diff --git a/scripts/resolvers/constants.ts b/scripts/resolvers/constants.ts
index 2a7e649b9..82ef4d5f6 100644
--- a/scripts/resolvers/constants.ts
+++ b/scripts/resolvers/constants.ts
@@ -164,4 +164,4 @@ Branch on the echoed \`CODEX_MODE\`:
* interpolate it directly. Same name as the placeholder for grep-ability.
*/
export const FOREGROUND_DISPATCH_NOTE =
- '**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.)';
+ '**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for.';
diff --git a/ship/sections/greptile.md b/ship/sections/greptile.md
index befb321e5..a3676963b 100644
--- a/ship/sections/greptile.md
+++ b/ship/sections/greptile.md
@@ -4,7 +4,7 @@
**Dispatch the fetch + classification as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent pulls every Greptile comment, runs the escalation detection algorithm, and classifies each comment. Parent receives a structured list and handles user interaction + file edits.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.)
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for.
**Subagent prompt:**
diff --git a/ship/sections/plan-completion.md b/ship/sections/plan-completion.md
index bac26c837..b3ec42b48 100644
--- a/ship/sections/plan-completion.md
+++ b/ship/sections/plan-completion.md
@@ -4,7 +4,7 @@
**Dispatch this step as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent reads the plan file and every referenced code file in its own fresh context. Parent gets only the conclusion.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) The Gate Logic below consumes this audit's LAST-line JSON before /ship can proceed.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. The Gate Logic below consumes this audit's LAST-line JSON before /ship can proceed.
**Subagent prompt:** Pass these instructions to the subagent:
diff --git a/ship/sections/pr-body.md b/ship/sections/pr-body.md
index 0031b5d24..00e10de15 100644
--- a/ship/sections/pr-body.md
+++ b/ship/sections/pr-body.md
@@ -4,7 +4,7 @@
**Dispatch /document-release as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent gets a fresh context window — zero rot from the preceding 17 steps. It also runs the **full** `/document-release` workflow (with CHANGELOG clobber protection, doc exclusions, risky-change gates, named staging, race-safe PR body editing) rather than a weaker reimplementation. The dispatch prompt marks the subagent session as spawned (`GSTACK_SESSION_KIND=spawned`) so document-release's interactive gates auto-choose their recommended options instead of prose-stopping — a prose-STOP inside the subagent breaks the parent's LAST-line JSON parse and drops the Documentation section (#2733).
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Step 19 consumes this subagent's LAST-line JSON, so the dispatch must block — a backgrounded dispatch strands the entire ship run (#497, #2440: third recurrence of this class). Record `git rev-parse HEAD` immediately before dispatching; the recovery branch below reconciles against it.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. Step 19 consumes this subagent's LAST-line JSON, so the dispatch must block — a backgrounded dispatch strands the entire ship run (#497, #2440: third recurrence of this class). Record `git rev-parse HEAD` immediately before dispatching; the recovery branch below reconciles against it.
**Sequencing:** This step runs AFTER Step 17 (Push) and BEFORE Step 19 (Create PR). The PR is created once from final HEAD with the `## Documentation` section baked into the initial body. No create-then-re-edit dance.
diff --git a/ship/sections/test-coverage.md b/ship/sections/test-coverage.md
index c4304e1d4..21e9fc81d 100644
--- a/ship/sections/test-coverage.md
+++ b/ship/sections/test-coverage.md
@@ -4,7 +4,7 @@
**Dispatch this step as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent runs the coverage audit in a fresh context window — the parent only sees the conclusion, not intermediate file reads. This is context-rot defense.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) The parent needs this audit's LAST-line JSON before continuing.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. The parent needs this audit's LAST-line JSON before continuing.
**Subagent prompt:** Pass the following instructions to the subagent, with `` substituted with the base branch:
diff --git a/test/fixtures/golden/codex-ship-SKILL.md b/test/fixtures/golden/codex-ship-SKILL.md
index 5ed78f025..e82d6b772 100644
--- a/test/fixtures/golden/codex-ship-SKILL.md
+++ b/test/fixtures/golden/codex-ship-SKILL.md
@@ -1070,7 +1070,7 @@ poller is reaped.
**Dispatch this step as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent runs the coverage audit in a fresh context window — the parent only sees the conclusion, not intermediate file reads. This is context-rot defense.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) The parent needs this audit's LAST-line JSON before continuing.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. The parent needs this audit's LAST-line JSON before continuing.
**Subagent prompt:** Pass the following instructions to the subagent, with `` substituted with the base branch:
@@ -1335,7 +1335,7 @@ Repo: {owner/repo}
**Dispatch this step as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent reads the plan file and every referenced code file in its own fresh context. Parent gets only the conclusion.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) The Gate Logic below consumes this audit's LAST-line JSON before /ship can proceed.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. The Gate Logic below consumes this audit's LAST-line JSON before /ship can proceed.
**Subagent prompt:** Pass these instructions to the subagent:
@@ -1818,7 +1818,7 @@ Save the review output — it goes into the PR body in Step 19.
**Dispatch the fetch + classification as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent pulls every Greptile comment, runs the escalation detection algorithm, and classifies each comment. Parent receives a structured list and handles user interaction + file edits.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.)
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for.
**Subagent prompt:**
@@ -2294,7 +2294,7 @@ git push -u origin
**Dispatch /document-release as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent gets a fresh context window — zero rot from the preceding 17 steps. It also runs the **full** `/document-release` workflow (with CHANGELOG clobber protection, doc exclusions, risky-change gates, named staging, race-safe PR body editing) rather than a weaker reimplementation. The dispatch prompt marks the subagent session as spawned (`GSTACK_SESSION_KIND=spawned`) so document-release's interactive gates auto-choose their recommended options instead of prose-stopping — a prose-STOP inside the subagent breaks the parent's LAST-line JSON parse and drops the Documentation section (#2733).
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Step 19 consumes this subagent's LAST-line JSON, so the dispatch must block — a backgrounded dispatch strands the entire ship run (#497, #2440: third recurrence of this class). Record `git rev-parse HEAD` immediately before dispatching; the recovery branch below reconciles against it.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. Step 19 consumes this subagent's LAST-line JSON, so the dispatch must block — a backgrounded dispatch strands the entire ship run (#497, #2440: third recurrence of this class). Record `git rev-parse HEAD` immediately before dispatching; the recovery branch below reconciles against it.
**Sequencing:** This step runs AFTER Step 17 (Push) and BEFORE Step 19 (Create PR). The PR is created once from final HEAD with the `## Documentation` section baked into the initial body. No create-then-re-edit dance.
diff --git a/test/fixtures/golden/factory-ship-SKILL.md b/test/fixtures/golden/factory-ship-SKILL.md
index 4351cc756..34f9e9b06 100644
--- a/test/fixtures/golden/factory-ship-SKILL.md
+++ b/test/fixtures/golden/factory-ship-SKILL.md
@@ -1050,7 +1050,7 @@ poller is reaped.
**Dispatch this step as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent runs the coverage audit in a fresh context window — the parent only sees the conclusion, not intermediate file reads. This is context-rot defense.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) The parent needs this audit's LAST-line JSON before continuing.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. The parent needs this audit's LAST-line JSON before continuing.
**Subagent prompt:** Pass the following instructions to the subagent, with `` substituted with the base branch:
@@ -1315,7 +1315,7 @@ Repo: {owner/repo}
**Dispatch this step as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent reads the plan file and every referenced code file in its own fresh context. Parent gets only the conclusion.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) The Gate Logic below consumes this audit's LAST-line JSON before /ship can proceed.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. The Gate Logic below consumes this audit's LAST-line JSON before /ship can proceed.
**Subagent prompt:** Pass these instructions to the subagent:
@@ -2071,7 +2071,7 @@ Save the review output — it goes into the PR body in Step 19.
**Dispatch the fetch + classification as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent pulls every Greptile comment, runs the escalation detection algorithm, and classifies each comment. Parent receives a structured list and handles user interaction + file edits.
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.)
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for.
**Subagent prompt:**
@@ -2729,7 +2729,7 @@ git push -u origin
**Dispatch /document-release as a subagent** using the Agent tool with `subagent_type: "general-purpose"`. The subagent gets a fresh context window — zero rot from the preceding 17 steps. It also runs the **full** `/document-release` workflow (with CHANGELOG clobber protection, doc exclusions, risky-change gates, named staging, race-safe PR body editing) rather than a weaker reimplementation. The dispatch prompt marks the subagent session as spawned (`GSTACK_SESSION_KIND=spawned`) so document-release's interactive gates auto-choose their recommended options instead of prose-stopping — a prose-STOP inside the subagent breaks the parent's LAST-line JSON parse and drops the Documentation section (#2733).
-**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Step 19 consumes this subagent's LAST-line JSON, so the dispatch must block — a backgrounded dispatch strands the entire ship run (#497, #2440: third recurrence of this class). Record `git rev-parse HEAD` immediately before dispatching; the recovery branch below reconciles against it.
+**Foreground required:** pass `run_in_background: false` on the Agent call — subagents run in the BACKGROUND by default since Claude Code v2.1.198. (Merely omitting the flag no longer produces a foreground run; it must be explicitly false.) Dispatch with the Agent tool itself — never substitute the Skill tool or inline execution to "guarantee" blocking: the explicit flag already makes the Agent call block, and running the work inline forfeits the fresh-context isolation this dispatch exists for. Step 19 consumes this subagent's LAST-line JSON, so the dispatch must block — a backgrounded dispatch strands the entire ship run (#497, #2440: third recurrence of this class). Record `git rev-parse HEAD` immediately before dispatching; the recovery branch below reconciles against it.
**Sequencing:** This step runs AFTER Step 17 (Push) and BEFORE Step 19 (Create PR). The PR is created once from final HEAD with the `## Documentation` section baked into the initial body. No create-then-re-edit dance.