devrites 5.1.0 → 5.2.1

package/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 All notable changes to DevRites are documented here. The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and DevRites adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). Releases are generated automatically by [semantic-release](https://semantic-release.gitbook.io/) from Conventional Commits on `main`.
 
+## [5.2.1](https://github.com/ViktorsBaikers/DevRites/compare/v5.2.0...v5.2.1) (2026-09-11)
+
+### Fixed
+
+* **skills:** scope drafter self-check to patched invariants ([#62](https://github.com/ViktorsBaikers/DevRites/issues/62)) ([d32bbf9](https://github.com/ViktorsBaikers/DevRites/commit/d32bbf9f81e255dae6e66622ab8b0e1fd1017a2c))
+
+## [5.2.0](https://github.com/ViktorsBaikers/DevRites/compare/v5.1.0...v5.2.0) (2026-09-11)
+
+### Added
+
+* **skills:** batch build-time gap repair and auto-chain plan/vet ([#61](https://github.com/ViktorsBaikers/DevRites/issues/61)) ([a668270](https://github.com/ViktorsBaikers/DevRites/commit/a668270b4a278ffb81a1b73bf962d13da2097e5a))
+
 ## [5.1.0](https://github.com/ViktorsBaikers/DevRites/compare/v5.0.0...v5.1.0) (2026-09-10)
 
 ### Added

package/README.md

@@ -33,7 +33,7 @@ project-conventional push, tag, or PR action, and archive the workspace.
 Unattended runs may create local WIP checkpoint commits along the way, but they
 remain local unless Ship's disclosed plan includes an approved remote action.
 
-**Status:** [`v5.1.0`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v5.1.0): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
+**Status:** [`v5.2.1`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v5.2.1): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
 
 This is the latest published release; `main` may contain unreleased work.
 

package/pack/.claude/agents/devrites-plan-drafter.md

@@ -53,6 +53,13 @@ principle-exception questions. List them for the root.
 - Do not invoke another agent.
 - Return candidate content only for requested paths. If unfinished, name the exact
   remaining path instead of compressing away a contract.
+- In `repair`, if the full bundle would exceed reliable output, return
+  `Outcome: partial` with complete hunks for a whole-finding prefix in packet
+  order plus `remaining_findings` — a finding is all its sites or none; never
+  split one across returns. The root materializes the partial bundle and
+  re-dispatches the rest. A finding blocked on human-owned information goes in
+  `blocked_findings` with the needed input named — never `remaining_findings`,
+  which is reserved for what another dispatch can complete.
 
 ## Output format
 

package/pack/.claude/agents/devrites-slice-wright.md

@@ -140,6 +140,10 @@ return an `Escalation`** when:
   scoped exception or the approach must change. Report the principle and conflict
   in `Escalation`.
 
+A plan-gap or underspecification escalation populates `assumptions` with every
+contract assumption already checked (verified|falsified); the orchestrator's
+batch sweep covers only the unchecked remainder. Never a bare "plan is wrong".
+
 If an answer would change scope or acceptance, do **not** fold it into the slice.
 Return it in `Escalation` so the orchestrator can route it through the Spec Drift
 Guard (`/rite-plan repair`). Respect any AFK budget in the contract.
@@ -174,7 +178,7 @@ reuse: []
 conventions: []
 principles: []
 sources: []
-assumptions: []
+assumptions: [] # plan-gap escalation: every checked contract assumption, verified|falsified
 decisions_stood: [] # irreversible-risk items go to escalation
 dead_ends: []
 escalation: <none | gate + crisp question + proposed answer>

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

@@ -38,8 +38,10 @@ Wright applies anti-slop; root verifies returns and never patches source.
   single-slice isolation when `wright-dispatch.md` preflight + reconcile hold.
 - Exact feature scope only; reject out-of-allowlist diffs; record adjacent issues.
 - Never rerun an unchanged check; re-prove after edits.
-- Unplanned dependency/design-system/gap/repair → Vet/Spec Drift Guard. Ask only
-  for licensing/cost/security/product or explicit architecture-policy decisions.
+- Unplanned dependency/design-system/gap/repair → Vet/Spec Drift Guard batch
+  sweep: every contract-assumption violation recorded before one folded
+  repair+vet. Ask only for licensing/cost/security/product or explicit
+  architecture-policy decisions.
 - Root never edits product source/tests (`.devrites/` + Workflow Artifact only).
   Wright is sole product writer; extras in returned paths/`git diff --name-only` hard-stop.
 - Principles bind; irreversible conflict needs human exception or stop.
@@ -57,8 +59,8 @@ Wright applies anti-slop; root verifies returns and never patches source.
 
 Omitted/`1` ≡ serial; `2`–`10` → path-disjoint fan-out when eligible; else hard refuse.
 All-green serial integrate; one red/gap aborts. Abort with agent-owned plan
-gaps continues via Spec Drift Guard (plan repair + vet inline); do not emit a
-human `Fix`. AFK charges after integrate only. Running lease blocks another
+gaps continues via Spec Drift Guard (batch sweep, one folded plan repair + one
+vet recheck inline); do not emit a human `Fix`. AFK charges after integrate only. Running lease blocks another
 `/rite-build`. Details: `parallel-batch.md`.
 
 ## Execute and reply

package/pack/.claude/skills/rite-build/reference/one-slice-cycle.md

@@ -39,7 +39,8 @@ you check yourself against: anything outside it is scope creep or a drift event.
 ## When the slice can't be completed cleanly
 
 - Discovered the plan is wrong → **Spec Drift Guard** (record, classify;
-  agent-owned repair+vet inline; ask only for product/policy/irreversible-risk).
+  sweep every remaining contract assumption, then one folded repair+vet inline;
+  ask only for product/policy/irreversible-risk).
 - Slice is bigger than one cycle → `/rite-plan reslice` inline when AC is
   preserved; do not emit a human Fix.
 - Blocked on a failing dependency → record in `state.md`, `/rite-plan unblock`

package/pack/.claude/skills/rite-build/reference/parallel-batch.md

@@ -51,8 +51,9 @@ Lease: `batch_id`, `created_at`, `base_sha`, `n`,
    per integrated sibling; optional `check candidate`.
 8. Cleanup: success removes worktrees/branches. Abort keeps them as repair
    inputs until the root consumes them: agent-owned plan gaps (AC unchanged)
-   follow [`spec-drift-guard.md`](spec-drift-guard.md) — `/rite-plan repair` then
-   `/rite-vet` inline, then cleanup and resume Build. Do not emit
+   follow [`spec-drift-guard.md`](spec-drift-guard.md) — batch-sweep all
+   siblings' contract assumptions, one folded `/rite-plan repair` + one
+   `/rite-vet` recheck inline, then cleanup and resume Build. Do not emit
    `Fix: /rite-plan repair`. Product/policy/irreversible-risk still stops.
 
 ## Engine verbs

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

@@ -24,13 +24,31 @@ other phases reference it here.
      YES, active-slice technical/tool failure → log it and use Build's bounded debug
        recovery. Do not ask for retry authorization and do not re-plan unless the
        durable remaining-work instructions are wrong.
-     YES, durable plan is wrong → log it, save the caller's return cursor, then
-       invoke `/rite-plan repair` and `/rite-vet` inline without a question and resume.
+     YES, durable plan is wrong → run the batch sweep below, log every
+       violation, save the caller's return cursor, then invoke `/rite-plan repair` and `/rite-vet` inline
+       without a question — ONE folded repair for all open entries, ONE
+       recheck for every open fingerprint — and resume.
      NO, product/policy/irreversible-risk decision → ask the user (format below).
 5. Never continue on a known-wrong durable plan. A repaired active-slice implementation
    may continue only after bounded recovery, returned-diff review, and proof gates pass.
 ```
 
+## Batch sweep (before repair)
+
+A durable-plan drift abort never repairs the first gap alone:
+
+1. Verify every remaining statically-checkable contract assumption against the
+   live repo — named paths, symbols/APIs/signatures, routes, commands, dependency
+   versions, contract artifacts. The wright's return names what it falsified;
+   check the rest yourself — existence checks are deterministic, no dispatch.
+2. Record each violation as its own `drift.md` entry/fingerprint; one folded
+   repair + one batched recheck resolves the set.
+3. A recheck-surfaced gap is a new fingerprint with its own budget — loop
+   internally, never hand an intermediate command to the human.
+4. Nothing skips or defers silently: every entry ends resolved, human-escalated,
+   or fingerprint-exhausted. Execution-only gaps (tests, UX, evidence) get the
+   identical path when they surface.
+
 ## User question format
 ```
 I hit spec drift:
@@ -50,7 +68,8 @@ human permission question. Re-plan only when the durable plan changed.
 
 ## Inline return contract
 
-The phase that detected agent-owned drift owns the whole backtrack. Preserve it
+The phase that detected agent-owned drift owns the whole backtrack, batch sweep
+included. Preserve it
 as `return_phase`/`return_next_action`; consume Plan and Vet's nested `STOP`
 boundaries internally; follow any vetted remediation required by the settled
 acceptance; then restore the cursor and resume the failed step. Do not hand an

package/pack/.claude/skills/rite-build/reference/wright-dispatch.md

@@ -83,4 +83,7 @@ Opt-in `/rite-build --parallel N` fans out only under [`parallel-batch.md`](para
    attempts is the limit; persist each and never dispatch a fourth related try.
 5. Reconcile returned reuse, conventions, principles, sources, assumptions,
    decisions, dead ends, follow-ups, gates, and touched files. Persist the
-   relevant facts in canonical artifacts, not the wholesale report.
+   relevant facts in canonical artifacts, not the wholesale report. A plan-gap
+   escalation without the checked-assumption list (verified|falsified) is
+   malformed; root sweeps the unchecked remainder per
+   [`spec-drift-guard.md`](spec-drift-guard.md) before repair.

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

@@ -79,6 +79,11 @@ Before classifying any Reslice, read `.claude/skills/devrites-lib/reference/stan
    require the drafter to apply `one-shot-actions.md` and return the bounded
    diagnostic-amplification design, injective boundary map, per-seam fixtures, and
    collision mutant. Past evidence loss is not terminal. The drafter supplies no bodies.
+   A repair candidate carries a delta self-check scoped to what the patch
+   touches: which intersected invariants it re-verified, with evidence of no
+   correction-created regression. Global re-derivation (ID/edge/HZN counts,
+   acyclicity) runs on materialized artifacts at the step-7 gate — the drafter
+   never re-derives them by exhaustive search.
    Bind exact active `.devrites/work/<slug>/` targets and executable contract; after Vet READY, root
    materializes the exact vetted workflow-artifact paths under
    [`workflow-artifacts.md`](../devrites-lib/reference/standards/workflow-artifacts.md)
@@ -101,7 +106,16 @@ Before classifying any Reslice, read `.claude/skills/devrites-lib/reference/stan
    [task-breakdown](reference/task-breakdown.md). Prefer thin, shippable, verifiable.
    **Completion:** every slice is independently shippable/provable or carries an irreducibility reason.
 5. Reconcile the candidate against steps 3 and 4, then the root updates `plan.md`, `tasks.md`,
-   `state.md`, and appends rationale to `decisions.md`.
+   `state.md`, and appends rationale to `decisions.md`. A rejected candidate
+   (malformed bundle, stale or non-unique anchor) or a drafter `Outcome: gap`
+   is one no-progress outcome on every open fingerprint in the fold; the
+   re-dispatch packet must name the rejection so the same hunks don't recur.
+   A gap naming genuinely human-owned information routes to `/rite-clarify`.
+   A drafter `Outcome: partial` is progress: materialize its complete findings,
+   then re-dispatch a narrowed packet for `remaining_findings` with anchors
+   re-derived from the just-updated files — same repair pass, fresh context.
+   A partial covering zero findings counts as no-progress. Findings in
+   `blocked_findings` route to `/rite-clarify`, never the re-dispatch.
    Any change to `architecture.md`, `plan.md`, `tasks.md`, or `traceability.md` invalidates
    the previous vet verdict: set `Phase: plan`, `Next step: /rite-vet`, and, when
    `eng-review.md` exists, set `Implementation readiness: NEEDS REPLAN`. Never retain READY
@@ -115,8 +129,9 @@ Before classifying any Reslice, read `.claude/skills/devrites-lib/reference/stan
    material assumption, or open blocking/escalating question routes `/rite-clarify`/HITL.
    Restore `CLEAR` only from current evidence.
 7. **Done when:** every slice is sized (builds + proves in one cycle; no slice scoring >3
-   left unjustified), the dependency order is acyclic, every `drift.md` entry you stopped for
-   is marked resolved, revised artifacts agree with each other, no source files changed in
+   left unjustified), the dependency order is acyclic, every open `drift.md` entry
+   was folded in one pass and marked resolved, the delta self-check is recorded,
+   revised artifacts agree with each other, no source files changed in
    `revise` mode, the marked action is complete, and every changed
    plan ends at `/rite-vet` rather than returning directly to build; horizon IDs stay stable,
    reclassifications cite evidence, and no unresolved item vanished. The `Shared contract proof`
@@ -128,5 +143,13 @@ to that caller so it can invoke Vet immediately. The phase boundary is not a
 user-facing stop unless a genuine HITL, safety/access, or exhausted-recovery
 condition was recorded.
 
+When invoked directly with no controlling caller and a planning artifact
+changed, become the caller for the mandated next step: record the return
+cursor, invoke `/rite-vet` inline, and consume its results — `NEEDS REPLAN`
+re-enters repair internally under the fingerprint caps; `NEEDS CLARIFICATION`
+and human-owned gates still reach the user. Stop only at Vet's boundary (READY
+readback; next step `/rite-build`). An unchanged plan keeps its recorded next
+step.
+
 > **Mid-flight discipline.** Do not change product behavior without confirmation or
 > absorb drift silently. See [`anti-patterns`](reference/anti-patterns.md).

package/pack/.claude/skills/rite-plan/reference/replan-and-repair.md

@@ -26,12 +26,19 @@ dependency edges.
 
 A drift event stopped the build. Steps:
 
-1. Read the `drift.md` entry and its classification.
+1. Read the `drift.md` entries and their classifications. Fold EVERY open entry
+   and accepted finding for the affected artifacts in ONE pass, never serially.
 2. If the user answered a drift question, encode that decision in `decisions.md`.
 3. Update `spec.md` (only the affected sections) and `plan.md`/`tasks.md` to match
    reality. Adjust acceptance criteria if they were wrong.
-4. Mark the `drift.md` entry **resolved** with the resolution + date.
-5. Resume at the corrected slice.
+4. Mark each `drift.md` entry **resolved** with the resolution + date.
+5. **Self-check the repaired candidate on the delta before handoff** — re-verify
+   every invariant the correction touched (acyclic dependency graph,
+   bidirectional traceability, Shared contract proof vs boundary set, sizing,
+   no correction-created regression) and record the evidence in the Plan
+   checkpoint; Vet's recheck verifies it rather than rediscovering the defect a
+   loop later.
+6. Resume at the corrected slice.
 Never quietly delete a requirement; use the marked action before contract edits.
 
 ## reorder

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

@@ -52,10 +52,14 @@ plan declares a root-authored executable workflow file, read
 - Use the lowest axis band; never average or round thin to ready. Search before
   asking and resolve reversible technical choices. Ask only human-owned choices.
 - Preserve a valid technical return cursor. Agent-owned `NEEDS REPLAN` returns
-  internally to its caller, not to the human.
-- **Recovery recheck is bounded.** A valid cursor plus open fingerprint enters
-  Recovery recheck; it does not start another Full Vet or repeat unaffected
-  axes/reviewers.
+  internally to its caller, not to the human; on a direct invocation there is
+  no caller, so Vet becomes it — record the cursor and invoke `/rite-plan`
+  repair inline under the same fingerprint caps.
+- **Recovery recheck is bounded and batched.** A valid cursor plus open
+  fingerprints enters Recovery recheck; it does not start another Full Vet or
+  repeat unaffected axes/reviewers. One dispatch covers every open fingerprint
+  of the fold — each checked individually — with a mandatory correction-created
+  regression audit.
 <!-- 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
 
@@ -73,10 +77,15 @@ plan declares a root-authored executable workflow file, read
    required account blocks.
 1b. **Recovery recheck.** Require valid return cursor, accepted prior finding,
    exact fingerprint/reproduction, repaired candidate identity, changed
-   paths/criteria, and affected drift/evidence. Freeze that packet and dispatch
-   each exact owning reviewer once, fresh/read-only, limited to it. Do not rerun
-   broad inventory or unaffected reviewers. Close the prior fingerprint only
-   with discriminating evidence. Otherwise record one no-progress outcome. A
+   paths/criteria, affected drift/evidence, and the recorded delta self-check.
+   Freeze that packet and dispatch each exact owning reviewer once,
+   fresh/read-only, limited to it — all its open fingerprints in that dispatch.
+   Do not rerun broad inventory or unaffected reviewers. Close the prior
+   fingerprint only with discriminating evidence plus an explicit
+   correction-created regression verdict on the touched invariants (acyclic
+   deps, traceability, contract proof, sizing) and every region depending on a
+   changed clause — enumerate dependents via the dep graph and traceability
+   refs, not only patched sites. Otherwise record one no-progress outcome. A
    different Critical/Important invariant needs exact evidence and a new
    fingerprint; a Suggestion, Nit, or FYI cannot keep recovery open. Reconcile
    shared artifact/readiness gates and return to caller or next repair.
@@ -119,11 +128,14 @@ plan declares a root-authored executable workflow file, read
    criterion needs positive, discriminating proof; every slice must be one-pass
    implementable; developer plans need a predicted scorecard. Durable commands
    are portable repository commands, not host wrappers.
-7. **Narrow recheck after edits.** Dispatch exact plan reviewer once per
-   correction/fingerprint (`per correction/fingerprint`) with accepted findings,
-   changed paths/criteria, and new
-   identity. Within one correction, no broad third loop. If it changes plan,
-   fold again. A closed input plus a distinct Critical/Important invariant returns
+7. **Narrow recheck after edits.** Dispatch the exact plan reviewer once per
+   fold — one dispatch covering every open fingerprint, preserving
+   per correction/fingerprint accounting (each checked individually with its
+   accepted findings, changed paths/criteria, new identity, and recorded delta
+   self-check); it must return an explicit correction-created regression
+   verdict over touched invariants plus every dependent of each changed clause
+   (dep-graph and traceability lookup), not only fingerprint closure. Within one correction, no broad
+   third loop. If it changes plan, fold again. A closed input plus a distinct Critical/Important invariant returns
    that new fingerprint as progress. Then close matrix and rerun ID/meaning audit.
 8. **Build readback and readiness.** Add a cited five-line readback to
    `eng-review.md` (artifacts.md §7 rows 1–5): outcome/ACs; IN/OUT/must-NOT; UI direction and architecture/

package/pack/generated/claude/agents/devrites-plan-drafter.md

@@ -53,6 +53,13 @@ principle-exception questions. List them for the root.
 - Do not invoke another agent.
 - Return candidate content only for requested paths. If unfinished, name the exact
   remaining path instead of compressing away a contract.
+- In `repair`, if the full bundle would exceed reliable output, return
+  `Outcome: partial` with complete hunks for a whole-finding prefix in packet
+  order plus `remaining_findings` — a finding is all its sites or none; never
+  split one across returns. The root materializes the partial bundle and
+  re-dispatches the rest. A finding blocked on human-owned information goes in
+  `blocked_findings` with the needed input named — never `remaining_findings`,
+  which is reserved for what another dispatch can complete.
 
 ## Output format
 

package/pack/generated/claude/agents/devrites-slice-wright.md

@@ -140,6 +140,10 @@ return an `Escalation`** when:
   scoped exception or the approach must change. Report the principle and conflict
   in `Escalation`.
 
+A plan-gap or underspecification escalation populates `assumptions` with every
+contract assumption already checked (verified|falsified); the orchestrator's
+batch sweep covers only the unchecked remainder. Never a bare "plan is wrong".
+
 If an answer would change scope or acceptance, do **not** fold it into the slice.
 Return it in `Escalation` so the orchestrator can route it through the Spec Drift
 Guard (`/rite-plan repair`). Respect any AFK budget in the contract.
@@ -174,7 +178,7 @@ reuse: []
 conventions: []
 principles: []
 sources: []
-assumptions: []
+assumptions: [] # plan-gap escalation: every checked contract assumption, verified|falsified
 decisions_stood: [] # irreversible-risk items go to escalation
 dead_ends: []
 escalation: <none | gate + crisp question + proposed answer>

package/pack/generated/claude/skills/rite-build/SKILL.md

@@ -38,8 +38,10 @@ Wright applies anti-slop; root verifies returns and never patches source.
   single-slice isolation when `wright-dispatch.md` preflight + reconcile hold.
 - Exact feature scope only; reject out-of-allowlist diffs; record adjacent issues.
 - Never rerun an unchanged check; re-prove after edits.
-- Unplanned dependency/design-system/gap/repair → Vet/Spec Drift Guard. Ask only
-  for licensing/cost/security/product or explicit architecture-policy decisions.
+- Unplanned dependency/design-system/gap/repair → Vet/Spec Drift Guard batch
+  sweep: every contract-assumption violation recorded before one folded
+  repair+vet. Ask only for licensing/cost/security/product or explicit
+  architecture-policy decisions.
 - Root never edits product source/tests (`.devrites/` + Workflow Artifact only).
   Wright is sole product writer; extras in returned paths/`git diff --name-only` hard-stop.
 - Principles bind; irreversible conflict needs human exception or stop.
@@ -57,8 +59,8 @@ Wright applies anti-slop; root verifies returns and never patches source.
 
 Omitted/`1` ≡ serial; `2`–`10` → path-disjoint fan-out when eligible; else hard refuse.
 All-green serial integrate; one red/gap aborts. Abort with agent-owned plan
-gaps continues via Spec Drift Guard (plan repair + vet inline); do not emit a
-human `Fix`. AFK charges after integrate only. Running lease blocks another
+gaps continues via Spec Drift Guard (batch sweep, one folded plan repair + one
+vet recheck inline); do not emit a human `Fix`. AFK charges after integrate only. Running lease blocks another
 `/rite-build`. Details: `parallel-batch.md`.
 
 ## Execute and reply

package/pack/generated/claude/skills/rite-build/reference/one-slice-cycle.md

@@ -39,7 +39,8 @@ you check yourself against: anything outside it is scope creep or a drift event.
 ## When the slice can't be completed cleanly
 
 - Discovered the plan is wrong → **Spec Drift Guard** (record, classify;
-  agent-owned repair+vet inline; ask only for product/policy/irreversible-risk).
+  sweep every remaining contract assumption, then one folded repair+vet inline;
+  ask only for product/policy/irreversible-risk).
 - Slice is bigger than one cycle → `/rite-plan reslice` inline when AC is
   preserved; do not emit a human Fix.
 - Blocked on a failing dependency → record in `state.md`, `/rite-plan unblock`

package/pack/generated/claude/skills/rite-build/reference/parallel-batch.md

@@ -51,8 +51,9 @@ Lease: `batch_id`, `created_at`, `base_sha`, `n`,
    per integrated sibling; optional `check candidate`.
 8. Cleanup: success removes worktrees/branches. Abort keeps them as repair
    inputs until the root consumes them: agent-owned plan gaps (AC unchanged)
-   follow [`spec-drift-guard.md`](spec-drift-guard.md) — `/rite-plan repair` then
-   `/rite-vet` inline, then cleanup and resume Build. Do not emit
+   follow [`spec-drift-guard.md`](spec-drift-guard.md) — batch-sweep all
+   siblings' contract assumptions, one folded `/rite-plan repair` + one
+   `/rite-vet` recheck inline, then cleanup and resume Build. Do not emit
    `Fix: /rite-plan repair`. Product/policy/irreversible-risk still stops.
 
 ## Engine verbs

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

@@ -24,13 +24,31 @@ other phases reference it here.
      YES, active-slice technical/tool failure → log it and use Build's bounded debug
        recovery. Do not ask for retry authorization and do not re-plan unless the
        durable remaining-work instructions are wrong.
-     YES, durable plan is wrong → log it, save the caller's return cursor, then
-       invoke `/rite-plan repair` and `/rite-vet` inline without a question and resume.
+     YES, durable plan is wrong → run the batch sweep below, log every
+       violation, save the caller's return cursor, then invoke `/rite-plan repair` and `/rite-vet` inline
+       without a question — ONE folded repair for all open entries, ONE
+       recheck for every open fingerprint — and resume.
      NO, product/policy/irreversible-risk decision → ask the user (format below).
 5. Never continue on a known-wrong durable plan. A repaired active-slice implementation
    may continue only after bounded recovery, returned-diff review, and proof gates pass.
 ```
 
+## Batch sweep (before repair)
+
+A durable-plan drift abort never repairs the first gap alone:
+
+1. Verify every remaining statically-checkable contract assumption against the
+   live repo — named paths, symbols/APIs/signatures, routes, commands, dependency
+   versions, contract artifacts. The wright's return names what it falsified;
+   check the rest yourself — existence checks are deterministic, no dispatch.
+2. Record each violation as its own `drift.md` entry/fingerprint; one folded
+   repair + one batched recheck resolves the set.
+3. A recheck-surfaced gap is a new fingerprint with its own budget — loop
+   internally, never hand an intermediate command to the human.
+4. Nothing skips or defers silently: every entry ends resolved, human-escalated,
+   or fingerprint-exhausted. Execution-only gaps (tests, UX, evidence) get the
+   identical path when they surface.
+
 ## User question format
 ```
 I hit spec drift:
@@ -50,7 +68,8 @@ human permission question. Re-plan only when the durable plan changed.
 
 ## Inline return contract
 
-The phase that detected agent-owned drift owns the whole backtrack. Preserve it
+The phase that detected agent-owned drift owns the whole backtrack, batch sweep
+included. Preserve it
 as `return_phase`/`return_next_action`; consume Plan and Vet's nested `STOP`
 boundaries internally; follow any vetted remediation required by the settled
 acceptance; then restore the cursor and resume the failed step. Do not hand an

package/pack/generated/claude/skills/rite-build/reference/wright-dispatch.md

@@ -83,4 +83,7 @@ Opt-in `/rite-build --parallel N` fans out only under [`parallel-batch.md`](para
    attempts is the limit; persist each and never dispatch a fourth related try.
 5. Reconcile returned reuse, conventions, principles, sources, assumptions,
    decisions, dead ends, follow-ups, gates, and touched files. Persist the
-   relevant facts in canonical artifacts, not the wholesale report.
+   relevant facts in canonical artifacts, not the wholesale report. A plan-gap
+   escalation without the checked-assumption list (verified|falsified) is
+   malformed; root sweeps the unchecked remainder per
+   [`spec-drift-guard.md`](spec-drift-guard.md) before repair.

package/pack/generated/claude/skills/rite-plan/SKILL.md

@@ -79,6 +79,11 @@ Before classifying any Reslice, read `.claude/skills/devrites-lib/reference/stan
    require the drafter to apply `one-shot-actions.md` and return the bounded
    diagnostic-amplification design, injective boundary map, per-seam fixtures, and
    collision mutant. Past evidence loss is not terminal. The drafter supplies no bodies.
+   A repair candidate carries a delta self-check scoped to what the patch
+   touches: which intersected invariants it re-verified, with evidence of no
+   correction-created regression. Global re-derivation (ID/edge/HZN counts,
+   acyclicity) runs on materialized artifacts at the step-7 gate — the drafter
+   never re-derives them by exhaustive search.
    Bind exact active `.devrites/work/<slug>/` targets and executable contract; after Vet READY, root
    materializes the exact vetted workflow-artifact paths under
    [`workflow-artifacts.md`](../devrites-lib/reference/standards/workflow-artifacts.md)
@@ -101,7 +106,16 @@ Before classifying any Reslice, read `.claude/skills/devrites-lib/reference/stan
    [task-breakdown](reference/task-breakdown.md). Prefer thin, shippable, verifiable.
    **Completion:** every slice is independently shippable/provable or carries an irreducibility reason.
 5. Reconcile the candidate against steps 3 and 4, then the root updates `plan.md`, `tasks.md`,
-   `state.md`, and appends rationale to `decisions.md`.
+   `state.md`, and appends rationale to `decisions.md`. A rejected candidate
+   (malformed bundle, stale or non-unique anchor) or a drafter `Outcome: gap`
+   is one no-progress outcome on every open fingerprint in the fold; the
+   re-dispatch packet must name the rejection so the same hunks don't recur.
+   A gap naming genuinely human-owned information routes to `/rite-clarify`.
+   A drafter `Outcome: partial` is progress: materialize its complete findings,
+   then re-dispatch a narrowed packet for `remaining_findings` with anchors
+   re-derived from the just-updated files — same repair pass, fresh context.
+   A partial covering zero findings counts as no-progress. Findings in
+   `blocked_findings` route to `/rite-clarify`, never the re-dispatch.
    Any change to `architecture.md`, `plan.md`, `tasks.md`, or `traceability.md` invalidates
    the previous vet verdict: set `Phase: plan`, `Next step: /rite-vet`, and, when
    `eng-review.md` exists, set `Implementation readiness: NEEDS REPLAN`. Never retain READY
@@ -115,8 +129,9 @@ Before classifying any Reslice, read `.claude/skills/devrites-lib/reference/stan
    material assumption, or open blocking/escalating question routes `/rite-clarify`/HITL.
    Restore `CLEAR` only from current evidence.
 7. **Done when:** every slice is sized (builds + proves in one cycle; no slice scoring >3
-   left unjustified), the dependency order is acyclic, every `drift.md` entry you stopped for
-   is marked resolved, revised artifacts agree with each other, no source files changed in
+   left unjustified), the dependency order is acyclic, every open `drift.md` entry
+   was folded in one pass and marked resolved, the delta self-check is recorded,
+   revised artifacts agree with each other, no source files changed in
    `revise` mode, the marked action is complete, and every changed
    plan ends at `/rite-vet` rather than returning directly to build; horizon IDs stay stable,
    reclassifications cite evidence, and no unresolved item vanished. The `Shared contract proof`
@@ -128,5 +143,13 @@ to that caller so it can invoke Vet immediately. The phase boundary is not a
 user-facing stop unless a genuine HITL, safety/access, or exhausted-recovery
 condition was recorded.
 
+When invoked directly with no controlling caller and a planning artifact
+changed, become the caller for the mandated next step: record the return
+cursor, invoke `/rite-vet` inline, and consume its results — `NEEDS REPLAN`
+re-enters repair internally under the fingerprint caps; `NEEDS CLARIFICATION`
+and human-owned gates still reach the user. Stop only at Vet's boundary (READY
+readback; next step `/rite-build`). An unchanged plan keeps its recorded next
+step.
+
 > **Mid-flight discipline.** Do not change product behavior without confirmation or
 > absorb drift silently. See [`anti-patterns`](reference/anti-patterns.md).

package/pack/generated/claude/skills/rite-plan/reference/replan-and-repair.md

@@ -26,12 +26,19 @@ dependency edges.
 
 A drift event stopped the build. Steps:
 
-1. Read the `drift.md` entry and its classification.
+1. Read the `drift.md` entries and their classifications. Fold EVERY open entry
+   and accepted finding for the affected artifacts in ONE pass, never serially.
 2. If the user answered a drift question, encode that decision in `decisions.md`.
 3. Update `spec.md` (only the affected sections) and `plan.md`/`tasks.md` to match
    reality. Adjust acceptance criteria if they were wrong.
-4. Mark the `drift.md` entry **resolved** with the resolution + date.
-5. Resume at the corrected slice.
+4. Mark each `drift.md` entry **resolved** with the resolution + date.
+5. **Self-check the repaired candidate on the delta before handoff** — re-verify
+   every invariant the correction touched (acyclic dependency graph,
+   bidirectional traceability, Shared contract proof vs boundary set, sizing,
+   no correction-created regression) and record the evidence in the Plan
+   checkpoint; Vet's recheck verifies it rather than rediscovering the defect a
+   loop later.
+6. Resume at the corrected slice.
 Never quietly delete a requirement; use the marked action before contract edits.
 
 ## reorder

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

@@ -52,10 +52,14 @@ plan declares a root-authored executable workflow file, read
 - Use the lowest axis band; never average or round thin to ready. Search before
   asking and resolve reversible technical choices. Ask only human-owned choices.
 - Preserve a valid technical return cursor. Agent-owned `NEEDS REPLAN` returns
-  internally to its caller, not to the human.
-- **Recovery recheck is bounded.** A valid cursor plus open fingerprint enters
-  Recovery recheck; it does not start another Full Vet or repeat unaffected
-  axes/reviewers.
+  internally to its caller, not to the human; on a direct invocation there is
+  no caller, so Vet becomes it — record the cursor and invoke `/rite-plan`
+  repair inline under the same fingerprint caps.
+- **Recovery recheck is bounded and batched.** A valid cursor plus open
+  fingerprints enters Recovery recheck; it does not start another Full Vet or
+  repeat unaffected axes/reviewers. One dispatch covers every open fingerprint
+  of the fold — each checked individually — with a mandatory correction-created
+  regression audit.
 <!-- 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
 
@@ -73,10 +77,15 @@ plan declares a root-authored executable workflow file, read
    required account blocks.
 1b. **Recovery recheck.** Require valid return cursor, accepted prior finding,
    exact fingerprint/reproduction, repaired candidate identity, changed
-   paths/criteria, and affected drift/evidence. Freeze that packet and dispatch
-   each exact owning reviewer once, fresh/read-only, limited to it. Do not rerun
-   broad inventory or unaffected reviewers. Close the prior fingerprint only
-   with discriminating evidence. Otherwise record one no-progress outcome. A
+   paths/criteria, affected drift/evidence, and the recorded delta self-check.
+   Freeze that packet and dispatch each exact owning reviewer once,
+   fresh/read-only, limited to it — all its open fingerprints in that dispatch.
+   Do not rerun broad inventory or unaffected reviewers. Close the prior
+   fingerprint only with discriminating evidence plus an explicit
+   correction-created regression verdict on the touched invariants (acyclic
+   deps, traceability, contract proof, sizing) and every region depending on a
+   changed clause — enumerate dependents via the dep graph and traceability
+   refs, not only patched sites. Otherwise record one no-progress outcome. A
    different Critical/Important invariant needs exact evidence and a new
    fingerprint; a Suggestion, Nit, or FYI cannot keep recovery open. Reconcile
    shared artifact/readiness gates and return to caller or next repair.
@@ -119,11 +128,14 @@ plan declares a root-authored executable workflow file, read
    criterion needs positive, discriminating proof; every slice must be one-pass
    implementable; developer plans need a predicted scorecard. Durable commands
    are portable repository commands, not host wrappers.
-7. **Narrow recheck after edits.** Dispatch exact plan reviewer once per
-   correction/fingerprint (`per correction/fingerprint`) with accepted findings,
-   changed paths/criteria, and new
-   identity. Within one correction, no broad third loop. If it changes plan,
-   fold again. A closed input plus a distinct Critical/Important invariant returns
+7. **Narrow recheck after edits.** Dispatch the exact plan reviewer once per
+   fold — one dispatch covering every open fingerprint, preserving
+   per correction/fingerprint accounting (each checked individually with its
+   accepted findings, changed paths/criteria, new identity, and recorded delta
+   self-check); it must return an explicit correction-created regression
+   verdict over touched invariants plus every dependent of each changed clause
+   (dep-graph and traceability lookup), not only fingerprint closure. Within one correction, no broad
+   third loop. If it changes plan, fold again. A closed input plus a distinct Critical/Important invariant returns
    that new fingerprint as progress. Then close matrix and rerun ID/meaning audit.
 8. **Build readback and readiness.** Add a cited five-line readback to
    `eng-review.md` (artifacts.md §7 rows 1–5): outcome/ACs; IN/OUT/must-NOT; UI direction and architecture/

package/pack/generated/codex/agents/devrites-plan-drafter.toml

@@ -51,6 +51,13 @@ principle-exception questions. List them for the root.
 - Do not invoke another agent.
 - Return candidate content only for requested paths. If unfinished, name the exact
   remaining path instead of compressing away a contract.
+- In `repair`, if the full bundle would exceed reliable output, return
+  `Outcome: partial` with complete hunks for a whole-finding prefix in packet
+  order plus `remaining_findings` — a finding is all its sites or none; never
+  split one across returns. The root materializes the partial bundle and
+  re-dispatches the rest. A finding blocked on human-owned information goes in
+  `blocked_findings` with the needed input named — never `remaining_findings`,
+  which is reserved for what another dispatch can complete.
 
 ## Output format