devrites 7.2.8 → 7.3.0

package/pack/.claude/skills/rite-review/reference/feature-scoped-review.md

@@ -1,7 +1,7 @@
 # Feature-scoped review
 
-The review boundary is the **active feature**: the files in `touched-files.md` and the
-current diff. This is a hard rule, not a guideline.
+The review boundary is the **selected source feature** per [phase target binding](../../devrites-lib/reference/parallel-workspaces.md#phase-target-binding):
+its `touched-files.md` and current diff. This is a hard rule, not a guideline.
 
 ## In scope
 - Code added/changed by this feature.

package/pack/.claude/skills/rite-seal/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[feature-slug] [--full]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/candidate-integrity.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/verification-methods.md","rite-seal/reference/phase-contract.md","rite-seal/reference/final-evidence.md","rite-seal/reference/go-no-go.md","rite-seal/reference/risk-and-rollback.md","rite-seal/reference/seal-template.md","rite-seal/reference/output.md","rite-seal/reference/anti-patterns.md"],"triggers":{"agents":["devrites-lib/reference/standards/agents.md"],"browser":["devrites-lib/reference/standards/browser-proof-checklist.md"],"code-review":["devrites-lib/reference/standards/code-review.md"],"deprecation":["devrites-lib/reference/standards/deprecation.md"],"documentation":["devrites-lib/reference/standards/documentation.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"observability":["devrites-lib/reference/standards/observability.md"],"principles":["devrites-lib/reference/standards/principles.md"],"security":["devrites-lib/reference/standards/security.md"],"testing":["devrites-lib/reference/standards/testing.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","evidence.md","touched-files.md","review.md","seal.md"],"workspaceByRole":{"code-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","architecture.md","decisions.md","state.md","evidence.md","touched-files.md","review.md"],"devex-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","devex.md","review.md"],"doubt-reviewer":["spec.md","plan.md","tasks.md","state.md","decisions.md","review.md"],"frontend-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","review.md"],"performance-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","review.md"],"proof-runner":["spec.md","test-plan.md","tasks.md","gates.md","evidence.md","state.md"],"security-auditor":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","review.md"],"simplifier-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","review.md"],"spec-reviewer":["brief.md","spec.md","decision-coverage.md","questions.md","decisions.md","assumptions.md","state.md","review.md"],"test-analyst":["spec.md","tasks.md","test-plan.md","state.md","evidence.md","review.md"]},"rootOnly":["devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/candidate-integrity.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/verification-methods.md","rite-seal/reference/phase-contract.md","rite-seal/reference/final-evidence.md","rite-seal/reference/go-no-go.md","rite-seal/reference/risk-and-rollback.md","rite-seal/reference/seal-template.md","rite-seal/reference/output.md","rite-seal/reference/anti-patterns.md"],"triggers":{"agents":["devrites-lib/reference/standards/agents.md"],"browser":["devrites-lib/reference/standards/browser-proof-checklist.md"],"code-review":["devrites-lib/reference/standards/code-review.md"],"deprecation":["devrites-lib/reference/standards/deprecation.md"],"documentation":["devrites-lib/reference/standards/documentation.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"observability":["devrites-lib/reference/standards/observability.md"],"principles":["devrites-lib/reference/standards/principles.md"],"security":["devrites-lib/reference/standards/security.md"],"testing":["devrites-lib/reference/standards/testing.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","evidence.md","touched-files.md","review.md","seal.md"],"workspaceByRole":{"code-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","architecture.md","decisions.md","state.md","evidence.md","touched-files.md","review.md"],"devex-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","devex.md","review.md"],"doubt-reviewer":["spec.md","plan.md","tasks.md","state.md","decisions.md","review.md"],"frontend-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","review.md"],"performance-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","review.md"],"proof-runner":["spec.md","test-plan.md","tasks.md","gates.md","evidence.md","state.md"],"security-auditor":["spec.md","plan.md","tasks.md","state.md","touched-files.md","evidence.md","review.md"],"simplifier-reviewer":["spec.md","plan.md","tasks.md","state.md","touched-files.md","review.md"],"spec-reviewer":["brief.md","spec.md","decision-coverage.md","questions.md","decisions.md","assumptions.md","state.md","review.md"],"test-analyst":["spec.md","tasks.md","test-plan.md","state.md","evidence.md","review.md"]},"rootOnly":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md"]} -->
 > Read-set manifest: `devrites-engine context <slug> --phase seal` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 

package/pack/.claude/skills/rite-seal/reference/phase-contract.md

@@ -1,6 +1,6 @@
 # rite-seal phase contract
 
-1. **Read.** Resolve the explicit slug or `.devrites/ACTIVE`, require its
+1. **Read.** Resolve source per [phase target binding](../../devrites-lib/reference/parallel-workspaces.md#phase-target-binding), require its
    `state.md`, then read required workspace artifacts, conditional
    browser/design/devex evidence, and final diff.
 2. **Recheck identity and real proof.** Run

package/pack/.claude/skills/rite-ship/SKILL.md

@@ -5,13 +5,13 @@ argument-hint: "[feature-slug]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/candidate-integrity.md","devrites-lib/reference/standards/git-workflow.md","devrites-lib/reference/standards/definition-of-done.md","devrites-lib/reference/standards/release/ship-checklist.md","rite-ship/reference/git-ship.md","rite-ship/reference/rollout.md","rite-ship/reference/close-out.md","rite-ship/reference/ship-template.md","rite-ship/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","evidence.md","touched-files.md","review.md","seal.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/core.md","devrites-lib/reference/candidate-integrity.md","devrites-lib/reference/standards/git-workflow.md","devrites-lib/reference/standards/definition-of-done.md","devrites-lib/reference/standards/release/ship-checklist.md","rite-ship/reference/git-ship.md","rite-ship/reference/rollout.md","rite-ship/reference/close-out.md","rite-ship/reference/ship-template.md","rite-ship/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md","evidence.md","touched-files.md","review.md","seal.md"],"rootOnly":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/afk-hitl.md"]} -->
 > Read-set manifest: `devrites-engine context <slug> --phase ship` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
 # /rite-ship: ship + close the task
 
-`/rite-seal` decides; `/rite-ship` mutates Git and closes. Read the active workspace;
+`/rite-seal` decides; `/rite-ship` mutates Git and closes. Read the source workspace per [phase target binding](../devrites-lib/reference/parallel-workspaces.md#phase-target-binding);
 if absent, route to `/rite-spec <feature>`. Ship only with current **GO** in `seal.md`.
 
 ## Rules consulted (read on demand from `.claude/skills/devrites-lib/reference/standards/`)

package/pack/.claude/skills/rite-ship/reference/git-ship.md

@@ -12,7 +12,7 @@ Acceptance criteria proven: <n / total>
 Branch:   <target branch>
 Candidate paths: <exact project-relative paths>
 Checkpoint collapse: <exact `git reset --soft '<merge-base>'` command | skip>
-Collapse slugs: <active slug plus every recorded sequence slug in the range | n/a>
+Collapse slugs: <selected source slug plus every recorded sequence slug in the range | n/a>
 Stage plan: <exact argv-safe `git add -- '<path>'` command for every manifest row>
 Commit:   <exact git commit command>
 Push:     <exact git push command | skip>
@@ -47,7 +47,7 @@ Pre-GO is read-only. Do not run the disclosed collapse or staging commands.
 1. **Analyze checkpoint history without mutating it.** Read the upstream, merge
    base, commit OIDs, and full subjects. If no checkpoint commit exists, disclose
    `skip`. A collapse is eligible only when every commit in its range has the exact
-   `WIP(<slug>):` prefix for the validated active slug — or, for a release ship of a
+   `WIP(<slug>):` prefix for the validated source slug — or, for a release ship of a
    deferred-ship sequence, for a slug recorded in the parent's `decisions.md`
    sequence whose workspace is sealed in this run
    ([afk-hitl.md § Sequence continuation](../../devrites-lib/reference/standards/afk-hitl.md#sequence-continuation-continue_sequence-max_workspaces));

package/pack/.claude/skills/rite-spec/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "<feature or idea>"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/standards/elicitation.md","devrites-lib/reference/standards/agents.md","rite-spec/reference/investigation.md","rite-spec/reference/question-protocol.md","rite-spec/reference/spec-template.md","rite-spec/reference/spec-checklists.md","rite-spec/reference/state-workspace.md","rite-spec/reference/acceptance-criteria.md","rite-spec/reference/interview-patterns.md","rite-spec/reference/ai-spec-template.md","rite-spec/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"documentation":["devrites-lib/reference/standards/documentation.md"],"edge-cases":["devrites-lib/reference/standards/edge-case-trace.md"],"frontend":["rite-build/reference/frontend-trigger.md"],"grammar":["devrites-lib/reference/standards/spec-grammar.md"],"principles":["devrites-lib/reference/standards/principles.md"],"references":["rite-spec/reference/references-intake.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md"],"workspaceByRole":{"evidence-scout":["brief.md","spec.md","state.md","questions.md"]},"rootOnly":["devrites-lib/reference/standards/code-index.md","devrites-lib/reference/standards/afk-hitl.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/standards/elicitation.md","devrites-lib/reference/standards/agents.md","rite-spec/reference/investigation.md","rite-spec/reference/question-protocol.md","rite-spec/reference/spec-template.md","rite-spec/reference/spec-checklists.md","rite-spec/reference/state-workspace.md","rite-spec/reference/acceptance-criteria.md","rite-spec/reference/interview-patterns.md","rite-spec/reference/ai-spec-template.md","rite-spec/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"documentation":["devrites-lib/reference/standards/documentation.md"],"edge-cases":["devrites-lib/reference/standards/edge-case-trace.md"],"frontend":["rite-build/reference/frontend-trigger.md"],"grammar":["devrites-lib/reference/standards/spec-grammar.md"],"principles":["devrites-lib/reference/standards/principles.md"],"references":["rite-spec/reference/references-intake.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md"],"workspaceByRole":{"evidence-scout":["brief.md","spec.md","state.md","questions.md"]},"rootOnly":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/standards/afk-hitl.md"]} -->
 > Read-set manifest: `devrites-engine context <slug> --phase spec` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -38,7 +38,7 @@ load a routed standard to discover required behavior, not to prescribe implement
   [`elicitation.md`](../devrites-lib/reference/standards/elicitation.md) before continuing.
 
 ## Workflow
-0. Read core; if `.devrites/ACTIVE` exists, require its `state.md`.
+0. Read core; apply shared [phase target binding](../devrites-lib/reference/parallel-workspaces.md#phase-target-binding). If `.devrites/ACTIVE` exists, require its owner's `state.md`; it is not the target when the controller explicitly prepares a recorded future continuation.
 0a. **Adoption check.** For a never-adopted existing codebase, route first to
    `/rite-adopt` with `$ARGUMENTS`; it derives baseline spec/principles. HITL
    offers ranked adopt-first and spec-only choices; permitted AFK adopts.
@@ -123,9 +123,12 @@ load a routed standard to discover required behavior, not to prescribe implement
    product/acceptance ambiguity, irreversible/external approval, or human-only access. Record
    owned prerequisites. Keep a build checkpoint only for unavailable pre-code evidence or a
    mandatory action-time approval. **Completion:** no foreseeable human choice is deferred.
-5. **Create or update the workspace** + set `.devrites/ACTIVE` from
-   [state-workspace](reference/state-workspace.md); a `--lookahead` run
-   leaves `.devrites/ACTIVE` unchanged. If the slug already exists,
+5. **Create or update the workspace** per
+   [state-workspace](reference/state-workspace.md). Ordinary standalone Spec sets
+   `.devrites/ACTIVE`; explicit `--lookahead` and main-controller preparation of
+   an authorized recorded future continuation preserve the ordered owner's ACTIVE.
+   Pass the target slug explicitly to every phase; no new flag or global workspace
+   override. If the slug already exists,
    update the existing workspace rather than overwrite it; preserve history and
    unrelated settled content. Write every required artifact and conditional
    annex exactly from [spec-template](reference/spec-template.md)

package/pack/.claude/skills/rite-spec/reference/state-workspace.md

@@ -66,6 +66,11 @@ Before any HTML:
 - Create or reuse the slug exactly under the canonical schema's
   [Slug identity](../../devrites-lib/reference/workspace-artifact-schema.md#slug-identity)
   contract.
+- Standalone Spec sets ACTIVE to its target. Explicit lookahead and the existing
+  Autocomplete controller's recorded-future preparation leave ACTIVE on the
+  ordered owner; pass source slug explicitly, preserve claims and opening budget,
+  and use the shared [controller workflow](../../devrites-lib/reference/parallel-workspaces.md).
+  A new directory alone never authorizes future enrollment.
 - `/rite-spec` creates the workspace map, `brief.md`, `spec.md`, `decisions.md`,
   `assumptions.md`, `questions.md`, `state.md`, optional `references.md` /
   `references/`, optional `flows.md` when a diagram already clarifies investigation,

package/pack/.claude/skills/rite-temper/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[feature-slug] [--mode expand|selective|hold-rigor|reduce-to-MVP
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/agents.md","rite-temper/reference/significance.md","rite-temper/reference/scope-modes.md","rite-temper/reference/review-dimensions.md","rite-temper/reference/strategy-template.md","rite-temper/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"documentation":["devrites-lib/reference/standards/documentation.md"],"elicitation":["devrites-lib/reference/standards/elicitation.md"],"yagni":["devrites-lib/reference/standards/patterns.md","devrites-lib/reference/standards/coding-style.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","strategy.md","design-brief.md"],"workspaceByRole":{"strategy-reviewer":["brief.md","spec.md","decision-coverage.md","decisions.md","strategy.md","state.md"]},"rootOnly":["devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/afk-hitl.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/agents.md","rite-temper/reference/significance.md","rite-temper/reference/scope-modes.md","rite-temper/reference/review-dimensions.md","rite-temper/reference/strategy-template.md","rite-temper/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"documentation":["devrites-lib/reference/standards/documentation.md"],"elicitation":["devrites-lib/reference/standards/elicitation.md"],"yagni":["devrites-lib/reference/standards/patterns.md","devrites-lib/reference/standards/coding-style.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","strategy.md","design-brief.md"],"workspaceByRole":{"strategy-reviewer":["brief.md","spec.md","decision-coverage.md","decisions.md","strategy.md","state.md"]},"rootOnly":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/afk-hitl.md"]} -->
 > Read-set manifest: `devrites-engine context <slug> --phase temper` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -14,7 +14,7 @@ user-invocable: true
 Review readied spec ambition, scope, pre-mortem risk, and excess surface. Fold
 accepted decisions into the canonical contract before `/rite-define`. Optional for
 small work; skips low-stakes specs; `/rite-autocomplete` always invokes it.
-**Read active workspace first**; no readied `spec.md` → `/rite-spec`. Depth follows
+**Read the selected source workspace first**; no readied `spec.md` → `/rite-spec`. Depth follows
 [`devrites-lib/reference/orchestration-profiles.md`](../devrites-lib/reference/orchestration-profiles.md);
 the required exact strategy reviewer never changes with profile.
 
@@ -49,7 +49,7 @@ the spec applicability map triggers that risk family.
 
 ## Workflow
 0. **Read `.claude/skills/devrites-lib/reference/standards/core.md`**, then
-   resolve the active slug, require its `state.md`, and read the cursor directly.
+   resolve source per [phase target binding](../devrites-lib/reference/parallel-workspaces.md#phase-target-binding), require its `state.md`, and read the cursor directly.
    Then read the workspace: `spec.md`, `decision-coverage.md` (+ `decisions.md`,
    `assumptions.md`, `design-brief.md` if UI), `state.md`. Require `state.md` `spec_gate: passed` (legacy `Spec gate:` accepted): else
    STOP → `/rite-spec`. Require `Decision coverage: CLEAR`: else STOP →

package/pack/.claude/skills/rite-vet/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[slug] [--cross-model] [--full]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/gates.md","rite-vet/reference/review-axes.md","rite-vet/reference/artifacts.md","rite-vet/reference/depth.md","rite-vet/reference/eng-lenses.md","rite-vet/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"assumption-delta":["devrites-lib/reference/standards/assumption-checkpoints.md"],"cross-model":["rite-vet/reference/cross-model.md"],"devex":["devrites-lib/reference/standards/developer-experience.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"elicitation":["devrites-lib/reference/standards/elicitation.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"grammar":["devrites-lib/reference/standards/spec-grammar.md"],"one-shot":["devrites-lib/reference/standards/one-shot-actions.md"],"performance":["devrites-lib/reference/standards/performance.md"],"principles":["devrites-lib/reference/standards/principles.md"],"reslice":["devrites-lib/reference/standards/acceptance-preserving-reslice.md"],"testing":["devrites-lib/reference/standards/testing.md"],"workflow":["devrites-lib/reference/standards/development-workflow.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"yagni":["devrites-lib/reference/standards/patterns.md","devrites-lib/reference/standards/coding-style.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","strategy.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md"],"rootOnly":["devrites-lib/reference/standards/code-index.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/elicitation.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/workflow-artifacts.md"],"workspaceByRole":{"doubt-reviewer":["spec.md","architecture.md","plan.md","tasks.md","test-plan.md","decisions.md","state.md"],"devex-reviewer":["spec.md","plan.md","tasks.md","decisions.md","state.md"],"plan-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","decision-coverage.md","architecture.md","decisions.md","state.md"],"strategy-reviewer":["brief.md","spec.md","plan.md","decisions.md","decision-coverage.md","strategy.md","state.md"]}} -->
+<!-- loads: {"always":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/code-navigation.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/gates.md","rite-vet/reference/review-axes.md","rite-vet/reference/artifacts.md","rite-vet/reference/depth.md","rite-vet/reference/eng-lenses.md","rite-vet/reference/anti-patterns.md"],"triggers":{"afk":["devrites-lib/reference/standards/afk-hitl.md"],"applicability":["devrites-lib/reference/standards/repository-topology.md","devrites-lib/reference/standards/data-integrity.md","devrites-lib/reference/standards/integration-reliability.md"],"assumption-delta":["devrites-lib/reference/standards/assumption-checkpoints.md"],"cross-model":["rite-vet/reference/cross-model.md"],"devex":["devrites-lib/reference/standards/developer-experience.md"],"dod":["devrites-lib/reference/standards/definition-of-done.md"],"elicitation":["devrites-lib/reference/standards/elicitation.md"],"errors":["devrites-lib/reference/standards/error-handling.md"],"grammar":["devrites-lib/reference/standards/spec-grammar.md"],"one-shot":["devrites-lib/reference/standards/one-shot-actions.md"],"performance":["devrites-lib/reference/standards/performance.md"],"principles":["devrites-lib/reference/standards/principles.md"],"reslice":["devrites-lib/reference/standards/acceptance-preserving-reslice.md"],"testing":["devrites-lib/reference/standards/testing.md"],"workflow":["devrites-lib/reference/standards/development-workflow.md"],"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"yagni":["devrites-lib/reference/standards/patterns.md","devrites-lib/reference/standards/coding-style.md"]},"workspace":["brief.md","spec.md","state.md","decisions.md","assumptions.md","questions.md","decision-coverage.md","strategy.md","architecture.md","plan.md","tasks.md","traceability.md","eng-review.md","test-plan.md","gates.md"],"rootOnly":["devrites-lib/reference/parallel-workspaces.md","devrites-lib/reference/standards/code-index.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/elicitation.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/parallel-dispatch.md","devrites-lib/reference/standards/workflow-artifacts.md"],"workspaceByRole":{"doubt-reviewer":["spec.md","architecture.md","plan.md","tasks.md","test-plan.md","decisions.md","state.md"],"devex-reviewer":["spec.md","plan.md","tasks.md","decisions.md","state.md"],"plan-reviewer":["spec.md","plan.md","tasks.md","test-plan.md","decision-coverage.md","architecture.md","decisions.md","state.md"],"strategy-reviewer":["brief.md","spec.md","plan.md","decisions.md","decision-coverage.md","strategy.md","state.md"]}} -->
 > Read-set manifest: `devrites-engine context <slug> --phase vet` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -71,7 +71,7 @@ plan declares a root-authored executable workflow file, read
 <!-- workflow-artifact-adapter: {"module":"devrites-lib/reference/standards/workflow-artifacts.md","entry":"plan declares root-authored executable workflow file","action":"emit exact admission; stale/missing authority uses PLAN_VET_REPAIR","return":"Vet READY cursor or exact technical replan"} -->
 ## Workflow
 
-0. **Orient.** Read core. Resolve active slug, require state, and read plan,
+0. **Orient.** Read core. Resolve source per [phase target binding](../devrites-lib/reference/parallel-workspaces.md#phase-target-binding), require state, and read plan,
    tasks, spec, decision coverage, optional strategy/design brief, decisions,
    assumptions, and state. Require approved Plan and `Decision coverage: CLEAR`;
    otherwise stop for Define or Clarify. Check placement (`get_architecture`),
@@ -219,9 +219,13 @@ plan declares a root-authored executable workflow file, read
    READY needs each to pass (fix failures in `/rite-plan`). READY also needs every
    unbuilt slice's write set closed against the live tree (plan-reviewer
    dimension 6), so frontier gaps fold in one Plan repair, not one per slice; an
-   affected recheck also closes every unbuilt slice and never defers a closure row. A `sequence_lookahead: yes` workspace also records one
-   `Predecessor readiness: <predecessor> <digest>` line from the predecessor's
-   `--emit-binding` hex; readiness re-checks it. Record the per-input drift baseline alongside it:
+   affected recheck also closes every unbuilt slice and never defers a closure row.
+   A future sequence workspace prepared by lookahead or the main controller records
+   `Predecessor readiness: <predecessor> <digest>` from the predecessor's
+   `--emit-binding` hex; readiness re-checks it. Apply the native dependency-safety
+   axis to its explicit workspace declarations before early admission; stale
+   assumptions need affected re-Vet, never automatic rebinding.
+   Record the per-input drift baseline alongside it:
    `devrites-engine check drift <slug> --record` — a later stale binding then
    names the exact artifact that moved instead of "something changed". An `ADVISORY
    proportion:` line names a slice whose proof outgrew its ACs: move its rows without a

package/pack/.claude/skills/rite-vet/reference/review-axes.md

@@ -29,6 +29,8 @@ Before implementation review, check for work beyond the settled spec.
    `Budget override`: route to `/rite-plan course-correct` (`MVP cut`) with the
    continuation sequence named; do not vet the whole epic. An `ADVISORY size:`
    or `hub:` line without its rationale is a non-blocking Suggestion to split or seam it.
+   Before READY, apply the shared [serialization audit](../../devrites-lib/reference/parallel-workspaces.md#recover-avoidable-serialization):
+   verify independent cuts and retained producer/proof/authority gates, or the concrete serial rationale.
 4. **Built-in check.** For each new pattern/infra/concurrency approach, invoke
    `devrites-source-driven` inline to verify current framework/runtime support and cite it. Custom
    work where a built-in suffices is a scope-reduction finding.
@@ -195,11 +197,16 @@ Use standard `AskUserQuestion`:
 3. **Failure-mode table:** per new codepath: realistic failure, partial/unknown effect,
    recovery owner, test, handling, and user-visible/silent result. No test + no handling +
    silent = **Critical** (`artifacts.md`).
-4. **Dependency safety:** verify graph/order and shared file/state/contract/lock/port/queue/env
-   conflicts. Each `Dependencies` edge must genuinely gate its slice (consumes an
-   output, interface, or state the predecessor produces); remove an ordering-only
-   edge, since it silently shrinks the parallel set. Correct the plan; native host
-   scheduling needs no lane artifact.
+4. **Dependency safety:** verify local and qualified workspace graph/order,
+   assumptions, consumed interfaces, shared file/state/contract/lock/port/queue/env
+   conflicts and independent proof. Verify Plan's explicit `Workspace dependencies`
+   for each future-admission slice under the
+   [canonical grammar](../../devrites-lib/reference/workspace-artifact-schema.md#canonical-slice-grammar);
+   `none` needs native judgment, not disjoint-path inference. Real producer edges
+   remain until durably BUILT/integrated; green unlanded work is not a producer
+   checkpoint. Remove ordering-only edges, never genuine interface/runtime/proof
+   dependencies. Missing legacy future declarations route narrow Plan repair/Vet;
+   current local execution stays compatible. Native scheduling needs no lane artifact.
 5. **Build-entry preflight:** commands/cwds, tools, package state, parser/browser smoke,
    prerequisites, and provenance ([`artifacts.md`](artifacts.md)).
 6. **Implementation readiness:** goal-backward coverage, wiring, dependency simulation,

package/pack/generated/claude/agents/devrites-proof-runner.md

@@ -32,8 +32,8 @@ and only the orchestrator-supplied changed paths.
    contradictory, whose output and exit come from different executions, whose
    command masks status, or whose exit and output disagree. A pass after a failed
    attempt on an unchanged digest is `flaky`: `fail` for its AC.
-2. Confirm every log, screenshot, trace, and result belongs to the supplied
-   candidate.
+2. Confirm proof belongs to the supplied candidate, except explicitly scoped
+   reuse backed by unchanged declared inputs and a valid executed origin.
 3. Map real REQ/AC/scenario/link IDs **and meaning** to observed proof. Invented/
    label-only maps or internal proof of an external outcome fail. Behavior MUST
    be positive, discriminating; reject skipped/focused/filtered/pending, zero-test,
@@ -55,13 +55,20 @@ and only the orchestrator-supplied changed paths.
    named blocker, never a pass. Otherwise use `cannot_verify`.
 8. A manual gate whose `gates.md` note lacks the human's own words or source, is a
    placeholder, or was runnable at Vet is `cannot_verify` ([`gates.md`](../skills/devrites-lib/reference/standards/gates.md)).
-9. An engine transcript (`DEVRITES-GATE-TRANSCRIPT v1` under `references/gates/`)
-   is immutable proof of its COMMAND, CWD, ATTEMPT, EXIT and output for the
-   candidate in CANDIDATE_BEFORE/AFTER. A `-reused.log` proves a gate for the
-   current candidate only when its INPUTS_SHA256 equals that of the gate's latest
-   executed, passing transcript.
-10. Recheck supplied before/after candidate identities. A mismatch or unexpected
-   repository mutation fails the side-effect boundary.
+9. An engine transcript (`DEVRITES-GATE-TRANSCRIPT v2` under `references/gates/`)
+   records one execution, not an assertion that proof is sufficient. Verify its
+   `TRANSCRIPT_SHA256` over all bytes before that footer; match the definition,
+   original output identity/byte count, declared inputs, EXIT and EXPECT verdict
+   against current ledger evidence and approved commands. Metadata and output may
+   be redacted; never hash the redacted body as the original output.
+   Reuse cites the unchanged executed origin path and its historical candidate
+   labels, with matching current `INPUTS_SHA256` and bounded dependency closure.
+   A legacy v1 or `-reused.log` alone cannot authorize reuse; request engine
+   `gates run`/`reverify --transcripts` to recover approved missing origins.
+10. Before/after identities must match within the recorded execution.
+    Historical/current candidate differences need the scoped reuse justification
+    above; never relabel an old observation. Unexpected repository mutation fails
+    the side-effect boundary.
 
 ## Rules
 

package/pack/generated/claude/skills/devrites-lib/SKILL.md

@@ -37,6 +37,8 @@ lifecycle state from chat or optional `README.md`.
   ([`workspace-artifact-schema.md`](reference/workspace-artifact-schema.md)).
 - [`reference/reply-contract.md`](reference/reply-contract.md): compact user-facing
   completion states. The host renders the response normally.
+- [`reference/parallel-workspaces.md`](reference/parallel-workspaces.md): explicit
+  phase targets, one isolated global controller, and source-owned proof.
 - [`reference/visual-playbooks/index.md`](reference/visual-playbooks/index.md): progressive
   visual HTML playbook router (load matching ids only; dual-read outline).
 

package/pack/generated/claude/skills/devrites-lib/reference/candidate-integrity.md

@@ -29,9 +29,13 @@ Same-candidate accounts may be cited when permitted. Corrections require
 new candidate checks, affected real proof and fresh affected exact reviewers for
 all open findings and dependency/regression closure, including newly triggered roles.
 After an all-met acceptance ledger has been executed, any candidate digest change
-requires `devrites-engine gates reverify <slug>` against the corrected frozen
-candidate before refreshed evidence or review bindings are written; ordinary
-`gates run` skips already-met rows and cannot refresh them.
+requires `devrites-engine gates reverify <slug> --transcripts` against the corrected
+frozen candidate before refreshed evidence or review bindings are written.
+Unchanged declared `INPUTS` may reuse complete passing originating transcripts;
+missing origins rerun only affected approved checks. Reuse is not execution.
+If non-file prerequisites changed or prior proof is doubtful, invalidate affected
+automatic evidence through the workspace's single-writer protocol before rerun.
+Ordinary `gates run` skips already-met rows and cannot refresh them.
 Changed contracts or uncertain closure require a full applicable pass.
 Unchanged sub-scope needs explicit unchanged-input/dependency justification and a
 link to original evidence. Never relabel an old candidate-bound account.

package/pack/generated/claude/skills/devrites-lib/reference/parallel-dispatch.md

@@ -45,6 +45,9 @@ If the candidate diff has no matching surfaces, record
    `proof-runner`, keep their own) with `devrites-engine packet <slug> --wave <w> --phase <p>
    --role <role> [--slice <SLICE-ID>] [--focus <file>]`: it names the bundle and frozen
    diff by reference, copies the digests, and runs the `open` lints. Build roles add `--slice <SLICE-ID>` (slice-scoped, slice-named bundle).
+   Packet rendering and dispatch verify each named diff's recorded SHA-256.
+   Manually authored `.diff`/`.patch` packets need explicit
+   `diff <64hex> <path>` binding rows too; an unbound diff is refused.
    Evaluate the skill's trigger conditions and pass each that fires — a role's
    Trigger column maps to the phase manifest's names: `security-auditor` →
    `security`; at Review, `frontend-reviewer` → `ui` and `performance-reviewer` →

package/pack/generated/claude/skills/devrites-lib/reference/parallel-workspaces.md

@@ -0,0 +1,202 @@
+# One controller, multiple workspace sources
+
+> Root-only: not inlined in --role bundles. Every phase uses target binding below;
+> Autocomplete owns the global workflow. Standalone Build stays source-local.
+
+## Phase target binding
+
+For every lifecycle phase and cold handoff, resolve the existing explicit target
+or caller-supplied SOURCE slug first; use `.devrites/ACTIVE` only when neither is
+supplied. All workspace context, cursor, questions, artifact reads/writes, approval,
+candidate bindings and proof belong to that source. A missing source artifact
+routes its prerequisite; it never falls back to another workspace's artifacts.
+An explicit valid workspace does not require ACTIVE to name it or to exist.
+
+Carry that source through Spec → Clarify → Temper → Define/Plan → Vet and later
+Build/Converge/Prove/Polish/Review/Seal/Ship entrypoints. Use existing slug arguments
+where supported, including `context <source>` and `handoff <source> --resume`.
+For qid-only `state resolve` (including `--drop`/`--batch`), keep its existing argv
+and bind the call with `DEVRITES_ROOT=<absolute-control>/.devrites` and
+`DEVRITES_WORKSPACE=<absolute-control>/.devrites/work/<source>`. The override is a
+workspace path, not a slug. Apply this environment only to that invocation;
+neither a fabricated resolver slug argument nor process-global environment
+mutation is routing. Use the same source binding for nested recommended answers.
+
+Preparing or running an admitted future source preserves the ordered owner's
+ACTIVE and retained writer/controller. Ordinary standalone Spec still sets ACTIVE;
+explicit `--lookahead` still stops at planning/Vet and never becomes a Build root.
+Target binding changes neither phase approval nor Ship authority.
+
+## Authority and admission
+
+Resolve one controlling root and ordered lifecycle owner. `.devrites/ACTIVE` stays
+on that owner until normal sequence handoff; scheduling a future slice does not
+advance ACTIVE or create a second Build root. One repository-global lease owns
+control-tip mutations. Resume its controller, source identities and retained
+handles before admitting more work; status queried via ACTIVE/source reports the
+actual retained controller even after ordered handoff. Another retained
+controller is not bypassable; no extra cursor pointer is needed.
+
+The existing `--parallel N` is one global active-writer cap across all sources:
+explicit invocation value, else AFK `max_parallel`, else retained lease capacity
+on resume, else 10. Explicit 1 means one writer, not one writer per workspace.
+Review queues obey host capacity and existing reviewer caps separately; they never
+erase required specialist accounts.
+
+Discover only recorded forward sequence continuations through `sequence_parent`
+and the parent's recorded objectives. Honor `continue_sequence: false`, opening
+budget and human bounded requests. Charge each opening once; reuse prepared
+children and their cursor rather than re-specifying or charging them again.
+An unrelated directory or user-mentioned slug is not automatic enrollment.
+Respect workspace claims: a live lookahead owner retains its artifacts until
+release/terminal reconciliation. Root alone writes workspace artifacts; leaves
+never write `.devrites/**`.
+
+For each future slice, native Plan/Vet must have CURRENT approved readiness,
+a complete bound contract and explicit `Workspace dependencies` under
+[canonical slice grammar](workspace-artifact-schema.md#canonical-slice-grammar).
+Plan/Vet checks assumptions, consumed interfaces, shared runtime resources and
+independent slice proof. `none` is a native declaration, never an inference from
+path disjointness, local `Dependencies: none`, planning digests or a green branch.
+Only durably BUILT/integrated producer checkpoints satisfy qualified dependencies;
+validate each producer reference and graph, including safely archived predecessors.
+Cycles, unknown/malformed references and shared unisolated runtime withhold unsafe
+candidates. A waiting producer withholds only its consumers, not unrelated work.
+
+Missing declarations in legacy future plans need narrow Plan repair + affected
+Vet before early admission; existing local/standalone plans remain valid. Absent,
+incomplete, stale or human-blocked future work is a planning/repair/blocked
+opportunity, not a fatal pool failure. Retain every readiness reason: fixing stale
+bindings does not waive a coexisting human/access/safety gate. Re-Vet affected
+predecessor assumptions, then record current bindings; never auto-refresh a digest.
+
+## Recover avoidable serialization
+
+At native Plan/Vet, and when a full global scan leaves writer capacity unused,
+audit the remaining frontier before treating serialization as irreducible:
+
+1. Name what each edge consumes: product/interface, integration evidence, shared
+   writable path, runtime resource or explicit authority. Sequence/release order
+   alone is not a product dependency; current recorded prohibitions still bind.
+2. Recut unstarted work only where an accepted vertical capability is functional,
+   independently provable and rollbackable against an already real contract.
+   Keep producer edges on actual consumers and dependent integration/proof.
+   Consolidate hub edits in their real producer; worktrees alone do not isolate
+   shared files, databases, ports, credentials or measurement windows.
+3. Root routes a concrete opportunity through native Plan and the canonical
+   [Reslice classifier](standards/acceptance-preserving-reslice.md), preserving
+   every acceptance meaning, prohibition, semantic link and proof obligation.
+   Carry the blocked edge/resource and proposed independent cut into the drafter
+   packet. Invalidate readiness, obtain affected Vet, then reselect; a proposed
+   split or green branch is not admission authority.
+4. Freeze admissions to affected sources during repair. Preserve built and leased
+   slice identities/contracts; drain/reconcile affected workers before publishing
+   a repair that changes their inputs. Unrelated source planning/writers continue.
+5. Preserve human/safety/access/resource gates and explicit planning-only bounds.
+   Classify any authority change through its owning decision; never replace an
+   explicit prohibition with inferred permission or create placeholder slices.
+
+Completion: either admit a currently approved independent cut, or retain
+`Serial rationale: <consumed contract/resource/authority; next unblock event>`
+in affected `tasks.md` slice blocks only when normal Plan write authority permits; otherwise
+report the existing blocker without planning writes. Revisit after relevant
+inputs change, not merely because capacity remains unused. Target width never
+justifies extra architecture, acceptance loss, premature proof or repeatedly
+reslicing unchanged work.
+
+## Continuous global frontier
+
+At entry, each landing, planning/review return and before any wait or final reply:
+
+1. Re-read controller lease, per-source state/questions/readiness and authorized
+   sequence. Scan all stages, not only the owner's next local slice. While writers
+   run, root advances authorized Spec → Clarify → Temper → Define/Plan → Vet,
+   including narrow repair/re-Vet of prepared targets, under unchanged approval
+   and safety rules. Missing human authority blocks that target, not safe siblings.
+   If an explicit/AFK capacity change differs from retained capacity, reconcile it
+   before selection using `parallel add --root <repo> --slug <controller> --cap N --json -`
+   with stdin `[]`. This changes capacity only, not workers or a complete lease's
+   status. A decrease below active count refuses: pause admissions and drain to
+   the requested count, then retry; never cancel workers to meet a lower cap.
+   A pending landing is recovery, not free capacity: retry the exact recorded
+   integrate before admission; unrelated HEAD/ref movement remains blocked.
+2. Query the mixed pool in stable sequence order, controller first (the ordered
+   ACTIVE owner may now differ):
+   `devrites-engine parallel select --root <repo> --slug <controller> --from-plan --workspaces <controller,authorized-source,...> --cap N`.
+   `--workspaces` is an internal data-source parameter, not a user feature flag.
+   Read all notices and route repair/waits to their source. Existing running slots
+   and paths seed selection globally. Zero new picks with live writers means keep
+   planning/reviewing or wait, not Prove for those unfinished sources.
+3. Preflight selected slices against their SOURCE workspace with Build's normal
+   slice/readiness/precondition, exact-path and runtime-isolation gates. Early
+   foreign Build always uses isolated workers. For cap>1 on a capable host,
+   isolate even the first lone local writer, so later sources can refill. Persist
+   `--cap N` on create/add. With a retained lease, add even one pick; a complete
+   retained lease can reopen only at unchanged control tip. After cleanup,
+   create a new batch from current control. Never start another controller.
+   Unsupported isolation uses truthful serial owner dispatch and ordinary ordered
+   handoff, never early same-tree foreign Build or concurrent same-worktree writers.
+4. Launch every selected native writer before waiting on any; keep scheduling
+   planning and independent review while they run. Land each individually green
+   sibling through Build review/proof and `parallel integrate --slice <key>`;
+   refill immediately from the whole authorized pool. A red sibling repairs in
+   place and holds its slot/paths; it does not delay independent green landings.
+   Never satisfy a producer edge on writer return or green-but-unlanded work.
+   After worker-bound review/proof and source bookkeeping finish, prune only
+   verified clean integrated checkouts with `parallel prune --root <repo>
+   --slug <controller>`. Retain transfer refs/lease identities; dirty or ignored
+   data stays with its reported recovery path and does not justify forced deletion.
+
+## Identity, dispatch and proof
+
+Mixed JSON uses `{"slices":[{"id":"SLICE-001","paths":["src/child.go"],"workspace":"child"}]}`.
+Omitted workspace means controller; explicit controller normalizes to that lane.
+Lease targeting uses bare `SLICE-001` only for controller, `child/SLICE-001` for
+foreign sources. Duplicate local IDs across sources remain distinct typed keys.
+Use the lease's worktree/branch paths, not hand-built namespaces.
+
+Controller slug owns `parallel create/add/status/record-green/integrate/prune/cleanup`.
+SOURCE slug owns `context`, `packet`, `dispatch open/start/return`, slice checks,
+candidate freeze, proof, repair, evidence and bookkeeping. Open source-local waves
+with local roles `slice-wright.<SLICE-ID>` and local `--slice <SLICE-ID>`; no slash
+in a dispatch role. Start every source wave before first wait. Root explicitly
+supplies source slug, absolute worktree cwd, base and exact native profile to every
+writer/reviewer. Writer profile is `devrites-slice-wright`, never a suffixed or
+generic profile; reviewers use exact workflow-named `devrites-*` profiles in fresh
+read-only context. Labels/handles are not proof of native profile selection.
+Linked worktrees use `DEVRITES_ROOT=<control>/.devrites` for metadata, not source cwd.
+
+Run controller/global commands in a per-invocation environment without inherited
+worker `DEVRITES_WORKSPACE`; source calls use explicit source slug and control
+`DEVRITES_ROOT` in a source-bound environment, never another source's override.
+Never mutate process-global environment or ACTIVE to route a call.
+
+Freeze/review/prove each source slice in its own worktree/candidate window under
+Build's full required inventory, affected rechecks and repair rules. After landing,
+write `WIP(<source>):` with human summary, union only that source's paths into its
+manifest, persist checked BUILT/evidence and charge once there. Run source-local
+regression checks on resume and ratchet only after durable green advance. Neither
+controller bookkeeping nor sibling proof closes a child's acceptance.
+
+## Lifecycle closeout and Ship
+
+Prove/Polish/Review/Seal remain per workspace with fresh candidate bindings. Shared
+durable Polish outputs serialize; source changes invalidate affected evidence.
+Before any non-lease product correction, shared durable Polish write or control
+checkpoint, freeze new writer admissions, drain/reconcile retained writers, land
+safe green work and cleanup the lease. Preserve blocked work; never force-clean
+it merely to advance a phase. Perform phase-owned correction/proof/checkpoint,
+then resume the pool from new HEAD. Never accept unrelated commits as expected
+ControlTip or invent phase slices. Read-only frozen proof/review and planning-only
+`.devrites` repair may overlap writers; none may mutate the leased product/control tip.
+Normal ordered handoff reuses the same controller and prepared child cursor.
+Never archive controller/source while retained lease owns it; clean up owned
+workers first, preserving salvage and unknown outcomes.
+
+Early child WIPs can interleave with parent WIPs. Parent-only Ship must not absorb
+those commits as if parent alone were sealed. Deferred release waits for every
+participating sequence member's final proof/Review/Seal, uses engine-generated
+release union manifest and re-proves affected cross-workspace acceptance. Disclose
+all participating checkpoints in the exact Git plan, verify unchanged candidate
+and staged bytes, then require fresh literal `GO` plus native approval. Parallelism
+grants no push/tag/deploy authority and never broadens an earlier Ship approval.

package/pack/generated/claude/skills/devrites-lib/reference/standards/afk-hitl.md

@@ -118,18 +118,15 @@ candidate manifest to cover the whole recorded chain — run
   `/rite-autocomplete` recovers agent-owned Seal `NO-GO` per
   [stop-conditions.md](../../../rite-autocomplete/reference/stop-conditions.md), not a handoff.
 
-`max_parallel` is the unattended default batch cap only when this invocation does
-not contain `--parallel N`; `1` forces the serial cycle only in that default
-case. An exact `--parallel N` on `/rite-autocomplete` or `/rite-build` is the
-batch cap for this run: do not consult leftover sentinel `max_parallel`, and do
-not treat `max_parallel: 1` as serial. `/rite-autocomplete --parallel N` writes
-or replaces only that field so later ticks keep the cap; `/rite-build --parallel N`
-wins for that invocation without rewriting the sentinel. Never write `max_slices`
-from `--max-slices`. **Failing case:** `/rite-autocomplete --parallel 5` honors a
-leftover `max_parallel: 1` and stays serial.
-Unattended runs take the largest eligible set ≤ that cap and recompute after
-every completed round (serial slice or parallel integrate)
-([parallel-batch.md § Dynamic selection and re-batching](../../../rite-build/reference/parallel-batch.md#dynamic-selection-and-re-batching)).
+`max_parallel` is the unattended default writer cap when this invocation omits
+`--parallel N`; explicit N wins and Autocomplete writes/replaces only that field.
+Build's explicit flag wins without rewriting the sentinel. Never write
+`max_slices` from `--max-slices`. Autocomplete uses one cap across all authorized
+sources, including explicit 1, under the shared root-only
+[`workspace controller`](../parallel-workspaces.md); standalone Build stays local.
+Unattended runs recompute after each landing and planning/review return, not only
+after a batch completes. **Failing case:** `/rite-autocomplete --parallel 5`
+honors leftover `max_parallel: 1`, or grants five writers per workspace.
 
 ## Unattended resource envelope
 

package/pack/generated/claude/skills/devrites-lib/reference/standards/agents.md

@@ -72,7 +72,7 @@ Only that bounded writer may edit its exact project-relative source/test paths;
 workspace writes, scope widening, or second writer. Root remains source/test nonwriter.
 This exception grants no additional tools, permissions, phase, agent-launch, or Git authority.
 
-Isolated-worktree pilot only under [`wright-dispatch.md`](../../../rite-build/reference/wright-dispatch.md#isolated-writer-worktree-pilot): one writer, committed/clean baseline, non-submodule parent, exact transfer commit, candidate reconciliation — never parallel writers nor weaker exact-path admission. Root may materialize only exact Vet-ready workflow-artifact paths per [`workflow-artifacts.md`](workflow-artifacts.md) — not a writer dispatch or candidate mutation.
+Isolated-worktree pilot follows [`wright-dispatch.md`](../../../rite-build/reference/wright-dispatch.md#isolated-writer-worktree-pilot); sanctioned parallel work follows [`parallel-batch.md`](../../../rite-build/reference/parallel-batch.md) and Autocomplete's shared [`workspace controller`](../parallel-workspaces.md), never same-tree co-writers or weaker exact-path admission. Root may materialize only exact Vet-ready workflow-artifact paths per [`workflow-artifacts.md`](workflow-artifacts.md) — not a writer dispatch or candidate mutation.
 
 Each job gets objective/exclusions, exact paths/immutable candidate, rubric/result shape, a **stop condition** (when to return), and the exact result shape; a dispatch missing them is malformed and re-issued. Briefs MUST NOT seed verdict/severity cap/conclusion/suppression. Results state status/scope, outcome, commands/escalation; wright adds paths, changed files, gates, stood decisions; results never widen scope.