7.0.5**
-([`v7.0.5`](https://github.com/sumitake/agent-collab/releases/tag/v7.0.5)); it
+Current published release: **7.0.6**
+([`v7.0.6`](https://github.com/sumitake/agent-collab/releases/tag/v7.0.6)); it
 carries signed provider runtime `5.0.7`. Host installation, readiness, and
 provider availability remain separate evidence planes.
 
@@ -24,15 +24,17 @@ partial remains available to the caller.
 The 7.0.6 content update corrects reviewer-independence instructions: the caller
 establishes the primary and artifact-author families, checks an eligible
 reviewer before dispatch, and verifies observed lineage before accepting
-independent evidence. Routing does not perform that check. Publication and host
-refresh for 7.0.6 are pending.
+independent evidence. Routing does not perform that check. Version 7.0.6 is
+published; the dated status snapshot records verified installed bytes and
+provider-free planning separately from fresh host-session loading or inference.
 
 The 7.0.5 release restored migration-doctor reports for this descriptor
 and retains bounded opaque native output when final-answer extraction finds no
 text, including bytes observed during completion and cleanup. Native execution
 status remains separate from retained content, which the caller interprets.
 The dated status snapshot records host verification and the explicit Claude
-subscription/live-qualification deferral.
+subscription/live-qualification deferral for that release and the later
+7.0.6 task's observed subscription-access denial.
 
 General users should start with the public
 [architecture handbook](../../docs/architecture/README.md) and