diff --git a/commands/gsd/execute-phase.md b/commands/gsd/execute-phase.md
index 6e9d834da..c6cf7ad10 100644
--- a/commands/gsd/execute-phase.md
+++ b/commands/gsd/execute-phase.md
@@ -22,6 +22,11 @@ Optional wave filter:
- `--wave N` executes only Wave `N` for pacing, quota management, or staged rollout
- phase verification/completion still only happens when no incomplete plans remain after the selected wave finishes
+Flag handling rule:
+- The optional flags documented below are available behaviors, not implied active behaviors
+- A flag is active only when its literal token appears in `$ARGUMENTS`
+- If a documented flag is absent from `$ARGUMENTS`, treat it as inactive
+
Context budget: ~15% orchestrator, 100% fresh per subagent.
@@ -33,10 +38,16 @@ Context budget: ~15% orchestrator, 100% fresh per subagent.
Phase: $ARGUMENTS
-**Flags:**
+**Available optional flags (documentation only — not automatically active):**
- `--wave N` — Execute only Wave `N` in the phase. Use when you want to pace execution or stay inside usage limits.
- `--gaps-only` — Execute only gap closure plans (plans with `gap_closure: true` in frontmatter). Use after verify-work creates fix plans.
+**Active flags must be derived from `$ARGUMENTS`:**
+- `--wave N` is active only if the literal `--wave` token is present in `$ARGUMENTS`
+- `--gaps-only` is active only if the literal `--gaps-only` token is present in `$ARGUMENTS`
+- If neither token appears, run the standard full-phase execution flow with no flag-specific filtering
+- Do not infer that a flag is active just because it is documented in this prompt
+
Context files are resolved inside the workflow via `gsd-tools init execute-phase` and per-subagent `` blocks.
diff --git a/tests/execute-phase-active-flags.test.cjs b/tests/execute-phase-active-flags.test.cjs
new file mode 100644
index 000000000..09a87657e
--- /dev/null
+++ b/tests/execute-phase-active-flags.test.cjs
@@ -0,0 +1,58 @@
+/**
+ * Execute-phase active flag prompt tests
+ *
+ * Guards against prompt wording that makes optional flags look active by default.
+ * This is especially important for weaker runtimes that may infer `--gaps-only`
+ * from the command docs instead of the literal user arguments.
+ */
+
+const { test, describe } = require('node:test');
+const assert = require('node:assert');
+const fs = require('fs');
+const path = require('path');
+
+const COMMAND_PATH = path.join(__dirname, '..', 'commands', 'gsd', 'execute-phase.md');
+
+describe('execute-phase command: active flags are explicit', () => {
+ test('command file exists', () => {
+ assert.ok(fs.existsSync(COMMAND_PATH), 'commands/gsd/execute-phase.md should exist');
+ });
+
+ test('objective says documented flags are not implied active', () => {
+ const content = fs.readFileSync(COMMAND_PATH, 'utf-8');
+ const objectiveMatch = content.match(/([\s\S]*?)<\/objective>/);
+ assert.ok(objectiveMatch, 'should have section');
+ assert.ok(
+ objectiveMatch[1].includes('available behaviors, not implied active behaviors'),
+ 'objective should state that documented flags are not automatically active'
+ );
+ assert.ok(
+ objectiveMatch[1].includes('appears in `$ARGUMENTS`'),
+ 'objective should tie flag activation to literal $ARGUMENTS presence'
+ );
+ });
+
+ test('context separates available flags from active flags', () => {
+ const content = fs.readFileSync(COMMAND_PATH, 'utf-8');
+ assert.ok(
+ content.includes('Available optional flags (documentation only'),
+ 'context should clearly label flags as documentation only'
+ );
+ assert.ok(
+ content.includes('Active flags must be derived from `$ARGUMENTS`'),
+ 'context should have a separate active-flags section'
+ );
+ });
+
+ test('context explicitly warns against inferring inactive flags', () => {
+ const content = fs.readFileSync(COMMAND_PATH, 'utf-8');
+ assert.ok(
+ content.includes('Do not infer that a flag is active just because it is documented in this prompt'),
+ 'context should forbid inferring flags from documentation alone'
+ );
+ assert.ok(
+ content.includes('If neither token appears, run the standard full-phase execution flow'),
+ 'context should define the no-flags fallback behavior'
+ );
+ });
+});