devrites 7.0.0 → 7.0.1

package/pack/generated/codex/skills/devrites-lib/reference/standards/performance.md

@@ -28,6 +28,20 @@ Measure first. An optimization without a measurement is a guess that adds comple
   flaking wall-clock test is a flaky test, [`testing.md`](testing.md)). Budget regression:
   re-measure; fix to budget or record the accepted regression with reason and owner.
 
+## Performance gate protocol
+- A gate that judges a timing budget or a regression percentage pins its protocol
+  before Build: the environment (isolated cores, swap state, build flags such as
+  `CGO_ENABLED`), the repetitions and the aggregate (a median of at least five runs,
+  never one sample), and a noise floor measured as an A/A spread on that same
+  environment. Vet blocks READY on a timing gate without one. A threshold at or
+  below the noise floor is a plan defect for the owner, never a Build repair.
+- A timing gate that fails while no code changed (an A/A run, a rerun) is noise or
+  host state, not a code defect. Stop wright rounds on it and fix the protocol or the
+  environment first.
+- **Failing case:** a 10% p99 regression gate runs one sample per run on a shared host;
+  26 wright rounds repair code against noise until the owner reserves cores and asks
+  for a median of five.
+
 ## Frontend: Core Web Vitals
 For UI work, measure-first means LCP / INP / CLS judged against real numbers, each labeled
 by source (`Field (CrUX)`, `Lab (Lighthouse)`, `Trace (DevTools)`): field and lab are not

package/pack/generated/codex/skills/rite-autocomplete/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: rite-autocomplete
 description: Run the full DevRites lifecycle unattended; --ship continues to the final Git approval boundary. Use for one-shot autonomous work; not for a single phase.
-argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model]"
+argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model] [--lookahead]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"lookahead":["rite-autocomplete/reference/lookahead.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md","rite-autocomplete/reference/lookahead.md"]} -->
 > Read-set manifest: `devrites-engine context --skills-root .agents/skills <slug> --phase autocomplete` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -69,7 +69,7 @@ executable controller/harness/bundle bytes or a missing writer, read
   not a stop either: follow it in your next tool call, never in a text-only
   acknowledgement.
 - Parse flags only from this invocation. `--ship`, `--yolo`, `--max-slices`,
-  `--parallel`, `--full`, and `--cross-model` activate only as exact standalone
+  `--parallel`, `--full`, `--cross-model`, and `--lookahead` activate only as exact standalone
   tokens in `$ARGUMENTS`; examples or earlier messages can never arm them.
   `--max-slices` must occur once and be followed by a positive base-10 integer;
   `--parallel` must occur once and be followed by a base-10 integer in `1`–`10`.
@@ -82,6 +82,10 @@ executable controller/harness/bundle bytes or a missing writer, read
 
 ## Workflow
 
+With `--lookahead` (trigger `lookahead`), follow
+[`lookahead.md`](reference/lookahead.md) instead of the steps below: plan the
+next sequence continuation through Vet in a second session, then stop.
+
 1. **Orient and parse.** Resolve the explicit or active slug; when a workspace exists,
    require its `state.md` and read its cursor; a fresh idea starts empty at step 2.
    Before honoring `blocked` with terminal `next_action`,

package/pack/generated/codex/skills/rite-autocomplete/reference/lookahead.md

@@ -0,0 +1,50 @@
+# Sequence lookahead (`--lookahead`)
+
+> Root-only: not inlined in --role bundles.
+
+A second session plans the next sequence continuation while the active
+workspace builds, so the child's Spec → Vet overlaps its predecessor's
+Build → Seal. The main loop later resumes the planned child instead of
+specifying it again.
+
+## Start and target
+
+The operator starts the second host session with `$rite-autocomplete
+--lookahead` once the `.devrites/ACTIVE` workspace is in Build or later. The
+agent never launches a session itself. The target is the next recorded
+continuation after the active workspace: the entry
+[sequence continuation](loop.md#sequence-continuation) would open. Stop with
+nothing to do when the active workspace is before Build, no entry remains,
+`continue_sequence: false`, or the sequence budget is spent.
+
+## Lease
+
+Before any write, take the workspace lease:
+`devrites-engine claim add --session lookahead-<target> --ttl 240 --workspace <target> --reason lookahead`.
+Exit 3 means another session holds the target: stop. Re-add the lease with the
+same session at each phase start, and release it with `devrites-engine claim
+release` on every stop. A crashed session's lease reads `dead` and frees itself.
+
+## Rules
+
+- Never read or write `.devrites/ACTIVE`. Pass the target slug explicitly to every
+  skill and engine command, including `$rite-spec <target> "<objective>"` and
+  `devrites-engine handoff <target> --resume`.
+- After the workspace exists, run `devrites-engine state set <target> sequence_lookahead=yes`.
+- Run Spec → Clarify → Temper → Define → Plan → Vet as the main loop does.
+  Define and Plan read the predecessor's current tree and plan. Record an
+  assumption for each predecessor interface the plan relies on.
+- At Vet, beside the readiness binding, record exactly one line
+  `Predecessor readiness: <active-slug> <digest>` in `eng-review.md`. `<digest>`
+  is the hex that `devrites-engine check readiness --emit-binding <active-slug>`
+  prints. When the predecessor later changes its planning inputs, the child's
+  readiness check blocks with `DRV-GATE-READINESS-STALE` and the main loop
+  re-vets the child before Build.
+- Never Build, never write product source or tests, never commit, and never
+  arm or rewrite `.devrites/AFK`. Owner questions go to the target's
+  `questions.md` and stop the lookahead.
+- Stop at Vet `READY` with `next_action: build after predecessor Seal GO`, at a
+  human gate, or when the target's lease is lost.
+
+**Failing case:** the lookahead passes Vet and starts Build while the
+predecessor is still sealing, so two root sessions write one tree.

package/pack/generated/codex/skills/rite-autocomplete/reference/loop.md

@@ -93,6 +93,13 @@ step 10 does not end the run: leave the sealed workspace unshipped with its
 (`$rite-spec <parent>-<n> "<objective>"` from the parent's `decisions.md` sequence)
 and re-enter step 1. Spend one workspace per opened continuation.
 
+When that workspace already exists because a [lookahead](lookahead.md) session
+planned it, do not specify it again. Wait while `devrites-engine claim check
+--workspace <child>` exits 3 (a live lookahead holds it), then set
+`.devrites/ACTIVE` to the child and resume from its cursor at step 1. A
+predecessor replan since its Vet blocks the child's readiness with
+`DRV-GATE-READINESS-STALE`; route that to `$rite-vet` before Build.
+
 Spend accounting is durable in `state.md` cursors, not chat. Before invoking the
 continuation, ensure the current workspace's `sequence_workspaces_remaining` is
 set — absent, write `max_workspaces - 1` and `sequence_position: 1` first — and

package/pack/generated/codex/skills/rite-build/reference/spec-drift-guard.md

@@ -12,6 +12,10 @@ phases. Never silently code against a known-wrong plan.
 - the design system / existing UX pattern contradicts the planned UI;
 - a missing user decision that affects product behavior surfaces.
 
+A timing gate that fails with no code cause is a protocol or environment defect
+([performance.md § Performance gate protocol](../../devrites-lib/reference/standards/performance.md#performance-gate-protocol)),
+never another wright round.
+
 ## Workflow
 ```
 1. STOP coding.

package/pack/generated/codex/skills/rite-spec/SKILL.md

@@ -124,7 +124,8 @@ load a routed standard to discover required behavior, not to prescribe implement
    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). If the slug already exists,
+   [state-workspace](reference/state-workspace.md); a `--lookahead` run
+   leaves `.devrites/ACTIVE` unchanged. 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/generated/codex/skills/rite-vet/SKILL.md

@@ -211,7 +211,9 @@ plan declares a root-authored executable workflow file, read
    `marker sweep:` line is recorded in `eng-review.md`; a kept hit blocks READY. Write phase/next step and emit one
    `Readiness inputs SHA-256` with
    `devrites-engine check readiness --emit-binding <slug>`; normal readiness check
-   must pass. Record the per-input drift baseline alongside it:
+   must pass. 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:
    `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/generated/devin/skills/devrites-lib/reference/standards/performance.md

@@ -28,6 +28,20 @@ Measure first. An optimization without a measurement is a guess that adds comple
   flaking wall-clock test is a flaky test, [`testing.md`](testing.md)). Budget regression:
   re-measure; fix to budget or record the accepted regression with reason and owner.
 
+## Performance gate protocol
+- A gate that judges a timing budget or a regression percentage pins its protocol
+  before Build: the environment (isolated cores, swap state, build flags such as
+  `CGO_ENABLED`), the repetitions and the aggregate (a median of at least five runs,
+  never one sample), and a noise floor measured as an A/A spread on that same
+  environment. Vet blocks READY on a timing gate without one. A threshold at or
+  below the noise floor is a plan defect for the owner, never a Build repair.
+- A timing gate that fails while no code changed (an A/A run, a rerun) is noise or
+  host state, not a code defect. Stop wright rounds on it and fix the protocol or the
+  environment first.
+- **Failing case:** a 10% p99 regression gate runs one sample per run on a shared host;
+  26 wright rounds repair code against noise until the owner reserves cores and asks
+  for a median of five.
+
 ## Frontend: Core Web Vitals
 For UI work, measure-first means LCP / INP / CLS judged against real numbers, each labeled
 by source (`Field (CrUX)`, `Lab (Lighthouse)`, `Trace (DevTools)`): field and lab are not

package/pack/generated/devin/skills/rite-autocomplete/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: rite-autocomplete
 description: Run the full DevRites lifecycle unattended; --ship continues to the final Git approval boundary. Use for one-shot autonomous work; not for a single phase.
-argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model]"
+argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model] [--lookahead]"
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"lookahead":["rite-autocomplete/reference/lookahead.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md","rite-autocomplete/reference/lookahead.md"]} -->
 > Read-set manifest: `devrites-engine context --skills-root .devin/skills <slug> --phase autocomplete` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -68,7 +68,7 @@ executable controller/harness/bundle bytes or a missing writer, read
   not a stop either: follow it in your next tool call, never in a text-only
   acknowledgement.
 - Parse flags only from this invocation. `--ship`, `--yolo`, `--max-slices`,
-  `--parallel`, `--full`, and `--cross-model` activate only as exact standalone
+  `--parallel`, `--full`, `--cross-model`, and `--lookahead` activate only as exact standalone
   tokens in `$ARGUMENTS`; examples or earlier messages can never arm them.
   `--max-slices` must occur once and be followed by a positive base-10 integer;
   `--parallel` must occur once and be followed by a base-10 integer in `1`–`10`.
@@ -81,6 +81,10 @@ executable controller/harness/bundle bytes or a missing writer, read
 
 ## Workflow
 
+With `--lookahead` (trigger `lookahead`), follow
+[`lookahead.md`](reference/lookahead.md) instead of the steps below: plan the
+next sequence continuation through Vet in a second session, then stop.
+
 1. **Orient and parse.** Resolve the explicit or active slug; when a workspace exists,
    require its `state.md` and read its cursor; a fresh idea starts empty at step 2.
    Before honoring `blocked` with terminal `next_action`,

package/pack/generated/devin/skills/rite-autocomplete/reference/lookahead.md

@@ -0,0 +1,50 @@
+# Sequence lookahead (`--lookahead`)
+
+> Root-only: not inlined in --role bundles.
+
+A second session plans the next sequence continuation while the active
+workspace builds, so the child's Spec → Vet overlaps its predecessor's
+Build → Seal. The main loop later resumes the planned child instead of
+specifying it again.
+
+## Start and target
+
+The operator starts the second host session with `/rite-autocomplete
+--lookahead` once the `.devrites/ACTIVE` workspace is in Build or later. The
+agent never launches a session itself. The target is the next recorded
+continuation after the active workspace: the entry
+[sequence continuation](loop.md#sequence-continuation) would open. Stop with
+nothing to do when the active workspace is before Build, no entry remains,
+`continue_sequence: false`, or the sequence budget is spent.
+
+## Lease
+
+Before any write, take the workspace lease:
+`devrites-engine claim add --session lookahead-<target> --ttl 240 --workspace <target> --reason lookahead`.
+Exit 3 means another session holds the target: stop. Re-add the lease with the
+same session at each phase start, and release it with `devrites-engine claim
+release` on every stop. A crashed session's lease reads `dead` and frees itself.
+
+## Rules
+
+- Never read or write `.devrites/ACTIVE`. Pass the target slug explicitly to every
+  skill and engine command, including `/rite-spec <target> "<objective>"` and
+  `devrites-engine handoff <target> --resume`.
+- After the workspace exists, run `devrites-engine state set <target> sequence_lookahead=yes`.
+- Run Spec → Clarify → Temper → Define → Plan → Vet as the main loop does.
+  Define and Plan read the predecessor's current tree and plan. Record an
+  assumption for each predecessor interface the plan relies on.
+- At Vet, beside the readiness binding, record exactly one line
+  `Predecessor readiness: <active-slug> <digest>` in `eng-review.md`. `<digest>`
+  is the hex that `devrites-engine check readiness --emit-binding <active-slug>`
+  prints. When the predecessor later changes its planning inputs, the child's
+  readiness check blocks with `DRV-GATE-READINESS-STALE` and the main loop
+  re-vets the child before Build.
+- Never Build, never write product source or tests, never commit, and never
+  arm or rewrite `.devrites/AFK`. Owner questions go to the target's
+  `questions.md` and stop the lookahead.
+- Stop at Vet `READY` with `next_action: build after predecessor Seal GO`, at a
+  human gate, or when the target's lease is lost.
+
+**Failing case:** the lookahead passes Vet and starts Build while the
+predecessor is still sealing, so two root sessions write one tree.

package/pack/generated/devin/skills/rite-autocomplete/reference/loop.md

@@ -93,6 +93,13 @@ step 10 does not end the run: leave the sealed workspace unshipped with its
 (`/rite-spec <parent>-<n> "<objective>"` from the parent's `decisions.md` sequence)
 and re-enter step 1. Spend one workspace per opened continuation.
 
+When that workspace already exists because a [lookahead](lookahead.md) session
+planned it, do not specify it again. Wait while `devrites-engine claim check
+--workspace <child>` exits 3 (a live lookahead holds it), then set
+`.devrites/ACTIVE` to the child and resume from its cursor at step 1. A
+predecessor replan since its Vet blocks the child's readiness with
+`DRV-GATE-READINESS-STALE`; route that to `/rite-vet` before Build.
+
 Spend accounting is durable in `state.md` cursors, not chat. Before invoking the
 continuation, ensure the current workspace's `sequence_workspaces_remaining` is
 set — absent, write `max_workspaces - 1` and `sequence_position: 1` first — and

package/pack/generated/devin/skills/rite-build/reference/spec-drift-guard.md

@@ -12,6 +12,10 @@ phases. Never silently code against a known-wrong plan.
 - the design system / existing UX pattern contradicts the planned UI;
 - a missing user decision that affects product behavior surfaces.
 
+A timing gate that fails with no code cause is a protocol or environment defect
+([performance.md § Performance gate protocol](../../devrites-lib/reference/standards/performance.md#performance-gate-protocol)),
+never another wright round.
+
 ## Workflow
 ```
 1. STOP coding.

package/pack/generated/devin/skills/rite-spec/SKILL.md

@@ -123,7 +123,8 @@ load a routed standard to discover required behavior, not to prescribe implement
    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). If the slug already exists,
+   [state-workspace](reference/state-workspace.md); a `--lookahead` run
+   leaves `.devrites/ACTIVE` unchanged. 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/generated/devin/skills/rite-vet/SKILL.md

@@ -210,7 +210,9 @@ plan declares a root-authored executable workflow file, read
    `marker sweep:` line is recorded in `eng-review.md`; a kept hit blocks READY. Write phase/next step and emit one
    `Readiness inputs SHA-256` with
    `devrites-engine check readiness --emit-binding <slug>`; normal readiness check
-   must pass. Record the per-input drift baseline alongside it:
+   must pass. 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:
    `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/generated/omp/commands/rite-autocomplete.md

@@ -1,5 +1,5 @@
 ---
 description: "Run the full DevRites lifecycle unattended; --ship continues to the final Git approval boundary. Use for one-shot autonomous work; not for a single phase."
-argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model]"
+argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model] [--lookahead]"
 ---
 Read and follow the DevRites skill `skill://rite-autocomplete` (`.omp/skills/rite-autocomplete/SKILL.md`). Apply it to these arguments, or to the current request when they are empty: $ARGUMENTS

package/pack/generated/omp/skills/devrites-lib/reference/standards/performance.md

@@ -28,6 +28,20 @@ Measure first. An optimization without a measurement is a guess that adds comple
   flaking wall-clock test is a flaky test, [`testing.md`](testing.md)). Budget regression:
   re-measure; fix to budget or record the accepted regression with reason and owner.
 
+## Performance gate protocol
+- A gate that judges a timing budget or a regression percentage pins its protocol
+  before Build: the environment (isolated cores, swap state, build flags such as
+  `CGO_ENABLED`), the repetitions and the aggregate (a median of at least five runs,
+  never one sample), and a noise floor measured as an A/A spread on that same
+  environment. Vet blocks READY on a timing gate without one. A threshold at or
+  below the noise floor is a plan defect for the owner, never a Build repair.
+- A timing gate that fails while no code changed (an A/A run, a rerun) is noise or
+  host state, not a code defect. Stop wright rounds on it and fix the protocol or the
+  environment first.
+- **Failing case:** a 10% p99 regression gate runs one sample per run on a shared host;
+  26 wright rounds repair code against noise until the owner reserves cores and asks
+  for a median of five.
+
 ## Frontend: Core Web Vitals
 For UI work, measure-first means LCP / INP / CLS judged against real numbers, each labeled
 by source (`Field (CrUX)`, `Lab (Lighthouse)`, `Trace (DevTools)`): field and lab are not

package/pack/generated/omp/skills/rite-autocomplete/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: rite-autocomplete
 description: Run the full DevRites lifecycle unattended; --ship continues to the final Git approval boundary. Use for one-shot autonomous work; not for a single phase.
-argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model]"
+argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model] [--lookahead]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"lookahead":["rite-autocomplete/reference/lookahead.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md","rite-autocomplete/reference/lookahead.md"]} -->
 > Read-set manifest: `devrites-engine context --skills-root .omp/skills <slug> --phase autocomplete` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -69,7 +69,7 @@ executable controller/harness/bundle bytes or a missing writer, read
   not a stop either: follow it in your next tool call, never in a text-only
   acknowledgement.
 - Parse flags only from this invocation. `--ship`, `--yolo`, `--max-slices`,
-  `--parallel`, `--full`, and `--cross-model` activate only as exact standalone
+  `--parallel`, `--full`, `--cross-model`, and `--lookahead` activate only as exact standalone
   tokens in `$ARGUMENTS`; examples or earlier messages can never arm them.
   `--max-slices` must occur once and be followed by a positive base-10 integer;
   `--parallel` must occur once and be followed by a base-10 integer in `1`–`10`.
@@ -82,6 +82,10 @@ executable controller/harness/bundle bytes or a missing writer, read
 
 ## Workflow
 
+With `--lookahead` (trigger `lookahead`), follow
+[`lookahead.md`](reference/lookahead.md) instead of the steps below: plan the
+next sequence continuation through Vet in a second session, then stop.
+
 1. **Orient and parse.** Resolve the explicit or active slug; when a workspace exists,
    require its `state.md` and read its cursor; a fresh idea starts empty at step 2.
    Before honoring `blocked` with terminal `next_action`,

package/pack/generated/omp/skills/rite-autocomplete/reference/lookahead.md

@@ -0,0 +1,50 @@
+# Sequence lookahead (`--lookahead`)
+
+> Root-only: not inlined in --role bundles.
+
+A second session plans the next sequence continuation while the active
+workspace builds, so the child's Spec → Vet overlaps its predecessor's
+Build → Seal. The main loop later resumes the planned child instead of
+specifying it again.
+
+## Start and target
+
+The operator starts the second host session with `/rite-autocomplete
+--lookahead` once the `.devrites/ACTIVE` workspace is in Build or later. The
+agent never launches a session itself. The target is the next recorded
+continuation after the active workspace: the entry
+[sequence continuation](loop.md#sequence-continuation) would open. Stop with
+nothing to do when the active workspace is before Build, no entry remains,
+`continue_sequence: false`, or the sequence budget is spent.
+
+## Lease
+
+Before any write, take the workspace lease:
+`devrites-engine claim add --session lookahead-<target> --ttl 240 --workspace <target> --reason lookahead`.
+Exit 3 means another session holds the target: stop. Re-add the lease with the
+same session at each phase start, and release it with `devrites-engine claim
+release` on every stop. A crashed session's lease reads `dead` and frees itself.
+
+## Rules
+
+- Never read or write `.devrites/ACTIVE`. Pass the target slug explicitly to every
+  skill and engine command, including `/rite-spec <target> "<objective>"` and
+  `devrites-engine handoff <target> --resume`.
+- After the workspace exists, run `devrites-engine state set <target> sequence_lookahead=yes`.
+- Run Spec → Clarify → Temper → Define → Plan → Vet as the main loop does.
+  Define and Plan read the predecessor's current tree and plan. Record an
+  assumption for each predecessor interface the plan relies on.
+- At Vet, beside the readiness binding, record exactly one line
+  `Predecessor readiness: <active-slug> <digest>` in `eng-review.md`. `<digest>`
+  is the hex that `devrites-engine check readiness --emit-binding <active-slug>`
+  prints. When the predecessor later changes its planning inputs, the child's
+  readiness check blocks with `DRV-GATE-READINESS-STALE` and the main loop
+  re-vets the child before Build.
+- Never Build, never write product source or tests, never commit, and never
+  arm or rewrite `.devrites/AFK`. Owner questions go to the target's
+  `questions.md` and stop the lookahead.
+- Stop at Vet `READY` with `next_action: build after predecessor Seal GO`, at a
+  human gate, or when the target's lease is lost.
+
+**Failing case:** the lookahead passes Vet and starts Build while the
+predecessor is still sealing, so two root sessions write one tree.

package/pack/generated/omp/skills/rite-autocomplete/reference/loop.md

@@ -93,6 +93,13 @@ step 10 does not end the run: leave the sealed workspace unshipped with its
 (`/rite-spec <parent>-<n> "<objective>"` from the parent's `decisions.md` sequence)
 and re-enter step 1. Spend one workspace per opened continuation.
 
+When that workspace already exists because a [lookahead](lookahead.md) session
+planned it, do not specify it again. Wait while `devrites-engine claim check
+--workspace <child>` exits 3 (a live lookahead holds it), then set
+`.devrites/ACTIVE` to the child and resume from its cursor at step 1. A
+predecessor replan since its Vet blocks the child's readiness with
+`DRV-GATE-READINESS-STALE`; route that to `/rite-vet` before Build.
+
 Spend accounting is durable in `state.md` cursors, not chat. Before invoking the
 continuation, ensure the current workspace's `sequence_workspaces_remaining` is
 set — absent, write `max_workspaces - 1` and `sequence_position: 1` first — and

package/pack/generated/omp/skills/rite-build/reference/spec-drift-guard.md

@@ -12,6 +12,10 @@ phases. Never silently code against a known-wrong plan.
 - the design system / existing UX pattern contradicts the planned UI;
 - a missing user decision that affects product behavior surfaces.
 
+A timing gate that fails with no code cause is a protocol or environment defect
+([performance.md § Performance gate protocol](skill://devrites-lib/reference/standards/performance.md#performance-gate-protocol)),
+never another wright round.
+
 ## Workflow
 ```
 1. STOP coding.

package/pack/generated/omp/skills/rite-spec/SKILL.md

@@ -124,7 +124,8 @@ load a routed standard to discover required behavior, not to prescribe implement
    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). If the slug already exists,
+   [state-workspace](reference/state-workspace.md); a `--lookahead` run
+   leaves `.devrites/ACTIVE` unchanged. 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/generated/omp/skills/rite-vet/SKILL.md

@@ -211,7 +211,9 @@ plan declares a root-authored executable workflow file, read
    `marker sweep:` line is recorded in `eng-review.md`; a kept hit blocks READY. Write phase/next step and emit one
    `Readiness inputs SHA-256` with
    `devrites-engine check readiness --emit-binding <slug>`; normal readiness check
-   must pass. Record the per-input drift baseline alongside it:
+   must pass. 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:
    `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/generated/pi/prompts/rite-autocomplete.md

@@ -1,5 +1,5 @@
 ---
 description: "Run the full DevRites lifecycle unattended; --ship continues to the final Git approval boundary. Use for one-shot autonomous work; not for a single phase."
-argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model]"
+argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model] [--lookahead]"
 ---
 Read and follow the DevRites skill at `.pi/skills/rite-autocomplete/SKILL.md`, applying it to: ${ARGUMENTS:-the current request}.

package/pack/generated/pi/skills/devrites-lib/reference/standards/performance.md

@@ -28,6 +28,20 @@ Measure first. An optimization without a measurement is a guess that adds comple
   flaking wall-clock test is a flaky test, [`testing.md`](testing.md)). Budget regression:
   re-measure; fix to budget or record the accepted regression with reason and owner.
 
+## Performance gate protocol
+- A gate that judges a timing budget or a regression percentage pins its protocol
+  before Build: the environment (isolated cores, swap state, build flags such as
+  `CGO_ENABLED`), the repetitions and the aggregate (a median of at least five runs,
+  never one sample), and a noise floor measured as an A/A spread on that same
+  environment. Vet blocks READY on a timing gate without one. A threshold at or
+  below the noise floor is a plan defect for the owner, never a Build repair.
+- A timing gate that fails while no code changed (an A/A run, a rerun) is noise or
+  host state, not a code defect. Stop wright rounds on it and fix the protocol or the
+  environment first.
+- **Failing case:** a 10% p99 regression gate runs one sample per run on a shared host;
+  26 wright rounds repair code against noise until the owner reserves cores and asks
+  for a median of five.
+
 ## Frontend: Core Web Vitals
 For UI work, measure-first means LCP / INP / CLS judged against real numbers, each labeled
 by source (`Field (CrUX)`, `Lab (Lighthouse)`, `Trace (DevTools)`): field and lab are not

package/pack/generated/pi/skills/rite-autocomplete/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: rite-autocomplete
 description: Run the full DevRites lifecycle unattended; --ship continues to the final Git approval boundary. Use for one-shot autonomous work; not for a single phase.
-argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model]"
+argument-hint: "[idea] [--ship|--yolo] [--max-slices N] [--parallel N] [--full] [--cross-model] [--lookahead]"
 user-invocable: true
 ---
 
-<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md"]} -->
+<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/standards/one-shot-actions.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/acceptance-preserving-reslice.md","rite-autocomplete/reference/decision-policy.md","rite-autocomplete/reference/loop.md","rite-autocomplete/reference/stop-conditions.md"],"triggers":{"workflow-artifacts":["devrites-lib/reference/standards/workflow-artifacts.md"],"lookahead":["rite-autocomplete/reference/lookahead.md"]},"workspace":["state.md","spec.md","plan.md","tasks.md","questions.md","decisions.md","drift.md","evidence.md","test-plan.md"],"rootOnly":["devrites-lib/reference/standards/afk-hitl.md","devrites-lib/reference/orchestration-profiles.md","devrites-lib/reference/standards/workflow-artifacts.md","rite-autocomplete/reference/lookahead.md"]} -->
 > Read-set manifest: `devrites-engine context --skills-root .pi/skills <slug> --phase autocomplete` bundles every file named below into one deduplicated read. Trigger names map to the conditional rules in the sections that follow.
 
 
@@ -69,7 +69,7 @@ executable controller/harness/bundle bytes or a missing writer, read
   not a stop either: follow it in your next tool call, never in a text-only
   acknowledgement.
 - Parse flags only from this invocation. `--ship`, `--yolo`, `--max-slices`,
-  `--parallel`, `--full`, and `--cross-model` activate only as exact standalone
+  `--parallel`, `--full`, `--cross-model`, and `--lookahead` activate only as exact standalone
   tokens in `$ARGUMENTS`; examples or earlier messages can never arm them.
   `--max-slices` must occur once and be followed by a positive base-10 integer;
   `--parallel` must occur once and be followed by a base-10 integer in `1`–`10`.
@@ -82,6 +82,10 @@ executable controller/harness/bundle bytes or a missing writer, read
 
 ## Workflow
 
+With `--lookahead` (trigger `lookahead`), follow
+[`lookahead.md`](reference/lookahead.md) instead of the steps below: plan the
+next sequence continuation through Vet in a second session, then stop.
+
 1. **Orient and parse.** Resolve the explicit or active slug; when a workspace exists,
    require its `state.md` and read its cursor; a fresh idea starts empty at step 2.
    Before honoring `blocked` with terminal `next_action`,

package/pack/generated/pi/skills/rite-autocomplete/reference/lookahead.md

@@ -0,0 +1,50 @@
+# Sequence lookahead (`--lookahead`)
+
+> Root-only: not inlined in --role bundles.
+
+A second session plans the next sequence continuation while the active
+workspace builds, so the child's Spec → Vet overlaps its predecessor's
+Build → Seal. The main loop later resumes the planned child instead of
+specifying it again.
+
+## Start and target
+
+The operator starts the second host session with `/rite-autocomplete
+--lookahead` once the `.devrites/ACTIVE` workspace is in Build or later. The
+agent never launches a session itself. The target is the next recorded
+continuation after the active workspace: the entry
+[sequence continuation](loop.md#sequence-continuation) would open. Stop with
+nothing to do when the active workspace is before Build, no entry remains,
+`continue_sequence: false`, or the sequence budget is spent.
+
+## Lease
+
+Before any write, take the workspace lease:
+`devrites-engine claim add --session lookahead-<target> --ttl 240 --workspace <target> --reason lookahead`.
+Exit 3 means another session holds the target: stop. Re-add the lease with the
+same session at each phase start, and release it with `devrites-engine claim
+release` on every stop. A crashed session's lease reads `dead` and frees itself.
+
+## Rules
+
+- Never read or write `.devrites/ACTIVE`. Pass the target slug explicitly to every
+  skill and engine command, including `/rite-spec <target> "<objective>"` and
+  `devrites-engine handoff <target> --resume`.
+- After the workspace exists, run `devrites-engine state set <target> sequence_lookahead=yes`.
+- Run Spec → Clarify → Temper → Define → Plan → Vet as the main loop does.
+  Define and Plan read the predecessor's current tree and plan. Record an
+  assumption for each predecessor interface the plan relies on.
+- At Vet, beside the readiness binding, record exactly one line
+  `Predecessor readiness: <active-slug> <digest>` in `eng-review.md`. `<digest>`
+  is the hex that `devrites-engine check readiness --emit-binding <active-slug>`
+  prints. When the predecessor later changes its planning inputs, the child's
+  readiness check blocks with `DRV-GATE-READINESS-STALE` and the main loop
+  re-vets the child before Build.
+- Never Build, never write product source or tests, never commit, and never
+  arm or rewrite `.devrites/AFK`. Owner questions go to the target's
+  `questions.md` and stop the lookahead.
+- Stop at Vet `READY` with `next_action: build after predecessor Seal GO`, at a
+  human gate, or when the target's lease is lost.
+
+**Failing case:** the lookahead passes Vet and starts Build while the
+predecessor is still sealing, so two root sessions write one tree.