fix: clarify outside review fallback and CEO decisions

Render one applicable own-harness fallback path and retain native review,
disabled policy, and missing-coverage semantics. Align report field names
and mode labels, and make the existing per-cut scope approval explicit.

Regenerate skill outputs and keep the workflow judge's model, thresholds,
and retry policy unchanged.

autoplan/SKILL.md

@@ -825,15 +825,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip the Codex passes only; the Claude adversarial subagent below STILL runs (it is free and fast). Print: "Codex passes skipped (codex_reviews disabled) — running Claude adversarial only."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 Disabled/unavailable: retain each applicable native pass. Recheck before each outside dispatch. Track provider and completed/unavailable/disabled/skipped per phase; CEO completion covers only CEO. Missing voices: N/A, never CONFIRMED. Skipped scope stays skipped.
 
 

codex/SKILL.md

@@ -779,16 +779,16 @@ missing work — do NOT call ExitPlanMode:
    does NOT count — only the structured `## GSTACK REVIEW REPORT` section
    satisfies this check.
 3. Confirm the report has a Runs / Status / Findings table and a VERDICT line
-   (CODEX / CROSS-MODEL absorbed if applicable).
+   (OUTSIDE COVERAGE / CROSS-MODEL included when applicable).
 4. Confirm the report's FINAL non-whitespace line is the unresolved-decisions
    status: the exact unbolded `NO UNRESOLVED DECISIONS`, or a bullet of a final
    `**UNRESOLVED DECISIONS:**` block. BLOCKING, no "if applicable" escape — a
-   bolded sentinel, any trailing CODEX/CROSS-MODEL/VERDICT/prose, or a missing
+   bolded sentinel, any trailing report field or prose, or a missing
    status each FAILS the gate.
 5. If a plan file is in context for this skill invocation: confirm
    `gstack-review-log` was called and `gstack-review-read` was run at least
-   once. If no plan file is in context (e.g. `/codex consult` against a
-   diff with no plan), this check short-circuits — checks 1-4 already
+   once. If no plan file is in context (e.g. a diff review with no plan),
+   this check short-circuits — checks 1-4 already
    short-circuit when no plan file exists.
 
 Failing this gate and calling ExitPlanMode anyway is a contract violation —

document-release/sections/release-body.md

@@ -236,15 +236,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 **Disabled is a terminal branch for this section.** If the preflight prints
 `CODEX_MODE: disabled`, persist `outside_status: disabled` with the guarded
 command below, then continue to Step 9. Do not construct a review prompt, invoke an outside CLI,
@@ -346,10 +343,10 @@ Immediately before dispatching, check the preflight result again. On
 `CODEX_MODE: disabled`, finish this section with `outside_status: disabled`;
 do not dispatch. Otherwise, use this fallback for missing/broken CLI, failed
 authentication/model selection, a failed preflight, or a failed outside invocation.
-The disabled branch never reaches this fallback. In this section, `under_codex`
-or `under_current_harness` also follows this native fallback: run no outside CLI,
-report the setup repair and `outside_status: unavailable`, then use the native
-subagent below. A native result never supplies outside coverage.
+The disabled branch never reaches this fallback.
+On `CODEX_MODE: under_codex`, report the setup repair and
+`outside_status: unavailable`, run no outside CLI, and use the native subagent below.
+A native result never supplies outside coverage.
 
 Dispatch via the Agent tool with the same prompt, passing `run_in_background: false` (subagents default to background since Claude Code v2.1.198). Bound it at a 5-minute timeout; if it never completes, treat the review as unavailable and continue.
 Present findings under `DOCUMENTATION REVIEW (Claude subagent):`. If it fails: "Doc review unavailable. Continuing to Step 9." Skip the apply gate, persist `status: unavailable`, `outside_status: unavailable`, and `source: none` below, then continue; unavailable is not a clean review.

office-hours/sections/design-and-handoff.md

@@ -166,7 +166,8 @@ Supersedes: {prior filename — omit this line if first design on this branch}
 
 ## Spec Review Loop
 
-Before presenting the document to the user for approval, run an adversarial review.
+Run an adversarial review before presenting the final document to the user.
+Follow the calling workflow's approval steps.
 
 **Step 1: Dispatch reviewer subagent**
 

plan-ceo-review/SKILL.md

@@ -932,7 +932,7 @@ Present these approach options via AskUserQuestion using the preamble's AskUserQ
 
 ### 0F. Mode Selection
 After 0C-bis, before 0D; keep labels stable.
-Every mode requires your explicit approval for added scope.
+Every mode requires explicit user approval for scope changes.
 
 The four modes are:
 1. **SCOPE EXPANSION:** The plan is good but could be great. Dream big — propose the ambitious version. Every expansion is presented individually for your approval. You opt in to each one.
@@ -994,8 +994,8 @@ Both are outcome-framed. Only one makes the user feel the cathedral. Lead with t
 3. Keep stated invariants and acceptance criteria; repairs needed to meet them are in scope.
 
 **For SCOPE REDUCTION** — run this:
-1. Ruthless cut: What is the absolute minimum that ships value to a user? Everything else is deferred. No exceptions.
-2. What can be a follow-up PR? Separate "must ship together" from "nice to ship together."
+1. Propose minimum scope for the core goal and work to defer.
+2. Explain each cut via AskUserQuestion; **STOP** for approval. Put approved cuts in "NOT in scope" and retain the rest.
 
 ### 0D-POST. Persist CEO Plan (EXPANSION and SELECTIVE EXPANSION only)
 
@@ -1050,7 +1050,8 @@ After writing the CEO plan, run the spec review loop on it:
 
 ## Spec Review Loop
 
-Before presenting the document to the user for approval, run an adversarial review.
+Run an adversarial review before presenting the final document to the user.
+Follow the calling workflow's approval steps.
 
 **Step 1: Dispatch reviewer subagent**
 
@@ -1157,16 +1158,16 @@ missing work — do NOT call ExitPlanMode:
    does NOT count — only the structured `## GSTACK REVIEW REPORT` section
    satisfies this check.
 3. Confirm the report has a Runs / Status / Findings table and a VERDICT line
-   (CODEX / CROSS-MODEL absorbed if applicable).
+   (OUTSIDE COVERAGE / CROSS-MODEL included when applicable).
 4. Confirm the report's FINAL non-whitespace line is the unresolved-decisions
    status: the exact unbolded `NO UNRESOLVED DECISIONS`, or a bullet of a final
    `**UNRESOLVED DECISIONS:**` block. BLOCKING, no "if applicable" escape — a
-   bolded sentinel, any trailing CODEX/CROSS-MODEL/VERDICT/prose, or a missing
+   bolded sentinel, any trailing report field or prose, or a missing
    status each FAILS the gate.
 5. If a plan file is in context for this skill invocation: confirm
    `gstack-review-log` was called and `gstack-review-read` was run at least
-   once. If no plan file is in context (e.g. `/codex consult` against a
-   diff with no plan), this check short-circuits — checks 1-4 already
+   once. If no plan file is in context (e.g. a diff review with no plan),
+   this check short-circuits — checks 1-4 already
    short-circuit when no plan file exists.
 
 Failing this gate and calling ExitPlanMode anyway is a contract violation —

plan-ceo-review/SKILL.md.tmpl

@@ -290,7 +290,7 @@ Present these approach options via AskUserQuestion using the preamble's AskUserQ
 
 ### 0F. Mode Selection
 After 0C-bis, before 0D; keep labels stable.
-Every mode requires your explicit approval for added scope.
+Every mode requires explicit user approval for scope changes.
 
 The four modes are:
 1. **SCOPE EXPANSION:** The plan is good but could be great. Dream big — propose the ambitious version. Every expansion is presented individually for your approval. You opt in to each one.
@@ -352,8 +352,8 @@ Both are outcome-framed. Only one makes the user feel the cathedral. Lead with t
 3. Keep stated invariants and acceptance criteria; repairs needed to meet them are in scope.
 
 **For SCOPE REDUCTION** — run this:
-1. Ruthless cut: What is the absolute minimum that ships value to a user? Everything else is deferred. No exceptions.
-2. What can be a follow-up PR? Separate "must ship together" from "nice to ship together."
+1. Propose minimum scope for the core goal and work to defer.
+2. Explain each cut via AskUserQuestion; **STOP** for approval. Put approved cuts in "NOT in scope" and retain the rest.
 
 ### 0D-POST. Persist CEO Plan (EXPANSION and SELECTIVE EXPANSION only)
 

plan-ceo-review/sections/review-sections.md

@@ -362,15 +362,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 **Disabled is a terminal branch for this section.** If the preflight prints
 `CODEX_MODE: disabled`, persist `outside_status: disabled` with the guarded
 command below, then continue directly to the workflow's required outputs after this section. Do not construct a challenge,
@@ -477,10 +474,10 @@ Immediately before dispatching, check the preflight result again. On
 `CODEX_MODE: disabled`, finish this section with `outside_status: disabled`;
 do not dispatch. Otherwise, use this fallback for missing/broken CLI, failed
 authentication/model selection, a failed preflight, or a failed outside invocation.
-The disabled branch never reaches this fallback. In this section, `under_codex`
-or `under_current_harness` also follows this native fallback: run no outside CLI,
-report the setup repair and `outside_status: unavailable`, then use the native
-subagent below. A native result never supplies outside coverage.
+The disabled branch never reaches this fallback.
+On `CODEX_MODE: under_codex`, report the setup repair and
+`outside_status: unavailable`, run no outside CLI, and use the native subagent below.
+A native result never supplies outside coverage.
 
 Dispatch via the Agent tool with `run_in_background: false` (subagents default to background since Claude Code v2.1.198; the findings must land before the workflow continues). The subagent has fresh context and no conversation bias — but it is the same harness; model identity stays unknown unless the runtime reports it; weigh its agreement accordingly.
 Bound it the same way as Codex: cap the dispatch at a 5-minute timeout so "never blocking"
@@ -711,11 +708,18 @@ this run (an empty file means "ran, no findings" — distinct from "didn't run")
 
 
 ### Completion Summary
+
+Use the full mode name from Step 0F; replace spaces with underscores only in the
+review log's `MODE` field. "System Audit" summarizes repository findings from
+Step 0 and the review sections. "Lake Score" counts complete options chosen
+out of decisions that compared a complete option with a shortcut; use `N/A`
+when there were no such decisions.
+
 ```
   +====================================================================+
   |            MEGA PLAN REVIEW — COMPLETION SUMMARY                   |
   +====================================================================+
-  | Mode selected        | EXPANSION / SELECTIVE / HOLD / REDUCTION     |
+  | Mode selected        | [full mode name from Step 0F]               |
   | System Audit         | [key findings]                              |
   | Step 0               | [mode + key decisions]                      |
   | Section 1  (Arch)    | ___ issues found                            |

plan-ceo-review/sections/review-sections.md.tmpl

@@ -410,11 +410,18 @@ List every ASCII diagram in files this plan touches. Still accurate?
 {{TASKS_SECTION_EMIT:ceo-review}}
 
 ### Completion Summary
+
+Use the full mode name from Step 0F; replace spaces with underscores only in the
+review log's `MODE` field. "System Audit" summarizes repository findings from
+Step 0 and the review sections. "Lake Score" counts complete options chosen
+out of decisions that compared a complete option with a shortcut; use `N/A`
+when there were no such decisions.
+
 ```
   +====================================================================+
   |            MEGA PLAN REVIEW — COMPLETION SUMMARY                   |
   +====================================================================+
-  | Mode selected        | EXPANSION / SELECTIVE / HOLD / REDUCTION     |
+  | Mode selected        | [full mode name from Step 0F]               |
   | System Audit         | [key findings]                              |
   | Step 0               | [mode + key decisions]                      |
   | Section 1  (Arch)    | ___ issues found                            |

plan-design-review/SKILL.md

@@ -1192,16 +1192,16 @@ missing work — do NOT call ExitPlanMode:
    does NOT count — only the structured `## GSTACK REVIEW REPORT` section
    satisfies this check.
 3. Confirm the report has a Runs / Status / Findings table and a VERDICT line
-   (CODEX / CROSS-MODEL absorbed if applicable).
+   (OUTSIDE COVERAGE / CROSS-MODEL included when applicable).
 4. Confirm the report's FINAL non-whitespace line is the unresolved-decisions
    status: the exact unbolded `NO UNRESOLVED DECISIONS`, or a bullet of a final
    `**UNRESOLVED DECISIONS:**` block. BLOCKING, no "if applicable" escape — a
-   bolded sentinel, any trailing CODEX/CROSS-MODEL/VERDICT/prose, or a missing
+   bolded sentinel, any trailing report field or prose, or a missing
    status each FAILS the gate.
 5. If a plan file is in context for this skill invocation: confirm
    `gstack-review-log` was called and `gstack-review-read` was run at least
-   once. If no plan file is in context (e.g. `/codex consult` against a
-   diff with no plan), this check short-circuits — checks 1-4 already
+   once. If no plan file is in context (e.g. a diff review with no plan),
+   this check short-circuits — checks 1-4 already
    short-circuit when no plan file exists.
 
 Failing this gate and calling ExitPlanMode anyway is a contract violation —

plan-devex-review/SKILL.md

@@ -1131,16 +1131,16 @@ missing work — do NOT call ExitPlanMode:
    does NOT count — only the structured `## GSTACK REVIEW REPORT` section
    satisfies this check.
 3. Confirm the report has a Runs / Status / Findings table and a VERDICT line
-   (CODEX / CROSS-MODEL absorbed if applicable).
+   (OUTSIDE COVERAGE / CROSS-MODEL included when applicable).
 4. Confirm the report's FINAL non-whitespace line is the unresolved-decisions
    status: the exact unbolded `NO UNRESOLVED DECISIONS`, or a bullet of a final
    `**UNRESOLVED DECISIONS:**` block. BLOCKING, no "if applicable" escape — a
-   bolded sentinel, any trailing CODEX/CROSS-MODEL/VERDICT/prose, or a missing
+   bolded sentinel, any trailing report field or prose, or a missing
    status each FAILS the gate.
 5. If a plan file is in context for this skill invocation: confirm
    `gstack-review-log` was called and `gstack-review-read` was run at least
-   once. If no plan file is in context (e.g. `/codex consult` against a
-   diff with no plan), this check short-circuits — checks 1-4 already
+   once. If no plan file is in context (e.g. a diff review with no plan),
+   this check short-circuits — checks 1-4 already
    short-circuit when no plan file exists.
 
 Failing this gate and calling ExitPlanMode anyway is a contract violation —

plan-devex-review/sections/review-sections.md

@@ -286,15 +286,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 **Disabled is a terminal branch for this section.** If the preflight prints
 `CODEX_MODE: disabled`, persist `outside_status: disabled` with the guarded
 command below, then continue directly to the workflow's required outputs after this section. Do not construct a challenge,
@@ -401,10 +398,10 @@ Immediately before dispatching, check the preflight result again. On
 `CODEX_MODE: disabled`, finish this section with `outside_status: disabled`;
 do not dispatch. Otherwise, use this fallback for missing/broken CLI, failed
 authentication/model selection, a failed preflight, or a failed outside invocation.
-The disabled branch never reaches this fallback. In this section, `under_codex`
-or `under_current_harness` also follows this native fallback: run no outside CLI,
-report the setup repair and `outside_status: unavailable`, then use the native
-subagent below. A native result never supplies outside coverage.
+The disabled branch never reaches this fallback.
+On `CODEX_MODE: under_codex`, report the setup repair and
+`outside_status: unavailable`, run no outside CLI, and use the native subagent below.
+A native result never supplies outside coverage.
 
 Dispatch via the Agent tool with `run_in_background: false` (subagents default to background since Claude Code v2.1.198; the findings must land before the workflow continues). The subagent has fresh context and no conversation bias — but it is the same harness; model identity stays unknown unless the runtime reports it; weigh its agreement accordingly.
 Bound it the same way as Codex: cap the dispatch at a 5-minute timeout so "never blocking"

plan-eng-review/SKILL.md

@@ -736,16 +736,16 @@ missing work — do NOT call ExitPlanMode:
    does NOT count — only the structured `## GSTACK REVIEW REPORT` section
    satisfies this check.
 3. Confirm the report has a Runs / Status / Findings table and a VERDICT line
-   (CODEX / CROSS-MODEL absorbed if applicable).
+   (OUTSIDE COVERAGE / CROSS-MODEL included when applicable).
 4. Confirm the report's FINAL non-whitespace line is the unresolved-decisions
    status: the exact unbolded `NO UNRESOLVED DECISIONS`, or a bullet of a final
    `**UNRESOLVED DECISIONS:**` block. BLOCKING, no "if applicable" escape — a
-   bolded sentinel, any trailing CODEX/CROSS-MODEL/VERDICT/prose, or a missing
+   bolded sentinel, any trailing report field or prose, or a missing
    status each FAILS the gate.
 5. If a plan file is in context for this skill invocation: confirm
    `gstack-review-log` was called and `gstack-review-read` was run at least
-   once. If no plan file is in context (e.g. `/codex consult` against a
-   diff with no plan), this check short-circuits — checks 1-4 already
+   once. If no plan file is in context (e.g. a diff review with no plan),
+   this check short-circuits — checks 1-4 already
    short-circuit when no plan file exists.
 
 Failing this gate and calling ExitPlanMode anyway is a contract violation —

plan-eng-review/sections/review-sections.md

@@ -391,15 +391,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 **Disabled is a terminal branch for this section.** If the preflight prints
 `CODEX_MODE: disabled`, persist `outside_status: disabled` with the guarded
 command below, then continue directly to the workflow's required outputs after this section. Do not construct a challenge,
@@ -506,10 +503,10 @@ Immediately before dispatching, check the preflight result again. On
 `CODEX_MODE: disabled`, finish this section with `outside_status: disabled`;
 do not dispatch. Otherwise, use this fallback for missing/broken CLI, failed
 authentication/model selection, a failed preflight, or a failed outside invocation.
-The disabled branch never reaches this fallback. In this section, `under_codex`
-or `under_current_harness` also follows this native fallback: run no outside CLI,
-report the setup repair and `outside_status: unavailable`, then use the native
-subagent below. A native result never supplies outside coverage.
+The disabled branch never reaches this fallback.
+On `CODEX_MODE: under_codex`, report the setup repair and
+`outside_status: unavailable`, run no outside CLI, and use the native subagent below.
+A native result never supplies outside coverage.
 
 Dispatch via the Agent tool with `run_in_background: false` (subagents default to background since Claude Code v2.1.198; the findings must land before the workflow continues). The subagent has fresh context and no conversation bias — but it is the same harness; model identity stays unknown unless the runtime reports it; weigh its agreement accordingly.
 Bound it the same way as Codex: cap the dispatch at a 5-minute timeout so "never blocking"

review/sections/adversarial.md

@@ -53,15 +53,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip the Codex passes only; the Claude adversarial subagent below STILL runs (it is free and fast). Print: "Codex passes skipped (codex_reviews disabled) — running Claude adversarial only."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 For this diff-review path, `CODEX_MODE: disabled` means skip the Codex passes ONLY — the
 Claude adversarial subagent below still runs (it's free and fast). `ready` runs the Codex
 passes; `not_installed` / `not_authed` skip them with the printed note and continue with

scripts/resolvers/constants.ts

@@ -152,7 +152,7 @@ echo "CODEX_MODE: $${m}"
 Branch on the echoed \`CODEX_MODE\`:
 - **\`disabled\`** — the user turned Codex reviews off (\`codex_reviews=disabled\`). ${disabledLine}
 - **\`not_installed\`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: \`npm install -g @openai/codex\`." Fall back to the Claude subagent path.
-- **\`under_codex\`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **\`under_codex\`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **\`not_authed\`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run \`codex login\` or set \`$CODEX_API_KEY\`." Fall back to the Claude subagent path.
 - **\`broken_install\`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: \`npm install -g @openai/codex\`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report \`ready\`, so every Codex pass was skipped silently (#2742).
 - **\`model_unusable\`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set \`GSTACK_CODEX_MODEL=<supported-model>\` or pass an explicit \`-c model=...\` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to \`ready\`.

scripts/resolvers/outside-voice.ts

@@ -71,7 +71,7 @@ export function outsideVoicePreflight(ctx: TemplateContext, opts: { disabledBeha
   if (v.id === 'codex' && opts.disabledBehavior !== 'opt-in') {
     const preflight = outsideVoiceLabels(ctx, codexPreflight(opts))
       .replace('```bash\n', `\`\`\`bash\n${outsideVoiceRuntime(ctx)}\n`);
-    return preflight + '\n\nA stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.\n';
+    return preflight;
   }
   const bin = toShellPath(ctx.paths.binDir);
   const probe = v.id === 'codex'

scripts/resolvers/review.ts

@@ -203,16 +203,16 @@ ${approvals}1. Read the plan file with the Read tool (after your most recent wri
    does NOT count — only the structured \`## GSTACK REVIEW REPORT\` section
    satisfies this check.
 3. Confirm the report has a Runs / Status / Findings table and a VERDICT line
-   (CODEX / CROSS-MODEL absorbed if applicable).
+   (OUTSIDE COVERAGE / CROSS-MODEL included when applicable).
 4. Confirm the report's FINAL non-whitespace line is the unresolved-decisions
    status: the exact unbolded \`NO UNRESOLVED DECISIONS\`, or a bullet of a final
    \`**UNRESOLVED DECISIONS:**\` block. BLOCKING, no "if applicable" escape — a
-   bolded sentinel, any trailing CODEX/CROSS-MODEL/VERDICT/prose, or a missing
+   bolded sentinel, any trailing report field or prose, or a missing
    status each FAILS the gate.
 5. If a plan file is in context for this skill invocation: confirm
    \`gstack-review-log\` was called and \`gstack-review-read\` was run at least
-   once. If no plan file is in context (e.g. \`/codex consult\` against a
-   diff with no plan), this check short-circuits — checks 1-4 already
+   once. If no plan file is in context (e.g. a diff review with no plan),
+   this check short-circuits — checks 1-4 already
    short-circuit when no plan file exists.
 
 Failing this gate and calling ExitPlanMode anyway is a contract violation —
@@ -230,7 +230,8 @@ export function generateAntiShortcutClause(_ctx: TemplateContext): string {
 export function generateSpecReviewLoop(_ctx: TemplateContext): string {
   return `## Spec Review Loop
 
-Before presenting the document to the user for approval, run an adversarial review.
+Run an adversarial review before presenting the final document to the user.
+Follow the calling workflow's approval steps.
 
 **Step 1: Dispatch reviewer subagent**
 
@@ -706,10 +707,10 @@ Immediately before dispatching, check the preflight result again. On
 \`CODEX_MODE: disabled\`, finish this section with \`outside_status: disabled\`;
 do not dispatch. Otherwise, use this fallback for missing/broken CLI, failed
 authentication/model selection, a failed preflight, or a failed outside invocation.
-The disabled branch never reaches this fallback. In this section, \`under_codex\`
-or \`under_current_harness\` also follows this native fallback: run no outside CLI,
-report the setup repair and \`outside_status: unavailable\`, then use the native
-subagent below. A native result never supplies outside coverage.
+The disabled branch never reaches this fallback.
+On \`CODEX_MODE: ${outsideVoiceFor(ctx).id === 'codex' ? 'under_codex' : 'under_current_harness'}\`, report the setup repair and
+\`outside_status: unavailable\`, run no outside CLI, and use the native subagent below.
+A native result never supplies outside coverage.
 
 Dispatch via the Agent tool with \`run_in_background: false\` (subagents default to background since ${CC_BACKGROUND_DEFAULT_SINCE}; the findings must land before the workflow continues). The subagent has fresh context and no conversation bias — but it is the same harness; model identity stays unknown unless the runtime reports it; weigh its agreement accordingly.
 Bound it the same way as ${outsideVoiceFor(ctx).label}: cap the dispatch at a 5-minute timeout so "never blocking"
@@ -846,10 +847,10 @@ Immediately before dispatching, check the preflight result again. On
 \`CODEX_MODE: disabled\`, finish this section with \`outside_status: disabled\`;
 do not dispatch. Otherwise, use this fallback for missing/broken CLI, failed
 authentication/model selection, a failed preflight, or a failed outside invocation.
-The disabled branch never reaches this fallback. In this section, \`under_codex\`
-or \`under_current_harness\` also follows this native fallback: run no outside CLI,
-report the setup repair and \`outside_status: unavailable\`, then use the native
-subagent below. A native result never supplies outside coverage.
+The disabled branch never reaches this fallback.
+On \`CODEX_MODE: ${outsideVoiceFor(ctx).id === 'codex' ? 'under_codex' : 'under_current_harness'}\`, report the setup repair and
+\`outside_status: unavailable\`, run no outside CLI, and use the native subagent below.
+A native result never supplies outside coverage.
 
 Dispatch via the Agent tool with the same prompt, passing \`run_in_background: false\` (subagents default to background since ${CC_BACKGROUND_DEFAULT_SINCE}). Bound it at a 5-minute timeout; if it never completes, treat the review as unavailable and continue.
 Present findings under \`DOCUMENTATION REVIEW (${outsideVoiceFor(ctx).nativeLabel} subagent):\`. If it fails: "Doc review unavailable. Continuing to Step 9." Skip the apply gate, persist \`status: unavailable\`, \`outside_status: unavailable\`, and \`source: none\` below, then continue; unavailable is not a clean review.

ship/sections/adversarial.md

@@ -53,15 +53,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip the Codex passes only; the Claude adversarial subagent below STILL runs (it is free and fast). Print: "Codex passes skipped (codex_reviews disabled) — running Claude adversarial only."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a Claude subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a Claude subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the Claude subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 For this diff-review path, `CODEX_MODE: disabled` means skip the Codex passes ONLY — the
 Claude adversarial subagent below still runs (it's free and fast). `ready` runs the Codex
 passes; `not_installed` / `not_authed` skip them with the printed note and continue with

test/ceo-mode-preference-al.test.ts

@@ -84,7 +84,7 @@ test('only an explicit user selection or enabled successful mode check bypasses
   expect(q).toContain('`ASK_NORMALLY` means ask.');
   expect(s).toContain('This settles only the mode, not approach or scope approval.');
   expect(document).toContain('Do NOT proceed to mode selection (0F) without user approval of the chosen approach.');
-  expect(s).toContain('Every mode requires your explicit approval for added scope.');
+  expect(s).toContain('Every mode requires explicit user approval for scope changes.');
   expect(s).toContain('Keep the approved 0C-bis approach; explain and obtain approval for any mode-required change.');
   expect(s).toContain('offer all four modes in one AskUserQuestion');
   expect(s).toContain('context defaults for RECOMMENDATION');

test/fixtures/golden/factory-ship-SKILL.md

@@ -2308,15 +2308,12 @@ echo "CODEX_MODE: $_CODEX_MODE"
 Branch on the echoed `CODEX_MODE`:
 - **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip the Codex passes only; the factory (in-host) adversarial subagent below STILL runs (it is free and fast). Print: "Codex passes skipped (codex_reviews disabled) — running factory (in-host) adversarial only."
 - **`not_installed`** — Codex CLI absent. Print: "Codex not installed — falling back to a factory (in-host) subagent (fresh context, but the same harness; model identity is unknown). Install Codex for an actual outside-model read: `npm install -g @openai/codex`." Fall back to the factory (in-host) subagent path.
-- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation; retain the section's native pass if defined. Conflicting inherited harness markers are not grounds to guess another provider.
+- **`under_codex`** — stale artifact selected its own harness. Print: "Codex outside review unavailable: harness mismatch; no outside process started. Missing coverage. Repair: setup --host codex." Skip the outside invocation and follow the workflow's native-review instructions below. Conflicting inherited harness markers are not grounds to guess another provider.
 - **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — falling back to a factory (in-host) subagent (same harness; model identity is unknown). Run `codex login` or set `$CODEX_API_KEY`." Fall back to the factory (in-host) subagent path.
 - **`broken_install`** — the CLI is on PATH but cannot execute (spawn ENOENT, non-executable binary, missing vendor payload). Print: "Codex is installed but its binary cannot run — Codex passes skipped. Reinstall: `npm install -g @openai/codex`." Relay the probe's HINT lines and fall back to the factory (in-host) subagent path. This state exists because a missing binary used to land in the model probe's fail-open bucket and report `ready`, so every Codex pass was skipped silently (#2742).
 - **`model_unusable`** — authed but the account cannot use gstack's selected Codex model (#2477: HTTP 400 on every call). Relay the probe's HINT lines, tell the user the one-line fix (set `GSTACK_CODEX_MODEL=<supported-model>` or pass an explicit `-c model=...` override), and fall back to the factory (in-host) subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
 - **`ready`** — run the Codex pass below.
 
-A stale artifact selecting its own harness must report missing coverage and run no outside CLI. Repair: `setup --host codex`. Never infer a replacement provider from inherited environment markers. The invocation below repeats this guard.
-
-
 For this diff-review path, `CODEX_MODE: disabled` means skip the Codex passes ONLY — the
 factory (in-host) adversarial subagent below still runs (it's free and fast). `ready` runs the Codex
 passes; `not_installed` / `not_authed` skip them with the printed note and continue with

test/outside-voice-preflight.test.ts

@@ -5,12 +5,41 @@ import * as os from 'node:os';
 import * as path from 'node:path';
 import { spawnSync } from 'node:child_process';
 import { outsideVoiceCommand, outsideVoicePreflight } from '../scripts/resolvers/outside-voice';
+import { generateCodexDocReview, generateCodexPlanReview } from '../scripts/resolvers/review';
 import { HOST_PATHS, type TemplateContext } from '../scripts/resolvers/types';
+import { ALL_HOST_CONFIGS } from '../hosts';
 
 const ROOT = path.resolve(import.meta.dir, '..');
 const TEMP = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-outside-preflight-'));
 afterAll(() => fs.rmSync(TEMP, { recursive: true, force: true }));
 
+describe('own-harness review fallback instructions', () => {
+  for (const host of ALL_HOST_CONFIGS) {
+    for (const [name, render] of [['plan', generateCodexPlanReview], ['documentation', generateCodexDocReview]] as const) {
+      test(`${host.name}: ${name} fallback names only the mode its preflight emits`, () => {
+        const ctx: TemplateContext = { host: host.name, skillName: 'review', tmplPath: 'review/SKILL.md.tmpl', paths: HOST_PATHS[host.name] };
+        const text = render(ctx);
+        const mode = host.name === 'codex' ? 'under_current_harness' : 'under_codex';
+        const preflight = text.match(/```bash\n([\s\S]*?)\n```/)![1];
+        expect(preflight).toContain(mode);
+        expect([...new Set(text.match(/under_codex|under_current_harness/g))]).toEqual([mode]);
+        expect(text.includes("retain the section's native pass if defined")).toBe(false);
+
+        const fallback = text.slice(text.indexOf('**Native fallback'), text.indexOf('Dispatch via the Agent tool'));
+        const ownHarnessBranch = `On \`CODEX_MODE: ${mode}\``;
+        expect(text.split(ownHarnessBranch)).toHaveLength(2);
+        expect(fallback).toContain(ownHarnessBranch);
+        expect(fallback).toContain('`outside_status: unavailable`');
+        expect(fallback).toContain('run no outside CLI');
+        expect(fallback).toContain('use the native subagent below');
+        expect(fallback).toContain('A native result never supplies outside coverage.');
+        expect(fallback).toContain('The disabled branch never reaches this fallback.');
+        expect(fallback).toContain('`CODEX_MODE: disabled`, finish this section with `outside_status: disabled`;');
+      });
+    }
+  }
+});
+
 function fixture() {
   const dir = fs.mkdtempSync(path.join(TEMP, 'case-'));
   const repo = path.join(dir, "repo ' $(touch NEVER)");