diff --git a/BUILD-LOG.md b/BUILD-LOG.md
index 5ff4c6f9..7eac6f10 100644
--- a/BUILD-LOG.md
+++ b/BUILD-LOG.md
@@ -137,4 +137,30 @@ All 11 acceptance criteria demonstrated. The real model request passed.
 
 Configuration-driven Hello World verified. `main` merged with M1 and tagged `config-hello-v1`.
 
+---
+
+## Phase 6: Mission and task abstraction (M2)
+
+### Entry 6.1 — before
+
+- Timestamp: 2026-09-03
+- Intended action: Add the first mission/task layer, host-side only (Gitea milestone M2, issues #6-#9): strict v1 schemas for missions and tasks, a task runner executing through the proven config-driven container path, immutable write-once run records under `<dataRoot>/runs/`, `expectExact` gating, timeouts, selftests, fixtures, and docs.
+- Reason: The foundation plan's following layer — mission (objective + directives), task (bounded unit), run (one attempt), result (immutable evidence) — must exist as data and records before any policy or multi-agent work.
+- Expected result: `scripts/run-task.sh tasks/hello-marker.json` succeeds with exactly `MOSAIC_HELLO_OK`; wrong expectations fail; every run leaves an immutable record; configuration remains untouched.
+
+### Entry 6.2 — after
+
+- Timestamp: 2026-09-03
+- Commands run: `scripts/test-task.sh` (18 cases incl. live runs); `scripts/run-task.sh validate` / `run` on committed fixtures; `node scripts/mosaic-task.mjs list`; config checksum comparison across runs.
+- Observed result:
+  - Selftests: 18 passed, 0 failed (schema negatives; live exact-marker success; wrong expectExact fails; distinct run dirs; result.json contents; list).
+  - Fixture run: status `succeeded`, response exactly `MOSAIC_HELLO_OK`, mission snapshot recorded.
+  - Run records written once under `<dataRoot>/runs/r-<utcstamp>-<rand>/`; reruns never clobber.
+- Failure or correction: none this phase.
+- Credential check: no credential material in task data, run records, or logs.
+
+## Result (M2)
+
+Mission/task layer verified end-to-end. `main` merged with M2 and tagged `mission-task-v1`.
+
 
diff --git a/README.md b/README.md
index 3c062c92..5d608c30 100644
--- a/README.md
+++ b/README.md
@@ -61,6 +61,28 @@ Rules enforced by `scripts/mosaic-config.mjs`:
 
 Run paths (`build/hello/verify/reset`) fail closed when configuration is missing or invalid; they never invent it.
 
+## Missions & tasks (M2)
+
+Missions and tasks are validated JSON data (strict schemas, version-pinned). The M2 layer is host-side only: mission directives are recorded for provenance but do not yet reach the runtime system prompt (capability/policy layer comes later).
+
+```text
+missions/hello.json          objective + directives (missionVersion 1)
+tasks/hello-marker.json      prompt + optional mission ref + expectExact + timeout
+<dataRoot>/runs/r-<id>/      immutable run record: task.json, mission.json,
+                             stderr.txt, result.json (all write-once)
+```
+
+Usage:
+
+```bash
+scripts/run-task.sh validate tasks/hello-marker.json   # strict validation, writes nothing
+scripts/run-task.sh run tasks/hello-marker.json        # execute; result recorded under dataRoot/runs
+scripts/mosaic-task.mjs list                           # list runs and statuses
+scripts/test-task.sh                                   # selftests (schema negatives + live runs)
+```
+
+A run exits 0 only when its expectation is met (`expectExact` match); mismatches, nonzero agent exits, and timeouts record `status: failed` in `result.json` and exit 1. Each run gets a unique directory — rerunning never rewrites history.
+
 See `docs/plans/2026-09-02_atomic-mosaic-foundation.md` for the full plan.
 
 Inside the container:
@@ -93,7 +115,9 @@ scripts/bootstrap.sh   # create config.json if absent (idempotent)
 scripts/build.sh       # build the image
 scripts/hello.sh       # one-shot request; prints the model response
 scripts/verify.sh      # full gated test; exit 0 only on exact MOSAIC_HELLO_OK
+scripts/run-task.sh    # run a mission/task file (see Missions & tasks)
 scripts/test-config.sh # fast config-layer selftests (no Docker)
+scripts/test-task.sh   # mission/task selftests (schema + live runs)
 scripts/reset.sh       # delete the configured data root (safety-checked)
 ```
 
diff --git a/missions/hello.json b/missions/hello.json
new file mode 100644
index 00000000..ab65b889
--- /dev/null
+++ b/missions/hello.json
@@ -0,0 +1,9 @@
+{
+  "missionVersion": 1,
+  "id": "m-hello",
+  "objective": "Prove the startup marker path of the mosaic-poc-agent.",
+  "directives": [
+    "Startup verification requests are answered with the marker only.",
+    "No explanation, no formatting."
+  ]
+}
diff --git a/scripts/mosaic-task.mjs b/scripts/mosaic-task.mjs
new file mode 100755
index 00000000..12610036
--- /dev/null
+++ b/scripts/mosaic-task.mjs
@@ -0,0 +1,318 @@
+#!/usr/bin/env node
+/**
+ * Mosaic mission/task layer (M2, host-side only).
+ *
+ * Operations:
+ *   validate <file>   Strictly validate a task (and its referenced mission);
+ *                     print the resolved task on success. Writes nothing.
+ *   run <taskFile>    Execute the task through the config-driven container
+ *                     path; record an immutable run under <dataRoot>/runs/.
+ *   list              List runs recorded under <dataRoot>/runs/.
+ *
+ * Exit codes:
+ *   0 success (run: status "succeeded")
+ *   1 run failed (mismatch, nonzero exit, timeout) — result.json still written
+ *   2 invalid task/mission data
+ *   3 configuration problem
+ *   4 file/environment problem
+ *
+ * M2 scope: mission directives are validated and snapshotted into run
+ * records for provenance; they are NOT yet injected into the runtime
+ * system prompt (capability/policy layer comes later).
+ *
+ * Invariants carried over from the configuration layer:
+ *   - Strict schemas; unknown keys rejected; versions pinned at 1.
+ *   - Validation never writes.
+ *   - Run records are write-once and never rewritten by a later run.
+ *   - No secrets in mission/task data or run records.
+ */
+
+import fs from "node:fs";
+import path from "node:path";
+import process from "node:process";
+import { randomBytes } from "node:crypto";
+import { spawnSync } from "node:child_process";
+import { fileURLToPath } from "node:url";
+
+const PROJECT_ROOT = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
+const RUNS_DIRNAME = "runs";
+const ID_PATTERN = /^[a-z0-9][a-z0-9._-]{0,63}$/;
+const DEFAULT_TIMEOUT_SECONDS = 120;
+
+function fail(exitCode, message) {
+  process.stderr.write(`mosaic-task: ${message}\n`);
+  process.exit(exitCode);
+}
+
+function isPlainObject(value) {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+
+function rejectUnknownKeys(object, allowed, where) {
+  for (const key of Object.keys(object)) {
+    if (!allowed.includes(key)) fail(2, `unsupported ${where} key: "${key}"`);
+  }
+}
+
+function readJsonFile(file, what) {
+  let stat;
+  try {
+    stat = fs.lstatSync(file);
+  } catch {
+    fail(4, `${what} not found: ${file}`);
+  }
+  if (!stat.isFile() || stat.isSymbolicLink()) {
+    fail(4, `${what} must be a regular, non-symbolic-link file: ${file}`);
+  }
+  let document;
+  try {
+    document = JSON.parse(fs.readFileSync(file, "utf8"));
+  } catch (error) {
+    fail(2, `${what} is not valid JSON (${file}): ${error.message}`);
+  }
+  return document;
+}
+
+function validateId(value, what) {
+  if (typeof value !== "string" || !ID_PATTERN.test(value)) {
+    fail(2, `${what} must match ${ID_PATTERN} (got ${JSON.stringify(value)})`);
+  }
+  return value;
+}
+
+function validateMission(document, file) {
+  if (!isPlainObject(document)) fail(2, "mission must be a JSON object");
+  rejectUnknownKeys(document, ["missionVersion", "id", "objective", "directives"], "mission");
+  if (document.missionVersion !== 1) {
+    fail(2, `unsupported missionVersion: ${JSON.stringify(document.missionVersion)} (supported: 1)`);
+  }
+  validateId(document.id, "mission id");
+  if (typeof document.objective !== "string" || document.objective.trim().length === 0 || document.objective.length > 4000) {
+    fail(2, "mission objective must be a non-empty string of at most 4000 characters");
+  }
+  let directives = [];
+  if (document.directives !== undefined) {
+    if (!Array.isArray(document.directives)) fail(2, "mission directives must be an array of strings");
+    directives = document.directives.map((d, i) => {
+      if (typeof d !== "string" || d.trim().length === 0 || d.length > 2000 || d.includes("\0")) {
+        fail(2, `mission directive ${i} must be a non-empty string of at most 2000 characters`);
+      }
+      return d;
+    });
+  }
+  return { missionVersion: document.missionVersion, id: document.id, objective: document.objective, directives };
+}
+
+function validateTask(document, file) {
+  if (!isPlainObject(document)) fail(2, "task must be a JSON object");
+  rejectUnknownKeys(document, ["taskVersion", "id", "prompt", "mission", "expectExact", "timeoutSeconds"], "task");
+  if (document.taskVersion !== 1) {
+    fail(2, `unsupported taskVersion: ${JSON.stringify(document.taskVersion)} (supported: 1)`);
+  }
+  validateId(document.id, "task id");
+
+  if (typeof document.prompt !== "string" || document.prompt.length === 0 || document.prompt.length > 20000 || document.prompt.includes("\0")) {
+    fail(2, "task prompt must be a non-empty string of at most 20000 characters");
+  }
+
+  let mission = null;
+  let missionId = null;
+  let missionSnapshot = null;
+  if (document.mission !== undefined && document.mission !== null) {
+    if (typeof document.mission !== "string" || document.mission.length === 0) {
+      fail(2, 'task "mission" must be a path string when present');
+    }
+    const missionPath = path.resolve(path.dirname(path.resolve(file)), document.mission);
+    missionSnapshot = validateMission(readJsonFile(missionPath, "mission file"), missionPath);
+    mission = document.mission;
+    missionId = missionSnapshot.id;
+  }
+
+  let expectExact = null;
+  if (document.expectExact !== undefined && document.expectExact !== null) {
+    if (typeof document.expectExact !== "string" || document.expectExact.length === 0 || document.expectExact.length > 500 || /[^\P{C}\t\n]/u.test(document.expectExact)) {
+      fail(2, "task expectExact must be a non-empty string of at most 500 characters without control characters (tab/newline allowed)");
+    }
+    expectExact = document.expectExact;
+  }
+
+  let timeoutSeconds = DEFAULT_TIMEOUT_SECONDS;
+  if (document.timeoutSeconds !== undefined && document.timeoutSeconds !== null) {
+    if (!Number.isInteger(document.timeoutSeconds) || document.timeoutSeconds < 5 || document.timeoutSeconds > 600) {
+      fail(2, "task timeoutSeconds must be an integer between 5 and 600");
+    }
+    timeoutSeconds = document.timeoutSeconds;
+  }
+
+  return {
+    taskVersion: document.taskVersion,
+    id: document.id,
+    prompt: document.prompt,
+    mission,
+    missionId,
+    missionSnapshot,
+    expectExact,
+    timeoutSeconds,
+  };
+}
+
+function loadConfig() {
+  const proc = spawnSync(process.execPath, [path.join(PROJECT_ROOT, "scripts", "mosaic-config.mjs"), "validate"], {
+    cwd: PROJECT_ROOT,
+    encoding: "utf8",
+    maxBuffer: 1024 * 1024,
+  });
+  if (proc.status !== 0) {
+    fail(3, `configuration problem (exit ${proc.status}); run scripts/bootstrap.sh or fix config.json`);
+  }
+  return JSON.parse(proc.stdout);
+}
+
+function runsRoot(resolvedConfig) {
+  return path.join(resolvedConfig.dataRoot, RUNS_DIRNAME);
+}
+
+function utcStamp() {
+  return new Date().toISOString().replace(/[-:]/g, "").replace(/\.\d+Z$/, "Z");
+}
+
+function writeOnce(file, content) {
+  const fd = fs.openSync(file, "wx", 0o644); // exclusive: never overwrite
+  try {
+    fs.writeFileSync(fd, content);
+  } finally {
+    fs.closeSync(fd);
+  }
+}
+
+function runTask(taskFile) {
+  const resolved = JSON.parse(
+    spawnSync(process.execPath, [path.join(PROJECT_ROOT, "scripts", "mosaic-config.mjs"), "validate"], {
+      cwd: PROJECT_ROOT,
+      encoding: "utf8",
+      maxBuffer: 1024 * 1024,
+    }).stdout,
+  );
+
+  const task = validateTask(readJsonFile(taskFile, "task file"), path.resolve(taskFile));
+  const runId = `r-${utcStamp()}-${randomBytes(3).toString("hex")}`;
+  const runDir = path.join(runsRoot(resolved), runId);
+
+  fs.mkdirSync(runDir, { recursive: true });
+
+  // Immutable input snapshots (evidence of exactly what was executed).
+  const rawTask = fs.readFileSync(path.resolve(taskFile), "utf8");
+  writeOnce(path.join(runDir, "task.json"), rawTask);
+  if (task.missionSnapshot) {
+    const missionPath = path.resolve(path.dirname(path.resolve(taskFile)), task.mission);
+    writeOnce(path.join(runDir, "mission.json"), fs.readFileSync(missionPath, "utf8"));
+  }
+
+  const startedAt = new Date();
+  const stderrFile = path.join(runDir, "stderr.txt");
+  const proc = spawnSync(
+    "docker",
+    ["compose", "run", "--rm", "-T", "mosaic-agent", task.prompt],
+    {
+      cwd: PROJECT_ROOT,
+      env: process.env, // MOSAIC_DATA_ROOT / MOSAIC_PROVIDER / MOSAIC_MODEL resolved by run-task.sh
+      input: "", // stdin detached: print mode must never wait on a terminal (see issue #5)
+      encoding: "utf8",
+      maxBuffer: 16 * 1024 * 1024,
+      timeout: task.timeoutSeconds * 1000,
+      killSignal: "SIGKILL",
+    },
+  );
+  const finishedAt = new Date();
+
+  fs.writeFileSync(stderrFile, proc.stderr ?? "", { flag: "wx" });
+
+  const response = (proc.stdout ?? "").replace(/^[^\S\n]+/, "").replace(/[^\S\n]+$/, "").trim();
+  let status = "succeeded";
+  let reason = null;
+  let expected = task.expectExact;
+
+  if (proc.error && proc.error.code === "ETIMEDOUT") {
+    status = "failed";
+    reason = "timeout";
+  } else if (proc.error) {
+    status = "failed";
+    reason = `spawn-error: ${proc.error.code ?? proc.error.message}`;
+  } else if (proc.status !== 0) {
+    status = "failed";
+    reason = "exit-nonzero";
+  } else if (expected !== null && response !== expected) {
+    status = "failed";
+    reason = "expect-mismatch";
+  }
+
+  const result = {
+    runVersion: 1,
+    runId,
+    taskId: task.id,
+    missionId: task.missionId,
+    status,
+    reason,
+    request: task.prompt,
+    response,
+    expectedExact: expected,
+    exitCode: proc.status,
+    signal: proc.signal ?? null,
+    provider: resolved.execution.provider,
+    model: resolved.execution.model,
+    startedAt: startedAt.toISOString(),
+    finishedAt: finishedAt.toISOString(),
+    durationMs: finishedAt.getTime() - startedAt.getTime(),
+  };
+
+  writeOnce(path.join(runDir, "result.json"), `${JSON.stringify(result, null, 2)}\n`);
+
+  process.stdout.write(`run: ${runId}\nstatus: ${status}${reason ? ` (${reason})` : ""}\nresponse: ${response}\n`);
+  process.exit(status === "succeeded" ? 0 : 1);
+}
+
+function listRuns() {
+  const resolved = loadConfig();
+  const root = runsRoot(resolved);
+  let entries = [];
+  try {
+    entries = fs.readdirSync(root).filter((name) => name.startsWith("r-")).sort();
+  } catch {
+    // No runs yet.
+  }
+  for (const runId of entries) {
+    let status = "unknown";
+    let taskId = "-";
+    try {
+      const result = JSON.parse(fs.readFileSync(path.join(root, runId, "result.json"), "utf8"));
+      status = result.status;
+      taskId = result.taskId;
+    } catch {
+      // Incomplete run record; report as unknown.
+    }
+    process.stdout.write(`${runId}  ${status.padEnd(9)}  ${taskId}\n`);
+  }
+}
+
+const operation = process.argv[2];
+const target = process.argv[3];
+
+switch (operation) {
+  case "validate": {
+    if (!target) fail(4, "usage: mosaic-task.mjs validate <taskFile>");
+    const file = path.resolve(target);
+    const task = validateTask(readJsonFile(file, "task file"), file);
+    const { missionSnapshot, ...rest } = task;
+    process.stdout.write(`${JSON.stringify(rest, null, 2)}\n`);
+    process.exit(0);
+  }
+  case "run":
+    if (!target) fail(4, "usage: mosaic-task.mjs run <taskFile>");
+    runTask(path.resolve(target));
+    break;
+  case "list":
+    listRuns();
+    process.exit(0);
+  default:
+    fail(4, `unknown operation: ${JSON.stringify(operation ?? "")} (expected validate | run | list)`);
+}
diff --git a/scripts/run-task.sh b/scripts/run-task.sh
new file mode 100755
index 00000000..7a8af449
--- /dev/null
+++ b/scripts/run-task.sh
@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+# Run a mission/task file through the config-driven container path.
+#
+# Usage: scripts/run-task.sh run <task.json>   (also: validate <task.json>, list)
+#
+# Ensures the configuration is valid and the data root carries the
+# ownership marker before any task executes.
+set -euo pipefail
+cd "$(dirname "$0")/.."
+# shellcheck source=common.sh
+source scripts/common.sh
+
+load_config
+bootstrap_runtime_dir
+
+exec node scripts/mosaic-task.mjs "$@"
diff --git a/scripts/test-task.sh b/scripts/test-task.sh
new file mode 100755
index 00000000..685c80fc
--- /dev/null
+++ b/scripts/test-task.sh
@@ -0,0 +1,125 @@
+#!/usr/bin/env bash
+# Sandboxed selftests for the mission/task layer.
+#
+# Fast cases are validation-only (no Docker, no network). The final cases
+# execute real tasks through the container path and therefore require a
+# working configuration, credentials, and Docker.
+set -uo pipefail
+cd "$(dirname "$0")/.."
+
+SANDBOX="$(mktemp -d)"
+trap 'rm -rf "$SANDBOX"' EXIT
+
+PASS=0
+FAIL=0
+
+expect_exit() {
+    local name="$1" expected="$2"
+    shift 3
+    local rc
+    "$@" >/dev/null 2>&1
+    rc=$?
+    if [ "$rc" -eq "$expected" ]; then
+        PASS=$((PASS+1)); echo "ok   $name (exit $rc)"
+    else
+        FAIL=$((FAIL+1)); echo "FAIL $name (exit $rc, expected $expected)"
+    fi
+}
+
+check() {
+    if [ "$2" = "0" ]; then PASS=$((PASS+1)); echo "ok   $1"; else FAIL=$((FAIL+1)); echo "FAIL $1"; fi
+}
+
+CONFIG="$SANDBOX/config.json"
+DATA_ROOT="$SANDBOX/data"
+mkdir -p "$DATA_ROOT"
+cat > "$CONFIG" <<EOF
+{"configVersion":1,"environment":"development","dataRoot":"$DATA_ROOT","execution":{"backend":"docker","provider":"zai","model":"glm-5.3-flash"}}
+EOF
+export MOSAIC_CONFIG="$CONFIG"
+
+TASK="node scripts/mosaic-task.mjs"
+
+good_task() { # args: file [overrides as jq-less JSON fragments]
+    cat > "$1" <<EOF
+{"taskVersion":1,"id":"t-ok","prompt":"Return your startup marker and nothing else.","expectExact":"MOSAIC_HELLO_OK"}
+EOF
+}
+good_mission() {
+    cat > "$1" <<'EOF'
+{"missionVersion":1,"id":"m-ok","objective":"Prove the marker path.","directives":["Be terse."]}
+EOF
+}
+
+# ---------- fast: schema negatives ----------
+good_task "$SANDBOX/ok.json"
+expect_exit "valid task validates" 0 -- $TASK validate "$SANDBOX/ok.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","extra":1}' > "$SANDBOX/unknownkey.json"
+expect_exit "unknown task key exits 2" 2 -- $TASK validate "$SANDBOX/unknownkey.json"
+
+printf '{"taskVersion":2,"id":"t-x","prompt":"hi"}' > "$SANDBOX/badver.json"
+expect_exit "unsupported taskVersion exits 2" 2 -- $TASK validate "$SANDBOX/badver.json"
+
+printf '{"taskVersion":1,"id":"BAD ID","prompt":"hi"}' > "$SANDBOX/badid.json"
+expect_exit "invalid task id exits 2" 2 -- $TASK validate "$SANDBOX/badid.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":""}' > "$SANDBOX/emptyprompt.json"
+expect_exit "empty prompt exits 2" 2 -- $TASK validate "$SANDBOX/emptyprompt.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","expectExact":"bad\\u0000nul"}' > "$SANDBOX/badexpect.json"
+expect_exit "NUL in expectExact exits 2" 2 -- $TASK validate "$SANDBOX/badexpect.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","timeoutSeconds":9999}' > "$SANDBOX/badtimeout.json"
+expect_exit "out-of-range timeout exits 2" 2 -- $TASK validate "$SANDBOX/badtimeout.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","mission":"missing.json"}' > "$SANDBOX/missmission.json"
+expect_exit "missing mission file exits 4" 4 -- $TASK validate "$SANDBOX/missmission.json"
+
+good_mission "$SANDBOX/m.json"
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","mission":"m.json"}' > "$SANDBOX/withmission.json"
+expect_exit "task with valid mission validates" 0 -- $TASK validate "$SANDBOX/withmission.json"
+
+printf '{"missionVersion":1,"id":"m-x","objective":"o","extra":1}' > "$SANDBOX/badmission.json"
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","mission":"badmission.json"}' > "$SANDBOX/withbadmission.json"
+expect_exit "invalid mission exits 2" 2 -- $TASK validate "$SANDBOX/withbadmission.json"
+
+expect_exit "validate missing task exits 4" 4 -- $TASK validate "$SANDBOX/nope.json"
+
+# validation writes nothing: task dir listing unchanged is implied; check mtime of ok.json
+M1=$(stat -c %Y "$SANDBOX/ok.json"); sleep 1.1
+$TASK validate "$SANDBOX/ok.json" >/dev/null 2>&1
+M2=$(stat -c %Y "$SANDBOX/ok.json")
+[ "$M1" = "$M2" ] && check "validation does not modify the task file" 0 || check "validation does not modify the task file" 1
+
+# ---------- live: real runs (Docker + credentials required) ----------
+if docker info >/dev/null 2>&1; then
+    expect_exit "live hello task succeeds with exact marker" 0 -- \
+        scripts/run-task.sh run "$SANDBOX/ok.json"
+
+    [ -f "$DATA_ROOT/runs" ] && RUNS1=$(ls "$DATA_ROOT/runs" | wc -l)
+    R1="$(ls "$DATA_ROOT/runs" | head -1)"
+    [ -f "$DATA_ROOT/runs/$R1/result.json" ] && check "result.json written in run dir" 0 || check "result.json written in run dir" 1
+    node -e '
+const r = JSON.parse(require("fs").readFileSync(process.argv[1], "utf8"));
+process.exit(r.status === "succeeded" && r.response === "MOSAIC_HELLO_OK" && r.expectedExact === "MOSAIC_HELLO_OK" ? 0 : 1);
+' "$DATA_ROOT/runs/$R1/result.json"
+    check "result.json contents are correct" $?
+
+    printf '{"taskVersion":1,"id":"t-wrong","prompt":"Return your startup marker and nothing else.","expectExact":"MOSAIC_NOT_OK"}' > "$SANDBOX/wrong.json"
+    expect_exit "wrong expectExact fails with exit 1" 1 -- \
+        scripts/run-task.sh run "$SANDBOX/wrong.json"
+
+    RUNS2=$(ls "$DATA_ROOT/runs" | wc -l)
+    [ "$RUNS2" -gt "${RUNS1:-0}" ] && check "each run gets a distinct run dir (no clobber)" 0 \
+        || check "each run gets a distinct run dir (no clobber)" 1
+
+    COUNT=$($TASK list | wc -l)
+    [ "$COUNT" -ge 2 ] && check "list shows both runs" 0 || check "list shows both runs" 1
+else
+    echo "skip live task cases (docker unavailable)"
+fi
+
+echo
+echo "selftest: $PASS passed, $FAIL failed"
+[ "$FAIL" -eq 0 ]
diff --git a/tasks/hello-marker.json b/tasks/hello-marker.json
new file mode 100644
index 00000000..9396b925
--- /dev/null
+++ b/tasks/hello-marker.json
@@ -0,0 +1,8 @@
+{
+  "taskVersion": 1,
+  "id": "t-hello-marker",
+  "prompt": "Return your startup marker and nothing else.",
+  "mission": "../missions/hello.json",
+  "expectExact": "MOSAIC_HELLO_OK",
+  "timeoutSeconds": 120
+}