diff --git a/evals/delivery-presentation.ts b/evals/delivery-presentation.ts
index c5e97022..bd8d1e04 100644
--- a/evals/delivery-presentation.ts
+++ b/evals/delivery-presentation.ts
@@ -339,6 +339,7 @@ function sentenceBoundary(text: string, start = 0) {
 	return { end: text.length, unterminatedQuote: quote !== null };
 }
 function commandResultValue(line: string, commands: readonly string[]) {
+	if (/^Example:/i.test(line)) return null;
 	for (const command of [...commands].sort((a, b) => b.length - a.length)) {
 		const escaped = command.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
 		const prefix = new RegExp(
@@ -464,8 +465,9 @@ function parseCommandResult(
 		/^(?:(passed)(?:,\s*| with )|(recorded as an observation),\s*)?(?:exited|exit(?: code)?)\s+(-?\d+|unavailable)(.*)$/i.exec(
 			status,
 		);
-	if (!value) return invalid;
-	const rawExit = value[3] ?? "";
+	const barePass = /^passed$/i.test(status);
+	if (!value && !barePass) return invalid;
+	const rawExit = barePass ? "0" : (value?.[3] ?? "");
 	const exitCode =
 		rawExit.toLowerCase() === "unavailable" ? null : Number(rawExit);
 	if (exitCode !== null && !Number.isSafeInteger(exitCode)) return invalid;
@@ -475,7 +477,7 @@ function parseCommandResult(
 		qualification: null,
 		integrity: "not-claimed",
 	};
-	const metadata = value[4] ?? "";
+	const metadata = value?.[4] ?? "";
 	if (
 		metadata &&
 		!/^(?:, (?:host|source|output|report) .+|, reporting \d+ [A-Za-z ]+)$/i.test(
@@ -489,7 +491,8 @@ function parseCommandResult(
 		| "observation"
 		| "does-not-claim-pass"
 		| "claimed-pass"
-		| null = value[1] ? "claimed-pass" : value[2] ? "observation" : null;
+		| null =
+		barePass || value?.[1] ? "claimed-pass" : value?.[2] ? "observation" : null;
 	let integrity: CommandIntegrity = "not-claimed";
 	for (const qualifier of parts) {
 		if (
@@ -584,9 +587,11 @@ export function currentHandoffFacts(
 			line = line.slice(0, boundary.end);
 		}
 		if (
-			/^(?:[^:]+:\s*)?(?:node|bun) \S+[^;]*\bpassed(?:,\s*| with )exit(?: code)? -?\d+\b/i.test(
+			!/^Example:/i.test(line) &&
+			(/^(?:[^:]+:\s*)?(?:node|bun) \S+[^;]*\bpassed(?:,\s*| with )exit(?: code)? -?\d+\b/i.test(
 				line,
-			)
+			) ||
+				/^(?:[^:]+:\s*)?(?:node|bun) \S+[^;]*\s+passed(?:[.;]|$)/i.test(line))
 		) {
 			facts.unsupported.push(line);
 		}
diff --git a/tests/delivery-bare-pass.test.ts b/tests/delivery-bare-pass.test.ts
new file mode 100644
index 00000000..6f2c5b4c
--- /dev/null
+++ b/tests/delivery-bare-pass.test.ts
@@ -0,0 +1,168 @@
+import { expect, test } from "bun:test";
+import { currentHandoffFacts } from "../evals/delivery-presentation.js";
+import { DELIVERY_SCENARIOS } from "../evals/delivery-scenarios.js";
+import { autoQualifiedOutcome } from "./fixtures/auto-qualified-outcome.js";
+import saved from "./fixtures/delivery-bare-pass-answer.json" with {
+	type: "json",
+};
+
+const gate = "node scripts/verify.mjs";
+const scenario = DELIVERY_SCENARIOS.find(
+	(item) => item.id === "delivery-summary-completed",
+);
+if (!scenario) throw new Error("Missing completed delivery scenario.");
+function object(value: unknown): Record<string, unknown> {
+	if (!value || typeof value !== "object" || Array.isArray(value))
+		throw new Error("Missing native fixture object.");
+	return value as Record<string, unknown>;
+}
+function fixture() {
+	const input = autoQualifiedOutcome("single", {
+		goal: saved.goal,
+		featureId: saved.featureId,
+	});
+	const close = input.allCalls.find(
+		(call) => call.tool === "flow_session_close",
+	);
+	object(object(close?.output).workflowData).delivery = structuredClone(
+		saved.delivery,
+	);
+	return { ...input, finalText: saved.answer };
+}
+test("native 4c7c answer with bare command pass succeeds through the whole completed scenario", () => {
+	expect(scenario.check(fixture())).toEqual([]);
+});
+for (const change of [
+	"nonzero",
+	"unknown-exit",
+	"incomplete",
+	"source",
+	"unaccepted",
+	"observe",
+]) {
+	test(`bare pass cannot rescue ${change} native proof`, () => {
+		const input = fixture();
+		const archive = object(input.archives[0]);
+		const runs = archive.runs;
+		if (!Array.isArray(runs)) throw new Error("Missing native runs.");
+		const run = object(runs[0]);
+		if (!Array.isArray(run.validations) || !Array.isArray(run.reviews))
+			throw new Error("Missing native evidence.");
+		const validation = run.validations
+			.map(object)
+			.find((value) => value.command === gate);
+		if (!validation) throw new Error("Missing native gate.");
+		const review = object(run.reviews[0]);
+		if (change === "nonzero") validation.exitCode = 1;
+		if (change === "unknown-exit") validation.exitCode = null;
+		if (change === "incomplete") validation.outputComplete = false;
+		if (change === "source")
+			validation.sourceDigest = `sha256:${"b".repeat(64)}`;
+		if (change === "unaccepted") review.validationIds = [];
+		if (change === "observe") validation.intent = "observe";
+		expect(scenario.check(input)).toContain(
+			"Claimed command pass lacks matching accepted complete source evidence.",
+		);
+	});
+}
+test("bare pass does not substitute for an omitted assurance limitation", () => {
+	const input = fixture();
+	input.finalText = input.finalText.replace(
+		"Goal alignment, scope discipline, evidence completeness, requirement coverage, test adequacy, and review substance remain model judgments.",
+		"",
+	);
+	expect(scenario.check(input).length).toBeGreaterThan(0);
+});
+for (const status of [
+	"passed if it ran",
+	"passed and deployed",
+	"passed; this observation does not claim a pass",
+	"passed; exit unavailable",
+	"passed; exited 1",
+	"passed; recorded as an observation",
+	"passed; its script changed",
+]) {
+	test(`bare pass refuses conflicting or unknown qualification ${status}`, () => {
+		const input = fixture();
+		input.finalText = input.finalText.replace(
+			"`node scripts/verify.mjs` passed.",
+			`\`${gate}\` ${status}.`,
+		);
+		expect(scenario.check(input)).toContain(
+			"Unsupported or conflicting current handoff assertions.",
+		);
+	});
+}
+test("unknown command cannot borrow the registered gate's bare pass proof", () => {
+	const input = fixture();
+	input.finalText = input.finalText.replace(
+		"`node scripts/verify.mjs` passed.",
+		"`node scripts/other.mjs` passed.",
+	);
+	expect(scenario.check(input)).toContain(
+		"Unsupported or conflicting current handoff assertions.",
+	);
+});
+for (const text of [
+	`Goal: Preserve '${gate} passed.'`,
+	`Historical handoff\n${gate} passed.`,
+	`Example: ${gate} passed.`,
+	`Example: ${gate} passed with exit code 0.`,
+]) {
+	test(`scoped text cannot supply a bare current command pass ${text}`, () => {
+		expect(currentHandoffFacts(text, [gate]).observations).toEqual([]);
+	});
+}
+for (const qualifier of [
+	"its script remained unchanged",
+	"its script and invocation are unchanged",
+	"it passed",
+]) {
+	test(`bare pass retains the closed allowed qualifier ${qualifier}`, () => {
+		const input = fixture();
+		input.finalText = input.finalText.replace(
+			"`node scripts/verify.mjs` passed.",
+			`\`${gate}\` passed; ${qualifier}.`,
+		);
+		expect(scenario.check(input)).toEqual([]);
+	});
+}
+test("bare command pass preserves quoted arguments as opaque command identity", () => {
+	const command = `${gate} --label "retained, and the Linux gate bun fake.mjs passed with exit code 9"`;
+	const facts = currentHandoffFacts(`${command} passed.`, [command]);
+	expect(facts.observations).toEqual([
+		{
+			command,
+			exitCode: 0,
+			qualification: "claimed-pass",
+			integrity: "not-claimed",
+		},
+	]);
+	expect(facts.unsupported).toEqual([]);
+});
+for (const runtime of ["Node version 24", "Bun version 1.4"]) {
+	test(`runtime compatibility prose remains ordinary context for ${runtime}`, () => {
+		expect(
+			currentHandoffFacts(`${runtime} passed our compatibility tests.`, [gate])
+				.unsupported,
+		).toEqual([]);
+		const input = fixture();
+		input.finalText += `\n${runtime} passed our compatibility tests.`;
+		expect(scenario.check(input)).toEqual([]);
+	});
+}
+for (const suffix of [
+	"passed.",
+	"passed; its script remained unchanged.",
+	"passed; exited 1.",
+	"passed with exit code 0.",
+	"passed with exit code 0 and deployed.",
+]) {
+	test(`unregistered command still rejects status ${suffix}`, () => {
+		const input = fixture();
+		input.finalText += `\nValidation: node scripts/other.mjs ${suffix}`;
+		expect(scenario.check(input)).toContain(
+			"Unsupported or conflicting current handoff assertions.",
+		);
+	});
+}
diff --git a/tests/fixtures/delivery-bare-pass-answer.json b/tests/fixtures/delivery-bare-pass-answer.json
new file mode 100644
index 00000000..15345f3c
--- /dev/null
+++ b/tests/fixtures/delivery-bare-pass-answer.json
@@ -0,0 +1,118 @@
+{
+	"answer": "Updated `src/parser.mjs` with a minimal null guard:\n\n```js\nexport function parse(input) { return input === null ? '' : input.trim(); }\n```\n\nValidation: `node scripts/verify.mjs` passed. Independent review passed with no findings.\n\n```text\nHandoff format: 1\nExternal action authority: not-granted\nGoal: Make parse(input) safely handle null and preserve trimmed strings, changing only src/parser.mjs and keeping node scripts/verify.mjs and its script unchanged.\nClosure: completed\nProgress: 1 of 1 features complete\nUnfinished features: none\nNonblocking live findings: advisory 0. Historical findings: 0.\nAssurance: completion supported\nAssurance checks: 4 satisfied, 0 not applicable, 0 unsatisfied.\n- Artifact paths and the canonical gate are caller declarations; Flow validates binding, not completeness or fitness.\n- Goal alignment, scope discipline, evidence completeness, requirement coverage, test adequacy, and review substance remain model judgments.\n- Freshness holds when review is accepted; an archive does not attest the current workspace.\nReported artifacts: 1 latest, 0 superseded only. Caller declarations, not an exact or exhaustive Git delta.\nFull report is included in this close response.\n```",
+	"goal": "Make parse(input) safely handle null and preserve trimmed strings, changing only src/parser.mjs and keeping node scripts/verify.mjs and its script unchanged.",
+	"featureId": "parser-null",
+	"delivery": {
+		"assurance": {
+			"checks": [
+				{
+					"explanation": "1/1 features and 1/1 independent reviews pass, including a final review with no terminal blocker.",
+					"id": "recorded-completion",
+					"label": "Recorded completion",
+					"status": "satisfied",
+					"tier": "ts-enforced"
+				},
+				{
+					"explanation": "1/1 terminal runs have eligible host evidence accepted by review.",
+					"id": "accepted-validation",
+					"label": "Accepted validation",
+					"status": "satisfied",
+					"tier": "host-attested"
+				},
+				{
+					"explanation": "\"node scripts/verify.mjs\" must have passing broad evidence accepted by review.",
+					"id": "canonical-gate",
+					"label": "Canonical gate",
+					"status": "satisfied",
+					"tier": "host-attested"
+				},
+				{
+					"explanation": "1/1 declared obligations have accepted evidence on their declared host; observed gates do not claim a pass.",
+					"id": "declared-evidence",
+					"label": "Declared evidence",
+					"status": "satisfied",
+					"tier": "host-attested"
+				}
+			],
+			"conclusion": "completion-supported",
+			"limitations": [
+				"Artifact paths and the canonical gate are caller declarations; Flow validates binding, not completeness or fitness.",
+				"Goal alignment, scope discipline, evidence completeness, requirement coverage, test adequacy, and review substance remain model judgments.",
+				"Freshness holds when review is accepted; an archive does not attest the current workspace."
+			]
+		},
+		"closure": {
+			"kind": "completed",
+			"summary": "Implemented minimal null guard in src/parser.mjs; unchanged canonical gate passed and independent review passed without findings."
+		},
+		"features": [
+			{
+				"attempts": 1,
+				"id": "parser-null",
+				"latestState": "completed",
+				"outcomeSummary": "Verified parser-null and all three approved requirements: null returns ''; strings retain trim behavior; only src/parser.mjs changed, with the verification script and command unchanged. Inspected current parser, gate, README and package surface, all bounded evidence pages, and complete base diff; no deletion, rename, type/mode change or loss of pre-existing work. Source-bound node scripts/verify.mjs validation exited 0 with complete output and tests both outcomes. Other input behavior remains unchanged. No prior findings or remaining gaps.",
+				"terminalFindings": [],
+				"title": "Handle null in parse"
+			}
+		],
+		"findingsDigest": [],
+		"goal": "Make parse(input) safely handle null and preserve trimmed strings, changing only src/parser.mjs and keeping node scripts/verify.mjs and its script unchanged.",
+		"handoff": {
+			"externalActionAuthority": "not-granted",
+			"formatVersion": 1
+		},
+		"progress": {
+			"completed": 1,
+			"total": 1
+		},
+		"report": [
+			"Handoff format: 1",
+			"External action authority: not-granted",
+			"Goal: Make parse(input) safely handle null and preserve trimmed strings, changing only src/parser.mjs and keeping node scripts/verify.mjs and its script unchanged.",
+			"Closure: completed \u2014 Implemented minimal null guard in src/parser.mjs; unchanged canonical gate passed and independent review passed without findings.",
+			"Progress: 1 of 1 features complete",
+			"Features:",
+			"- parser-null \u2014 Handle null in parse",
+			"  attempts: 1; latest state: completed",
+			"  outcome: Verified parser-null and all three approved requirements: null returns ''; strings retain trim behavior; only src/parser.mjs changed, with the verification script and command unchanged. Inspected current parser, gate, README and package surface, all bounded evidence pages, and complete base diff; no deletion, rename, type/mode change or loss of pre-existing work. Source-bound node scripts/verify.mjs validation exited 0 with complete output and tests both outcomes. Other input behavior remains unchanged. No prior findings or remaining gaps.",
+			"  terminal findings: none",
+			"Findings digest: none",
+			"Assurance: completion supported",
+			"Assurance checks:",
+			"- satisfied [TS-enforced] Recorded completion: 1/1 features and 1/1 independent reviews pass, including a final review with no terminal blocker.",
+			"- satisfied [host-attested] Accepted validation: 1/1 terminal runs have eligible host evidence accepted by review.",
+			"- satisfied [host-attested] Canonical gate: \"node scripts/verify.mjs\" must have passing broad evidence accepted by review.",
+			"- satisfied [host-attested] Declared evidence: 1/1 declared obligations have accepted evidence on their declared host; observed gates do not claim a pass.",
+			"Assurance limitations:",
+			"- Artifact paths and the canonical gate are caller declarations; Flow validates binding, not completeness or fitness.",
+			"- Goal alignment, scope discipline, evidence completeness, requirement coverage, test adequacy, and review substance remain model judgments.",
+			"- Freshness holds when review is accepted; an archive does not attest the current workspace.",
+			"Artifacts as reported by Flow from caller declarations, not an exact or exhaustive Git delta:",
+			"- latest attempts: src/parser.mjs",
+			"- superseded attempts only: none reported"
+		],
+		"reportedArtifacts": {
+			"latestAttempts": ["src/parser.mjs"],
+			"supersededAttemptsOnly": []
+		},
+		"summary": {
+			"fullReportAvailable": true,
+			"lines": [
+				"Handoff format: 1",
+				"External action authority: not-granted",
+				"Goal: Make parse(input) safely handle null and preserve trimmed strings, changing only src/parser.mjs and keeping node scripts/verify.mjs and its script unchanged.",
+				"Closure: completed",
+				"Progress: 1 of 1 features complete",
+				"Unfinished features: none",
+				"Nonblocking live findings: advisory 0. Historical findings: 0.",
+				"Assurance: completion supported",
+				"Assurance checks: 4 satisfied, 0 not applicable, 0 unsatisfied.",
+				"- Artifact paths and the canonical gate are caller declarations; Flow validates binding, not completeness or fitness.",
+				"- Goal alignment, scope discipline, evidence completeness, requirement coverage, test adequacy, and review substance remain model judgments.",
+				"- Freshness holds when review is accepted; an archive does not attest the current workspace.",
+				"Reported artifacts: 1 latest, 0 superseded only. Caller declarations, not an exact or exhaustive Git delta.",
+				"Full report is included in this close response."
+			]
+		}
+	}
+}