devrites 4.0.2 → 4.0.3

package/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 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`.
 
+## [4.0.3](https://github.com/ViktorsBaikers/DevRites/compare/v4.0.2...v4.0.3) (2026-08-07)
+
+### Fixed
+
+* **deps:** update js-yaml security patch ([d0b066a](https://github.com/ViktorsBaikers/DevRites/commit/d0b066aed4ff4544567fae14eb1fd90a08ef9e6d))
+* **rite:** keep technical backtracking autonomous ([45b17af](https://github.com/ViktorsBaikers/DevRites/commit/45b17af86e18930b983ec49ae399dd9f91f37a52))
+
 ## [4.0.2](https://github.com/ViktorsBaikers/DevRites/compare/v4.0.1...v4.0.2) (2026-08-05)
 
 ### Fixed

package/README.md

@@ -28,7 +28,7 @@ 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:** [`v4.0.2`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v4.0.2): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
+**Status:** [`v4.0.3`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v4.0.3): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
 
 This is the latest published release; `main` may contain unreleased work.
 

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

@@ -45,6 +45,20 @@ After native proof/review, `/rite-seal` runs `devrites-engine check seal <slug>`
 for structure/freshness, not prose. HITL/blocked stops follow
 [Persistence before stopping](#persistence-before-stopping-handoff-discipline).
 
+## Caller-owned technical backtracking
+
+When an active rite invokes an earlier rite inline to repair an agent-owned
+technical gap, the original rite remains the controlling caller. A nested
+rite's `STOP` is a nested phase boundary, not a user-facing handoff. The caller
+re-reads `state.md`, follows the durable return cursor and intermediate
+`next_action`, and resumes its originating phase while no human-owned, safety,
+access, budget, or exhausted-recovery stop is active.
+
+An intermediate `Next step` is cold-resume metadata. Do not ask the human to
+copy routine `/rite-plan repair`, `/rite-vet`, `/rite-build`, or proof-rerun
+commands during the active recovery chain. Only the controlling caller emits
+the final response; standalone phase invocations still stop normally.
+
 ## Final response
 
 Immediately before its final response, each rite loads

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

@@ -25,6 +25,10 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
   `--yolo` never authorizes Git; it reaches only the exact-plan literal-GO and
   native-approval boundary. Red checks run bounded recovery, then block unless
   the remaining decision is human-owned.
+- **Keep routine backtracking internal.** Always follow agent-owned backward edges
+  through repair, Vet, bounded implementation correction, and re-proof inside
+  the active run. A nested phase `STOP` or intermediate `Next step` is not a
+  user handoff; pause only on the shared real stop conditions.
 - **Budget from the post-vet slice count.** Vet may split/add slices.
   `--max-slices N` may lower the cap for a partial run; otherwise build all.
 - **Parse flags only from this invocation.** `--ship`, `--yolo`, `--max-slices`,
@@ -44,8 +48,9 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
   run `/rite-vet` on **every** feature (depth scales: a light pass on simple plans, full rigor on
   big/risky; never skipped). Unattended it auto-applies only *hardening* findings: added test
   requirements, error-handling / failure-mode coverage, tightened scope, reuse-over-rebuild,
-  dependency-order fixes (these never grow acceptance); **any finding that grows scope,
-  adds a slice, or changes acceptance is a blocking pause**, and irreversible-risk findings always
+  dependency-order fixes (these never grow acceptance); acceptance-preserving
+  reslicing or remediation remains agent-owned. **Any finding that grows product
+  scope or changes acceptance is a blocking pause**, and irreversible-risk findings always
   pause. Cross-model is off unless `--cross-model` was armed.
 
 ## Workflow
@@ -76,6 +81,9 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
    built; root charges the AFK budget once per green built slice) → `/rite-prove`
    → `/rite-polish` → `/rite-review` → `/rite-seal`.
    Read each `SKILL.md` and execute it; workspace files carry state, not chat.
+   Follow the loop's backward-edge contract whenever a later phase discovers an
+   agent-owned earlier-phase gap; keep the original return cursor until that
+   phase resumes.
    Immediately after `/rite-vet` and before the first Build dispatch, apply the loop's
    [mutable post-vet budget](reference/loop.md#derive-the-mutable-post-vet-budget)
    contract. **Completion:** the loop reaches Seal GO, or a stop condition is persisted

package/pack/.claude/skills/rite-autocomplete/reference/loop.md

@@ -52,6 +52,25 @@ Read each phase's `SKILL.md` and execute that workflow. Workspace files such as
 | 10 | `/rite-seal` | GO/NO-GO decision (no git here) |
 | 11 | `/rite-ship` | only if seal GO; `--ship` / `--yolo` never authorizes Git and only continues to the exact-plan literal-GO/native-approval boundary |
 
+## Backtrack without handing off
+
+When a later phase finds an agent-owned technical gap in an earlier phase, the
+Autocomplete root remains the caller:
+
+1. Save the originating phase/action in the native return cursor unless a valid
+   one already exists.
+2. Invoke the required repair, Vet, remediation, and proof skills inline. Their
+   `STOP` instructions end only those nested phases.
+3. Re-read `state.md` after each nested phase and follow its intermediate
+   `next_action`; do not hand the intermediate command to the user.
+4. When the prerequisite chain is green, restore and consume the return cursor,
+   resume the originating phase, and continue the forward table.
+
+Count failed corrections by causal fingerprint under `afk-hitl.md`. Ask only
+for a human-owned decision or mandatory safety/access action. Exhausted
+agent-owned recovery stops once with its reproduction and dead ends, never with
+another routine Plan/Vet command.
+
 ## Between phases
 
 - Re-read the active workspace before each phase (don't trust chat memory).

package/pack/.claude/skills/rite-autocomplete/reference/stop-conditions.md

@@ -16,6 +16,15 @@ Regardless of `allow_gates` or `--ship`:
 Red checks are hard non-advance gates. Run bounded `devrites-debug-recovery`;
 on exhaustion, stop as a technical blocker unless human-owned.
 
+## Not a stop: agent-owned backtracking
+
+Agent-owned backtracking is not a stop condition while its causal-fingerprint
+budget remains. The active caller invokes the earlier phase inline, follows Vet
+and any bounded remediation, then resumes the originating phase. Persist
+`Next step` for crash recovery, but do not surface it as a command the human must
+submit. Stop only when recovery is exhausted or the remaining choice is a real
+human/safety/access gate.
+
 ## Stop on gate severity
 
 - `blocking` gate fires → synchronous pause.

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

@@ -24,8 +24,8 @@ 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, run /rite-plan repair without a question,
-       re-vet, then resume.
+     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.
      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.
@@ -47,3 +47,13 @@ Which direction should DevRites take?
 
 Never turn an objective defect, environment repair, tool bug, or proof rerun into a
 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
+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
+intermediate command to the human. The shared three-attempt causal-fingerprint
+cap still applies: exhaustion produces one technical blocker, while a genuinely
+human-owned decision uses the question format below.

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

@@ -35,6 +35,10 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
 - **Root writes; drafter proposes.** Follow
   [`agents.md`](../devrites-lib/reference/standards/agents.md). The controlling chat owns
   human questions, decisions, reconciliation, and all planning-artifact writes.
+- **Nested repair preserves its caller.** When `state.md` contains a valid
+  technical-backtracking return cursor, preserve any valid return cursor
+  byte-for-byte. `/rite-vet` is the next internal prerequisite, not a command to
+  hand back to the human.
 
 ## Workflow
 0. Read `.claude/skills/devrites-lib/reference/standards/core.md` (operating rules) before reshaping anything.
@@ -93,7 +97,8 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
    `eng-review.md` exists, set `Implementation readiness: NEEDS REPLAN`. Never retain READY
    across changed planning inputs. Preserve `Plan approved` only for behavior/acceptance-neutral
    technical repair; clear and reconfirm it when the contract changed. If you stopped for drift,
-   mark the `drift.md` entry resolved.
+   mark the `drift.md` entry resolved. Never remove or overwrite a valid caller
+   return cursor while writing the Plan checkpoint.
 6. If product behavior/acceptance criteria change, confirm through `/rite-clarify` before
    writing, re-close `decision-coverage.md`, then reconcile the plan. After any edit to
    `brief.md`, `spec.md`, `decisions.md`, `assumptions.md`, or `questions.md`, including a
@@ -111,5 +116,10 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
    table or justified no-impact statement must still match the revised boundary set.
    If any check fails, loop back: don't hand off a half-reshaped plan.
 
+When invoked inline by a controlling rite, return the completed Plan checkpoint
+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.
+
 > **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-prove/SKILL.md

@@ -57,6 +57,10 @@ Pull these via `Read` when relevant:
   writes. The proof runner is read-only and validates immutable logs/artifacts.
   Every accepted source/test correction is one bounded
   `devrites-slice-wright` task, never an inline edit.
+- **Prove remains the controlling caller during technical backtracking.** Save
+  its return cursor, invoke Plan/Vet or bounded remediation inline, consume each
+  nested phase boundary, then resume the failed Prove step. Never make the human
+  submit an agent-owned repair, re-vet, or proof-rerun command.
 
 ## Released-workspace refresh entry
 
@@ -80,14 +84,15 @@ failure is a blocker; this Upgrade admission never authorizes source or test cha
    require its `state.md`, and read the cursor directly.
 1. **Confirm all slices built.** Read `spec.md`, `tasks.md`, `state.md`,
    `test-plan.md`, and the full diff.
-   A missing `test-plan.md` returns to Vet; it never authorizes ad hoc proof.
+   A missing `test-plan.md` enters caller-owned Vet backtracking; invoke Vet
+   inline and resume this step. It never authorizes ad hoc proof.
 2. **Discover commands** if not recorded:
    [test-command-discovery](reference/test-command-discovery.md): README, package
    scripts, Makefile, CI configs, Gemfile/Rakefile, pyproject, go.mod, Cargo.toml.
    Discovery only supplies evidence. `test-plan.md` is the sole approved runtime
    command list. If a discovered command is absent from it, do not run or
    silently approve the command: return to the current Vet contract to add and
-   vet it, refresh readiness, then return to Prove.
+   vet it inline, refresh readiness, then return to Prove without a user handoff.
    **Completion:** exact commands are approved in `test-plan.md` or unavailable.
 3. **Execute proof against a frozen candidate.** Run
    `devrites-engine check candidate <slug>` before any approved proof and retain
@@ -123,6 +128,11 @@ failure is a blocker; this Upgrade admission never authorizes source or test cha
    manifest from its actual scoped diff, rerun affected real proof and both
    candidate checks, then dispatch a fresh proof runner. If a fix would exceed
    scope, record a blocker.
+   If triage shows an agent-owned durable-plan error, apply the Spec Drift
+   Guard's inline return contract: preserve Prove as the origin, run repair and
+   Vet inside this invocation, and resume the exact failed proof rung. Ask only
+   for a human-owned decision; causal-fingerprint exhaustion stops once with a
+   technical blocker rather than another phase command.
 8. The root updates `evidence.md`, `browser-evidence.md` (when present),
    `traceability.md`, and `state.md`. Record exactly one binding for the observed
    digest in evidence and browser evidence. New proof goes to canonical

package/pack/.claude/skills/rite-prove/reference/failure-triage.md

@@ -20,6 +20,7 @@ loop to `devrites-debug-recovery`.
 - Quote the real error text; don't paraphrase it away.
 - Don't loosen/delete a failing assertion to get green: investigate whether it's drift.
 - Don't add blanket retries/sleeps to hide flakiness.
-- Three failed fix attempts on the same root cause → escalate: `devrites-debug-recovery`
-  for a hypothesis-driven pass, or ask the user.
+- Three failed fix attempts on the same root cause consume the shared recovery
+  cap: preserve the reproduction and dead ends, then stop once as a technical
+  blocker. Ask only when the remaining decision is human-owned.
 - A failure you can't fix in scope is a recorded **blocker**, not a silent skip.

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

@@ -105,8 +105,8 @@ None.
 | slice_mode | none |
 | risk | none |
 | next_action | <single command + reason> |
-| return_phase | <later phase; retrofit clarification only> |
-| return_next_action | <saved command; retrofit clarification only> |
+| return_phase | <originating later phase; clarification or agent-owned technical backtracking only> |
+| return_next_action | <saved originating command> |
 
 ## Awaiting human
 Only present when status is awaiting_human.
@@ -120,9 +120,16 @@ Only present when status is awaiting_human.
 `state.md` is a compact cursor, not a history file. Put proof in `evidence.md`,
 decisions in `decisions.md`, assumptions in `assumptions.md`, and drift in
 `drift.md`. Omit both `return_*` rows outside a later-phase `/rite-clarify`
-retrofit. The controlling root follows `/rite-clarify`'s native cursor protocol:
-save both fields before later-phase entry, restore and remove both only after a
-contract-neutral CLEAR verdict, and preserve every unrelated Markdown byte.
+retrofit or agent-owned technical backtracking chain.
+
+Before an active caller moves backward, it copies its current phase and
+non-empty action into the two return rows. Nested Plan, Vet, Build, and proof
+work preserves that valid cursor. Once the prerequisite chain is green, the
+controlling caller restores the saved phase/action and removes both rows in one
+rewrite. A real HITL or exhausted-recovery stop retains the cursor for cold
+resume. Never overwrite an existing valid return cursor, and preserve every
+unrelated Markdown byte. `/rite-clarify` applies its stricter native cursor
+protocol below.
 
 `afk_slices_remaining` is mutable runtime state, not `.devrites/AFK`
 configuration. Only the controlling root writes it under the shared

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

@@ -40,6 +40,9 @@ Pull the standard named by the active axis: `principles.md`, `patterns.md`,
 - **Search before asking.** Verify facts and fold reversible technical hardening into the
   plan; ask only human-owned choices under `afk-hitl.md`. Dispatch uses the bounded
   [`agents.md`](../devrites-lib/reference/standards/agents.md) contract.
+- **Honor a recovery origin.** Preserve a valid technical-backtracking return
+  cursor throughout review. Agent-owned `NEEDS REPLAN` returns internally to the
+  controlling caller; it never becomes a request for the human to invoke Plan.
 
 ## Workflow
 0. **Read `.claude/skills/devrites-lib/reference/standards/core.md`** first.
@@ -146,6 +149,11 @@ Pull the standard named by the active axis: `principles.md`, `patterns.md`,
    cross-model integration.
    Completion: the final axis floor clears, an objective technical blocker is recorded, or a
    genuine human-owned gate is recorded.
+   When READY has no pending remediation slice and a valid technical return
+   cursor exists, restore and consume the return cursor instead of defaulting to
+   `/rite-build`, then return the nested result to the controlling caller. If
+   vetted remediation remains, preserve the cursor while the caller follows it;
+   only a real stop condition reaches the human.
 7. **STOP.** Show the Build readback, scope verdict, lowest axis band, closed coverage
    gaps, preflight, action-time checkpoints, and failure-mode criticals; recommend
    `/rite-build` only when the entry contract is ready.

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

@@ -45,6 +45,20 @@ After native proof/review, `/rite-seal` runs `devrites-engine check seal <slug>`
 for structure/freshness, not prose. HITL/blocked stops follow
 [Persistence before stopping](#persistence-before-stopping-handoff-discipline).
 
+## Caller-owned technical backtracking
+
+When an active rite invokes an earlier rite inline to repair an agent-owned
+technical gap, the original rite remains the controlling caller. A nested
+rite's `STOP` is a nested phase boundary, not a user-facing handoff. The caller
+re-reads `state.md`, follows the durable return cursor and intermediate
+`next_action`, and resumes its originating phase while no human-owned, safety,
+access, budget, or exhausted-recovery stop is active.
+
+An intermediate `Next step` is cold-resume metadata. Do not ask the human to
+copy routine `/rite-plan repair`, `/rite-vet`, `/rite-build`, or proof-rerun
+commands during the active recovery chain. Only the controlling caller emits
+the final response; standalone phase invocations still stop normally.
+
 ## Final response
 
 Immediately before its final response, each rite loads

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

@@ -25,6 +25,10 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
   `--yolo` never authorizes Git; it reaches only the exact-plan literal-GO and
   native-approval boundary. Red checks run bounded recovery, then block unless
   the remaining decision is human-owned.
+- **Keep routine backtracking internal.** Always follow agent-owned backward edges
+  through repair, Vet, bounded implementation correction, and re-proof inside
+  the active run. A nested phase `STOP` or intermediate `Next step` is not a
+  user handoff; pause only on the shared real stop conditions.
 - **Budget from the post-vet slice count.** Vet may split/add slices.
   `--max-slices N` may lower the cap for a partial run; otherwise build all.
 - **Parse flags only from this invocation.** `--ship`, `--yolo`, `--max-slices`,
@@ -44,8 +48,9 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
   run `/rite-vet` on **every** feature (depth scales: a light pass on simple plans, full rigor on
   big/risky; never skipped). Unattended it auto-applies only *hardening* findings: added test
   requirements, error-handling / failure-mode coverage, tightened scope, reuse-over-rebuild,
-  dependency-order fixes (these never grow acceptance); **any finding that grows scope,
-  adds a slice, or changes acceptance is a blocking pause**, and irreversible-risk findings always
+  dependency-order fixes (these never grow acceptance); acceptance-preserving
+  reslicing or remediation remains agent-owned. **Any finding that grows product
+  scope or changes acceptance is a blocking pause**, and irreversible-risk findings always
   pause. Cross-model is off unless `--cross-model` was armed.
 
 ## Workflow
@@ -76,6 +81,9 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
    built; root charges the AFK budget once per green built slice) → `/rite-prove`
    → `/rite-polish` → `/rite-review` → `/rite-seal`.
    Read each `SKILL.md` and execute it; workspace files carry state, not chat.
+   Follow the loop's backward-edge contract whenever a later phase discovers an
+   agent-owned earlier-phase gap; keep the original return cursor until that
+   phase resumes.
    Immediately after `/rite-vet` and before the first Build dispatch, apply the loop's
    [mutable post-vet budget](reference/loop.md#derive-the-mutable-post-vet-budget)
    contract. **Completion:** the loop reaches Seal GO, or a stop condition is persisted

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

@@ -52,6 +52,25 @@ Read each phase's `SKILL.md` and execute that workflow. Workspace files such as
 | 10 | `/rite-seal` | GO/NO-GO decision (no git here) |
 | 11 | `/rite-ship` | only if seal GO; `--ship` / `--yolo` never authorizes Git and only continues to the exact-plan literal-GO/native-approval boundary |
 
+## Backtrack without handing off
+
+When a later phase finds an agent-owned technical gap in an earlier phase, the
+Autocomplete root remains the caller:
+
+1. Save the originating phase/action in the native return cursor unless a valid
+   one already exists.
+2. Invoke the required repair, Vet, remediation, and proof skills inline. Their
+   `STOP` instructions end only those nested phases.
+3. Re-read `state.md` after each nested phase and follow its intermediate
+   `next_action`; do not hand the intermediate command to the user.
+4. When the prerequisite chain is green, restore and consume the return cursor,
+   resume the originating phase, and continue the forward table.
+
+Count failed corrections by causal fingerprint under `afk-hitl.md`. Ask only
+for a human-owned decision or mandatory safety/access action. Exhausted
+agent-owned recovery stops once with its reproduction and dead ends, never with
+another routine Plan/Vet command.
+
 ## Between phases
 
 - Re-read the active workspace before each phase (don't trust chat memory).

package/pack/generated/claude/skills/rite-autocomplete/reference/stop-conditions.md

@@ -16,6 +16,15 @@ Regardless of `allow_gates` or `--ship`:
 Red checks are hard non-advance gates. Run bounded `devrites-debug-recovery`;
 on exhaustion, stop as a technical blocker unless human-owned.
 
+## Not a stop: agent-owned backtracking
+
+Agent-owned backtracking is not a stop condition while its causal-fingerprint
+budget remains. The active caller invokes the earlier phase inline, follows Vet
+and any bounded remediation, then resumes the originating phase. Persist
+`Next step` for crash recovery, but do not surface it as a command the human must
+submit. Stop only when recovery is exhausted or the remaining choice is a real
+human/safety/access gate.
+
 ## Stop on gate severity
 
 - `blocking` gate fires → synchronous pause.

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

@@ -24,8 +24,8 @@ 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, run /rite-plan repair without a question,
-       re-vet, then resume.
+     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.
      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.
@@ -47,3 +47,13 @@ Which direction should DevRites take?
 
 Never turn an objective defect, environment repair, tool bug, or proof rerun into a
 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
+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
+intermediate command to the human. The shared three-attempt causal-fingerprint
+cap still applies: exhaustion produces one technical blocker, while a genuinely
+human-owned decision uses the question format below.

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

@@ -35,6 +35,10 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
 - **Root writes; drafter proposes.** Follow
   [`agents.md`](../devrites-lib/reference/standards/agents.md). The controlling chat owns
   human questions, decisions, reconciliation, and all planning-artifact writes.
+- **Nested repair preserves its caller.** When `state.md` contains a valid
+  technical-backtracking return cursor, preserve any valid return cursor
+  byte-for-byte. `/rite-vet` is the next internal prerequisite, not a command to
+  hand back to the human.
 
 ## Workflow
 0. Read `.claude/skills/devrites-lib/reference/standards/core.md` (operating rules) before reshaping anything.
@@ -93,7 +97,8 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
    `eng-review.md` exists, set `Implementation readiness: NEEDS REPLAN`. Never retain READY
    across changed planning inputs. Preserve `Plan approved` only for behavior/acceptance-neutral
    technical repair; clear and reconfirm it when the contract changed. If you stopped for drift,
-   mark the `drift.md` entry resolved.
+   mark the `drift.md` entry resolved. Never remove or overwrite a valid caller
+   return cursor while writing the Plan checkpoint.
 6. If product behavior/acceptance criteria change, confirm through `/rite-clarify` before
    writing, re-close `decision-coverage.md`, then reconcile the plan. After any edit to
    `brief.md`, `spec.md`, `decisions.md`, `assumptions.md`, or `questions.md`, including a
@@ -111,5 +116,10 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
    table or justified no-impact statement must still match the revised boundary set.
    If any check fails, loop back: don't hand off a half-reshaped plan.
 
+When invoked inline by a controlling rite, return the completed Plan checkpoint
+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.
+
 > **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-prove/SKILL.md

@@ -57,6 +57,10 @@ Pull these via `Read` when relevant:
   writes. The proof runner is read-only and validates immutable logs/artifacts.
   Every accepted source/test correction is one bounded
   `devrites-slice-wright` task, never an inline edit.
+- **Prove remains the controlling caller during technical backtracking.** Save
+  its return cursor, invoke Plan/Vet or bounded remediation inline, consume each
+  nested phase boundary, then resume the failed Prove step. Never make the human
+  submit an agent-owned repair, re-vet, or proof-rerun command.
 
 ## Released-workspace refresh entry
 
@@ -80,14 +84,15 @@ failure is a blocker; this Upgrade admission never authorizes source or test cha
    require its `state.md`, and read the cursor directly.
 1. **Confirm all slices built.** Read `spec.md`, `tasks.md`, `state.md`,
    `test-plan.md`, and the full diff.
-   A missing `test-plan.md` returns to Vet; it never authorizes ad hoc proof.
+   A missing `test-plan.md` enters caller-owned Vet backtracking; invoke Vet
+   inline and resume this step. It never authorizes ad hoc proof.
 2. **Discover commands** if not recorded:
    [test-command-discovery](reference/test-command-discovery.md): README, package
    scripts, Makefile, CI configs, Gemfile/Rakefile, pyproject, go.mod, Cargo.toml.
    Discovery only supplies evidence. `test-plan.md` is the sole approved runtime
    command list. If a discovered command is absent from it, do not run or
    silently approve the command: return to the current Vet contract to add and
-   vet it, refresh readiness, then return to Prove.
+   vet it inline, refresh readiness, then return to Prove without a user handoff.
    **Completion:** exact commands are approved in `test-plan.md` or unavailable.
 3. **Execute proof against a frozen candidate.** Run
    `devrites-engine check candidate <slug>` before any approved proof and retain
@@ -123,6 +128,11 @@ failure is a blocker; this Upgrade admission never authorizes source or test cha
    manifest from its actual scoped diff, rerun affected real proof and both
    candidate checks, then dispatch a fresh proof runner. If a fix would exceed
    scope, record a blocker.
+   If triage shows an agent-owned durable-plan error, apply the Spec Drift
+   Guard's inline return contract: preserve Prove as the origin, run repair and
+   Vet inside this invocation, and resume the exact failed proof rung. Ask only
+   for a human-owned decision; causal-fingerprint exhaustion stops once with a
+   technical blocker rather than another phase command.
 8. The root updates `evidence.md`, `browser-evidence.md` (when present),
    `traceability.md`, and `state.md`. Record exactly one binding for the observed
    digest in evidence and browser evidence. New proof goes to canonical

package/pack/generated/claude/skills/rite-prove/reference/failure-triage.md

@@ -20,6 +20,7 @@ loop to `devrites-debug-recovery`.
 - Quote the real error text; don't paraphrase it away.
 - Don't loosen/delete a failing assertion to get green: investigate whether it's drift.
 - Don't add blanket retries/sleeps to hide flakiness.
-- Three failed fix attempts on the same root cause → escalate: `devrites-debug-recovery`
-  for a hypothesis-driven pass, or ask the user.
+- Three failed fix attempts on the same root cause consume the shared recovery
+  cap: preserve the reproduction and dead ends, then stop once as a technical
+  blocker. Ask only when the remaining decision is human-owned.
 - A failure you can't fix in scope is a recorded **blocker**, not a silent skip.

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

@@ -105,8 +105,8 @@ None.
 | slice_mode | none |
 | risk | none |
 | next_action | <single command + reason> |
-| return_phase | <later phase; retrofit clarification only> |
-| return_next_action | <saved command; retrofit clarification only> |
+| return_phase | <originating later phase; clarification or agent-owned technical backtracking only> |
+| return_next_action | <saved originating command> |
 
 ## Awaiting human
 Only present when status is awaiting_human.
@@ -120,9 +120,16 @@ Only present when status is awaiting_human.
 `state.md` is a compact cursor, not a history file. Put proof in `evidence.md`,
 decisions in `decisions.md`, assumptions in `assumptions.md`, and drift in
 `drift.md`. Omit both `return_*` rows outside a later-phase `/rite-clarify`
-retrofit. The controlling root follows `/rite-clarify`'s native cursor protocol:
-save both fields before later-phase entry, restore and remove both only after a
-contract-neutral CLEAR verdict, and preserve every unrelated Markdown byte.
+retrofit or agent-owned technical backtracking chain.
+
+Before an active caller moves backward, it copies its current phase and
+non-empty action into the two return rows. Nested Plan, Vet, Build, and proof
+work preserves that valid cursor. Once the prerequisite chain is green, the
+controlling caller restores the saved phase/action and removes both rows in one
+rewrite. A real HITL or exhausted-recovery stop retains the cursor for cold
+resume. Never overwrite an existing valid return cursor, and preserve every
+unrelated Markdown byte. `/rite-clarify` applies its stricter native cursor
+protocol below.
 
 `afk_slices_remaining` is mutable runtime state, not `.devrites/AFK`
 configuration. Only the controlling root writes it under the shared

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

@@ -40,6 +40,9 @@ Pull the standard named by the active axis: `principles.md`, `patterns.md`,
 - **Search before asking.** Verify facts and fold reversible technical hardening into the
   plan; ask only human-owned choices under `afk-hitl.md`. Dispatch uses the bounded
   [`agents.md`](../devrites-lib/reference/standards/agents.md) contract.
+- **Honor a recovery origin.** Preserve a valid technical-backtracking return
+  cursor throughout review. Agent-owned `NEEDS REPLAN` returns internally to the
+  controlling caller; it never becomes a request for the human to invoke Plan.
 
 ## Workflow
 0. **Read `.claude/skills/devrites-lib/reference/standards/core.md`** first.
@@ -146,6 +149,11 @@ Pull the standard named by the active axis: `principles.md`, `patterns.md`,
    cross-model integration.
    Completion: the final axis floor clears, an objective technical blocker is recorded, or a
    genuine human-owned gate is recorded.
+   When READY has no pending remediation slice and a valid technical return
+   cursor exists, restore and consume the return cursor instead of defaulting to
+   `/rite-build`, then return the nested result to the controlling caller. If
+   vetted remediation remains, preserve the cursor while the caller follows it;
+   only a real stop condition reaches the human.
 7. **STOP.** Show the Build readback, scope verdict, lowest axis band, closed coverage
    gaps, preflight, action-time checkpoints, and failure-mode criticals; recommend
    `/rite-build` only when the entry contract is ready.

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

@@ -45,6 +45,20 @@ After native proof/review, `$rite-seal` runs `devrites-engine check seal <slug>`
 for structure/freshness, not prose. HITL/blocked stops follow
 [Persistence before stopping](#persistence-before-stopping-handoff-discipline).
 
+## Caller-owned technical backtracking
+
+When an active rite invokes an earlier rite inline to repair an agent-owned
+technical gap, the original rite remains the controlling caller. A nested
+rite's `STOP` is a nested phase boundary, not a user-facing handoff. The caller
+re-reads `state.md`, follows the durable return cursor and intermediate
+`next_action`, and resumes its originating phase while no human-owned, safety,
+access, budget, or exhausted-recovery stop is active.
+
+An intermediate `Next step` is cold-resume metadata. Do not ask the human to
+copy routine `$rite-plan repair`, `$rite-vet`, `$rite-build`, or proof-rerun
+commands during the active recovery chain. Only the controlling caller emits
+the final response; standalone phase invocations still stop normally.
+
 ## Final response
 
 Immediately before its final response, each rite loads

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

@@ -25,6 +25,10 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
   `--yolo` never authorizes Git; it reaches only the exact-plan literal-GO and
   native-approval boundary. Red checks run bounded recovery, then block unless
   the remaining decision is human-owned.
+- **Keep routine backtracking internal.** Always follow agent-owned backward edges
+  through repair, Vet, bounded implementation correction, and re-proof inside
+  the active run. A nested phase `STOP` or intermediate `Next step` is not a
+  user handoff; pause only on the shared real stop conditions.
 - **Budget from the post-vet slice count.** Vet may split/add slices.
   `--max-slices N` may lower the cap for a partial run; otherwise build all.
 - **Parse flags only from this invocation.** `--ship`, `--yolo`, `--max-slices`,
@@ -44,8 +48,9 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
   run `$rite-vet` on **every** feature (depth scales: a light pass on simple plans, full rigor on
   big/risky; never skipped). Unattended it auto-applies only *hardening* findings: added test
   requirements, error-handling / failure-mode coverage, tightened scope, reuse-over-rebuild,
-  dependency-order fixes (these never grow acceptance); **any finding that grows scope,
-  adds a slice, or changes acceptance is a blocking pause**, and irreversible-risk findings always
+  dependency-order fixes (these never grow acceptance); acceptance-preserving
+  reslicing or remediation remains agent-owned. **Any finding that grows product
+  scope or changes acceptance is a blocking pause**, and irreversible-risk findings always
   pause. Cross-model is off unless `--cross-model` was armed.
 
 ## Workflow
@@ -76,6 +81,9 @@ default and **Full** for high-risk scope or explicit `--full`; profiles are defi
    built; root charges the AFK budget once per green built slice) → `$rite-prove`
    → `$rite-polish` → `$rite-review` → `$rite-seal`.
    Read each `SKILL.md` and execute it; workspace files carry state, not chat.
+   Follow the loop's backward-edge contract whenever a later phase discovers an
+   agent-owned earlier-phase gap; keep the original return cursor until that
+   phase resumes.
    Immediately after `$rite-vet` and before the first Build dispatch, apply the loop's
    [mutable post-vet budget](reference/loop.md#derive-the-mutable-post-vet-budget)
    contract. **Completion:** the loop reaches Seal GO, or a stop condition is persisted

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

@@ -52,6 +52,25 @@ Read each phase's `SKILL.md` and execute that workflow. Workspace files such as
 | 10 | `$rite-seal` | GO/NO-GO decision (no git here) |
 | 11 | `$rite-ship` | only if seal GO; `--ship` / `--yolo` never authorizes Git and only continues to the exact-plan literal-GO/native-approval boundary |
 
+## Backtrack without handing off
+
+When a later phase finds an agent-owned technical gap in an earlier phase, the
+Autocomplete root remains the caller:
+
+1. Save the originating phase/action in the native return cursor unless a valid
+   one already exists.
+2. Invoke the required repair, Vet, remediation, and proof skills inline. Their
+   `STOP` instructions end only those nested phases.
+3. Re-read `state.md` after each nested phase and follow its intermediate
+   `next_action`; do not hand the intermediate command to the user.
+4. When the prerequisite chain is green, restore and consume the return cursor,
+   resume the originating phase, and continue the forward table.
+
+Count failed corrections by causal fingerprint under `afk-hitl.md`. Ask only
+for a human-owned decision or mandatory safety/access action. Exhausted
+agent-owned recovery stops once with its reproduction and dead ends, never with
+another routine Plan/Vet command.
+
 ## Between phases
 
 - Re-read the active workspace before each phase (don't trust chat memory).

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

@@ -16,6 +16,15 @@ Regardless of `allow_gates` or `--ship`:
 Red checks are hard non-advance gates. Run bounded `devrites-debug-recovery`;
 on exhaustion, stop as a technical blocker unless human-owned.
 
+## Not a stop: agent-owned backtracking
+
+Agent-owned backtracking is not a stop condition while its causal-fingerprint
+budget remains. The active caller invokes the earlier phase inline, follows Vet
+and any bounded remediation, then resumes the originating phase. Persist
+`Next step` for crash recovery, but do not surface it as a command the human must
+submit. Stop only when recovery is exhausted or the remaining choice is a real
+human/safety/access gate.
+
 ## Stop on gate severity
 
 - `blocking` gate fires → synchronous pause.

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

@@ -24,8 +24,8 @@ 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, run $rite-plan repair without a question,
-       re-vet, then resume.
+     YES, durable plan is wrong → log it, save the caller's return cursor, then
+       invoke `$rite-plan repair` and `$rite-vet` inline without a question and resume.
      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.
@@ -47,3 +47,13 @@ Which direction should DevRites take?
 
 Never turn an objective defect, environment repair, tool bug, or proof rerun into a
 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
+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
+intermediate command to the human. The shared three-attempt causal-fingerprint
+cap still applies: exhaustion produces one technical blocker, while a genuinely
+human-owned decision uses the question format below.

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

@@ -35,6 +35,10 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
 - **Root writes; drafter proposes.** Follow
   [`agents.md`](../devrites-lib/reference/standards/agents.md). The controlling chat owns
   human questions, decisions, reconciliation, and all planning-artifact writes.
+- **Nested repair preserves its caller.** When `state.md` contains a valid
+  technical-backtracking return cursor, preserve any valid return cursor
+  byte-for-byte. `$rite-vet` is the next internal prerequisite, not a command to
+  hand back to the human.
 
 ## Workflow
 0. Read `.agents/skills/devrites-lib/reference/standards/core.md` (operating rules) before reshaping anything.
@@ -93,7 +97,8 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
    `eng-review.md` exists, set `Implementation readiness: NEEDS REPLAN`. Never retain READY
    across changed planning inputs. Preserve `Plan approved` only for behavior/acceptance-neutral
    technical repair; clear and reconfirm it when the contract changed. If you stopped for drift,
-   mark the `drift.md` entry resolved.
+   mark the `drift.md` entry resolved. Never remove or overwrite a valid caller
+   return cursor while writing the Plan checkpoint.
 6. If product behavior/acceptance criteria change, confirm through `$rite-clarify` before
    writing, re-close `decision-coverage.md`, then reconcile the plan. After any edit to
    `brief.md`, `spec.md`, `decisions.md`, `assumptions.md`, or `questions.md`, including a
@@ -111,5 +116,10 @@ Pull `development-workflow.md` via `Read` when reshaping slice cadence or DoD cr
    table or justified no-impact statement must still match the revised boundary set.
    If any check fails, loop back: don't hand off a half-reshaped plan.
 
+When invoked inline by a controlling rite, return the completed Plan checkpoint
+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.
+
 > **Mid-flight discipline.** Do not change product behavior without confirmation or
 > absorb drift silently. See [`anti-patterns`](reference/anti-patterns.md).

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

@@ -57,6 +57,10 @@ Pull these via `Read` when relevant:
   writes. The proof runner is read-only and validates immutable logs/artifacts.
   Every accepted source/test correction is one bounded
   `devrites-slice-wright` task, never an inline edit.
+- **Prove remains the controlling caller during technical backtracking.** Save
+  its return cursor, invoke Plan/Vet or bounded remediation inline, consume each
+  nested phase boundary, then resume the failed Prove step. Never make the human
+  submit an agent-owned repair, re-vet, or proof-rerun command.
 
 ## Released-workspace refresh entry
 
@@ -80,14 +84,15 @@ failure is a blocker; this Upgrade admission never authorizes source or test cha
    require its `state.md`, and read the cursor directly.
 1. **Confirm all slices built.** Read `spec.md`, `tasks.md`, `state.md`,
    `test-plan.md`, and the full diff.
-   A missing `test-plan.md` returns to Vet; it never authorizes ad hoc proof.
+   A missing `test-plan.md` enters caller-owned Vet backtracking; invoke Vet
+   inline and resume this step. It never authorizes ad hoc proof.
 2. **Discover commands** if not recorded:
    [test-command-discovery](reference/test-command-discovery.md): README, package
    scripts, Makefile, CI configs, Gemfile/Rakefile, pyproject, go.mod, Cargo.toml.
    Discovery only supplies evidence. `test-plan.md` is the sole approved runtime
    command list. If a discovered command is absent from it, do not run or
    silently approve the command: return to the current Vet contract to add and
-   vet it, refresh readiness, then return to Prove.
+   vet it inline, refresh readiness, then return to Prove without a user handoff.
    **Completion:** exact commands are approved in `test-plan.md` or unavailable.
 3. **Execute proof against a frozen candidate.** Run
    `devrites-engine check candidate <slug>` before any approved proof and retain
@@ -123,6 +128,11 @@ failure is a blocker; this Upgrade admission never authorizes source or test cha
    manifest from its actual scoped diff, rerun affected real proof and both
    candidate checks, then dispatch a fresh proof runner. If a fix would exceed
    scope, record a blocker.
+   If triage shows an agent-owned durable-plan error, apply the Spec Drift
+   Guard's inline return contract: preserve Prove as the origin, run repair and
+   Vet inside this invocation, and resume the exact failed proof rung. Ask only
+   for a human-owned decision; causal-fingerprint exhaustion stops once with a
+   technical blocker rather than another phase command.
 8. The root updates `evidence.md`, `browser-evidence.md` (when present),
    `traceability.md`, and `state.md`. Record exactly one binding for the observed
    digest in evidence and browser evidence. New proof goes to canonical

package/pack/generated/codex/skills/rite-prove/reference/failure-triage.md

@@ -20,6 +20,7 @@ loop to `devrites-debug-recovery`.
 - Quote the real error text; don't paraphrase it away.
 - Don't loosen/delete a failing assertion to get green: investigate whether it's drift.
 - Don't add blanket retries/sleeps to hide flakiness.
-- Three failed fix attempts on the same root cause → escalate: `devrites-debug-recovery`
-  for a hypothesis-driven pass, or ask the user.
+- Three failed fix attempts on the same root cause consume the shared recovery
+  cap: preserve the reproduction and dead ends, then stop once as a technical
+  blocker. Ask only when the remaining decision is human-owned.
 - A failure you can't fix in scope is a recorded **blocker**, not a silent skip.

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

@@ -105,8 +105,8 @@ None.
 | slice_mode | none |
 | risk | none |
 | next_action | <single command + reason> |
-| return_phase | <later phase; retrofit clarification only> |
-| return_next_action | <saved command; retrofit clarification only> |
+| return_phase | <originating later phase; clarification or agent-owned technical backtracking only> |
+| return_next_action | <saved originating command> |
 
 ## Awaiting human
 Only present when status is awaiting_human.
@@ -120,9 +120,16 @@ Only present when status is awaiting_human.
 `state.md` is a compact cursor, not a history file. Put proof in `evidence.md`,
 decisions in `decisions.md`, assumptions in `assumptions.md`, and drift in
 `drift.md`. Omit both `return_*` rows outside a later-phase `$rite-clarify`
-retrofit. The controlling root follows `$rite-clarify`'s native cursor protocol:
-save both fields before later-phase entry, restore and remove both only after a
-contract-neutral CLEAR verdict, and preserve every unrelated Markdown byte.
+retrofit or agent-owned technical backtracking chain.
+
+Before an active caller moves backward, it copies its current phase and
+non-empty action into the two return rows. Nested Plan, Vet, Build, and proof
+work preserves that valid cursor. Once the prerequisite chain is green, the
+controlling caller restores the saved phase/action and removes both rows in one
+rewrite. A real HITL or exhausted-recovery stop retains the cursor for cold
+resume. Never overwrite an existing valid return cursor, and preserve every
+unrelated Markdown byte. `$rite-clarify` applies its stricter native cursor
+protocol below.
 
 `afk_slices_remaining` is mutable runtime state, not `.devrites/AFK`
 configuration. Only the controlling root writes it under the shared

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

@@ -40,6 +40,9 @@ Pull the standard named by the active axis: `principles.md`, `patterns.md`,
 - **Search before asking.** Verify facts and fold reversible technical hardening into the
   plan; ask only human-owned choices under `afk-hitl.md`. Dispatch uses the bounded
   [`agents.md`](../devrites-lib/reference/standards/agents.md) contract.
+- **Honor a recovery origin.** Preserve a valid technical-backtracking return
+  cursor throughout review. Agent-owned `NEEDS REPLAN` returns internally to the
+  controlling caller; it never becomes a request for the human to invoke Plan.
 
 ## Workflow
 0. **Read `.agents/skills/devrites-lib/reference/standards/core.md`** first.
@@ -146,6 +149,11 @@ Pull the standard named by the active axis: `principles.md`, `patterns.md`,
    cross-model integration.
    Completion: the final axis floor clears, an objective technical blocker is recorded, or a
    genuine human-owned gate is recorded.
+   When READY has no pending remediation slice and a valid technical return
+   cursor exists, restore and consume the return cursor instead of defaulting to
+   `$rite-build`, then return the nested result to the controlling caller. If
+   vetted remediation remains, preserve the cursor while the caller follows it;
+   only a real stop condition reaches the human.
 7. **STOP.** Show the Build readback, scope verdict, lowest axis band, closed coverage
    gaps, preflight, action-time checkpoints, and failure-mode criticals; recommend
    `$rite-build` only when the entry contract is ready.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "devrites",
-  "version": "4.0.2",
+  "version": "4.0.3",
   "description": "DevRites: a disciplined senior-engineer workflow pack for Claude Code and Codex",
   "license": "SEE LICENSE IN LICENSE",
   "homepage": "https://github.com/ViktorsBaikers/DevRites#readme",