diff --git a/README.md b/README.md
index 9ede40f..787204b 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@
 
 ### Features
 
-- **Comprehensive CLI Tools** - 67 tools organized into 15 categories; Designed to integrate with any AI agent
+- **Comprehensive CLI Tools** - 69 tools organized into 15 categories; Designed to integrate with any AI agent
 - **Python-based Tools** - Used for agent / workflow code generation; Easier integration with [Bridgic](https://github.com/bitsky-tech/bridgic) 
 - **Snapshot with Semantic Invariance** - A representation of page snapshot based on accessibility tree and a specially designed ref-generation algorithm that ensures element refs remain unchanged across page reloads
 - **Skills** - Used for guided exploration and code generation; Compatible with most of coding agents
@@ -168,7 +168,7 @@ if __name__ == "__main__":
 
 ### CLI Tools
 
-`bridgic-browser` ships with a command-line interface for controlling a browser from the terminal (67 tools organized into 15 categories). A persistent daemon process holds a browser instance; each CLI invocation connects over a Unix domain socket and exits immediately.
+`bridgic-browser` ships with a command-line interface for controlling a browser from the terminal (69 tools organized into 15 categories). A persistent daemon process holds a browser instance; each CLI invocation connects over a Unix domain socket and exits immediately.
 
 #### Configuration
 
@@ -410,7 +410,7 @@ browser = Browser(cdp="ws://localhost:9222/devtools/browser/...")
 | Wait | `wait [SECONDS] [TEXT] [--gone]` |
 | Tabs | `tabs`, `new-tab`, `switch-tab`, `close-tab` |
 | Evaluate | `eval`, `eval-on` |
-| Capture | `screenshot`, `pdf` |
+| Capture | `screenshot`, `pdf`, `downloads`, `wait-download` |
 | Network | `network-start`, `network-stop`, `network`, `wait-network` |
 | Dialog | `dialog-setup`, `dialog`, `dialog-remove` |
 | Storage | `storage-save`, `storage-load`, `cookies-clear`, `cookies`, `cookie-set` |
@@ -427,7 +427,7 @@ bridgic-browser scroll -h
 
 ### Python Tools
 
-Bridgic Browser provides 67 tools organized into 15 categories. Use `BrowserToolSetBuilder` with category/name selection for scenario-focused tool sets.
+Bridgic Browser provides 69 tools organized into 15 categories. Use `BrowserToolSetBuilder` with category/name selection for scenario-focused tool sets.
 
 #### Category-based Selection
 
@@ -533,9 +533,11 @@ tools = [*builder1.build()["tool_specs"], *builder2.build()["tool_specs"]]
 **Wait (1 tool):**
 - `wait_for(time_seconds, text, text_gone, selector, state, timeout)` - Wait for conditions
 
-**Capture (2 tools):**
+**Capture (4 tools):**
 - `take_screenshot(filename=None, ref=None, full_page=False, type="png")` - Capture screenshot
 - `save_pdf(filename)` - Save page as PDF
+- `get_downloaded_files_text()` - Numbered list of all files downloaded in this session
+- `wait_for_next_download(timeout=30.0)` - Block until next download completes; returns a one-line summary or a timeout message
 
 **Network (4 tools):**
 - `start_network_capture()` / `stop_network_capture()` / `get_network_requests()` - Network monitoring
@@ -609,6 +611,8 @@ tools = [*builder1.build()["tool_specs"], *builder2.build()["tool_specs"]]
 | `wait` | `wait_for` |
 | `screenshot` | `take_screenshot` |
 | `pdf` | `save_pdf` |
+| `downloads` | `get_downloaded_files_text` |
+| `wait-download` | `wait_for_next_download` |
 | `network-start` | `start_network_capture` |
 | `network` | `get_network_requests` |
 | `network-stop` | `stop_network_capture` |
@@ -702,6 +706,8 @@ browser = Browser(stealth=config, headless=False)
 
 #### Downloads
 
+`Browser` always creates a `DownloadManager` and always accepts downloads. Files are saved to `downloads_path` if configured, or `~/Downloads` by default.
+
 bridgic preserves the original filename, suppresses the "Save As" dialog, and keeps the API the same across modes. Internally there are two pipelines — `DownloadManager` for non-CDP / CDP-owned, and `CdpDownloadRenamer` for CDP-borrowed (page-level CDP routing of `setDownloadBehavior(allowAndName)`). See [CLAUDE.md → Downloads](CLAUDE.md#downloads) for the full design.
 
 ##### Download path matrix
@@ -713,7 +719,7 @@ bridgic preserves the original filename, suppresses the "Save As" dialog, and ke
 | **CLI** | CDP (`--cdp ...`) | yes | the explicit value |
 | **CLI** | CDP | no | the CLI client's working directory at command time (`os.getcwd()`) — `curl -O`-style ergonomics |
 | **SDK** (`Browser(...)`) | non-CDP | yes | the explicit value |
-| **SDK** | non-CDP | no | downloads not captured (Playwright wipes the temp dir on close — pass `downloads_path`) |
+| **SDK** | non-CDP | no | `~/Downloads` (DownloadManager auto-default) |
 | **SDK** | CDP (`Browser(cdp=...)`) | yes | the explicit value |
 | **SDK** | CDP | no | `~/Downloads` (SDK has no CLI CWD hint) |
 
@@ -721,13 +727,22 @@ bridgic preserves the original filename, suppresses the "Save As" dialog, and ke
 # Non-CDP (DownloadManager pipeline)
 browser = Browser(downloads_path="./downloads", headless=True)
 await browser.navigate_to("https://example.com")
-# Programmatic access to completed downloads
+
+# Trigger a download, then wait for it to complete
+await browser.click_element_by_ref("8d4b03a9")
+result = await browser.wait_for_next_download(timeout=30.0)
+# "Download complete: report.pdf — 261.0 KB — /home/user/Downloads/report.pdf"
+
+# Get the formatted list of everything downloaded in this session
+print(await browser.get_downloaded_files_text())
+
+# Or access the raw list
 for f in browser.download_manager.downloaded_files:
     print(f"Downloaded: {f.file_name} ({f.file_size} bytes)")
 
 # CDP-borrowed (CdpDownloadRenamer pipeline; downloads land at downloads_path
-# with real filenames; download_manager is None — wait_for_download is
-# unsupported here).
+# with real filenames; download_manager is None — wait_for_download /
+# wait_for_next_download are unsupported here).
 browser = Browser(cdp="auto", downloads_path="./downloads")
 ```
 
diff --git a/README_zh.md b/README_zh.md
index 3f3a674..5d27f08 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -8,7 +8,7 @@
 
 ### 特性
 
-- **完善的 CLI 工具** — 67 个工具分为 15 类；可与各类 AI 智能体集成
+- **完善的 CLI 工具** — 69 个工具分为 15 类；可与各类 AI 智能体集成
 - **基于 Python 的工具** — 用于智能体 / 工作流代码生成；更易与 [Bridgic](https://github.com/bitsky-tech/bridgic) 集成
 - **语义不变的快照** — 基于无障碍树与专门设计的 ref 生成算法，保证元素 ref 在页面重载后仍可对应同一元素
 - **Skills** — 用于引导探索与代码生成；兼容多数编程类智能体
@@ -168,7 +168,7 @@ if __name__ == "__main__":
 
 ### CLI 工具
 
-`bridgic-browser` 提供命令行界面，用于在终端控制浏览器（67 个工具、15 类）。持久化 daemon 进程持有浏览器实例；每次 CLI 调用通过 Unix 域套接字连接后立即退出。
+`bridgic-browser` 提供命令行界面，用于在终端控制浏览器（69 个工具、15 类）。持久化 daemon 进程持有浏览器实例；每次 CLI 调用通过 Unix 域套接字连接后立即退出。
 
 #### 配置
 
@@ -404,7 +404,7 @@ browser = Browser(cdp="ws://localhost:9222/devtools/browser/...")
 | 等待 | `wait [SECONDS] [TEXT] [--gone]` |
 | 标签页 | `tabs`, `new-tab`, `switch-tab`, `close-tab` |
 | 执行 | `eval`, `eval-on` |
-| 捕获 | `screenshot`, `pdf` |
+| 捕获 | `screenshot`, `pdf`, `downloads`, `wait-download` |
 | 网络 | `network-start`, `network-stop`, `network`, `wait-network` |
 | 对话框 | `dialog-setup`, `dialog`, `dialog-remove` |
 | 存储 | `storage-save`, `storage-load`, `cookies-clear`, `cookies`, `cookie-set` |
@@ -421,7 +421,7 @@ bridgic-browser scroll -h
 
 ### Python 工具
 
-Bridgic Browser 提供 67 个工具，分为 15 类。使用 `BrowserToolSetBuilder` 按类别/名称选择，以适配不同场景。
+Bridgic Browser 提供 69 个工具，分为 15 类。使用 `BrowserToolSetBuilder` 按类别/名称选择，以适配不同场景。
 
 #### 按类别选择
 
@@ -527,9 +527,11 @@ tools = [*builder1.build()["tool_specs"], *builder2.build()["tool_specs"]]
 **等待（1 个工具）：**
 - `wait_for(time_seconds, text, text_gone, selector, state, timeout)` - 等待条件
 
-**捕获（2 个工具）：**
+**捕获（4 个工具）：**
 - `take_screenshot(filename=None, ref=None, full_page=False, type="png")` - 截图
 - `save_pdf(filename)` - 将页面保存为 PDF
+- `get_downloaded_files_text()` - 返回本次会话所有已下载文件的编号列表
+- `wait_for_next_download(timeout=30.0)` - 等待下一个下载完成；返回单行摘要或超时提示
 
 **网络（4 个工具）：**
 - `start_network_capture()` / `stop_network_capture()` / `get_network_requests()` - 网络监控
@@ -603,6 +605,8 @@ tools = [*builder1.build()["tool_specs"], *builder2.build()["tool_specs"]]
 | `wait` | `wait_for` |
 | `screenshot` | `take_screenshot` |
 | `pdf` | `save_pdf` |
+| `downloads` | `get_downloaded_files_text` |
+| `wait-download` | `wait_for_next_download` |
 | `network-start` | `start_network_capture` |
 | `network` | `get_network_requests` |
 | `network-stop` | `stop_network_capture` |
@@ -696,6 +700,8 @@ browser = Browser(stealth=config, headless=False)
 
 #### 下载
 
+`Browser` 始终创建 `DownloadManager` 并自动接受下载。文件保存至 `downloads_path`（若已配置），否则默认保存到 `~/Downloads`。
+
 bridgic 在所有模式下都保留原始文件名、屏蔽"另存为"对话框,API 一致。内部有两条流水线 —— 非 CDP / CDP-owned 用 `DownloadManager`,CDP-borrowed 用 `CdpDownloadRenamer`(通过 page-level CDP session 下发 `setDownloadBehavior(allowAndName)`)。完整设计见 [CLAUDE.md → Downloads](CLAUDE.md#downloads)。
 
 ##### 下载路径矩阵
@@ -707,7 +713,7 @@ bridgic 在所有模式下都保留原始文件名、屏蔽"另存为"对话框,
 | **CLI** | CDP (`--cdp ...`) | 有 | 显式值 |
 | **CLI** | CDP | 无 | CLI 启动时的工作目录(`os.getcwd()`)—— `curl -O` 风格 |
 | **SDK** (`Browser(...)`) | 非 CDP | 有 | 显式值 |
-| **SDK** | 非 CDP | 无 | 下载不被捕获(Playwright 会清掉 temp dir —— 请显式传 `downloads_path`) |
+| **SDK** | 非 CDP | 无 | `~/Downloads`(DownloadManager 自动默认) |
 | **SDK** | CDP (`Browser(cdp=...)`) | 有 | 显式值 |
 | **SDK** | CDP | 无 | `~/Downloads`(SDK 没有 CLI CWD 提示) |
 
@@ -715,12 +721,21 @@ bridgic 在所有模式下都保留原始文件名、屏蔽"另存为"对话框,
 # 非 CDP(DownloadManager 流水线)
 browser = Browser(downloads_path="./downloads", headless=True)
 await browser.navigate_to("https://example.com")
-# 程序化访问已完成的下载
+
+# 触发下载，然后等待其完成
+await browser.click_element_by_ref("8d4b03a9")
+result = await browser.wait_for_next_download(timeout=30.0)
+# "Download complete: report.pdf — 261.0 KB — /home/user/Downloads/report.pdf"
+
+# 列出本次会话的所有下载记录
+print(await browser.get_downloaded_files_text())
+
+# 或直接访问原始列表
 for f in browser.download_manager.downloaded_files:
     print(f"已下载:{f.file_name}({f.file_size} 字节)")
 
 # CDP-borrowed(CdpDownloadRenamer 流水线;文件以真名落到 downloads_path,
-# download_manager 为 None —— wait_for_download 在此模式不支持)
+# download_manager 为 None —— wait_for_download / wait_for_next_download 在此模式不支持)
 browser = Browser(cdp="auto", downloads_path="./downloads")
 ```
 
diff --git a/bridgic/browser/_cli_catalog.py b/bridgic/browser/_cli_catalog.py
index 1b796a4..cc69b88 100644
--- a/bridgic/browser/_cli_catalog.py
+++ b/bridgic/browser/_cli_catalog.py
@@ -43,7 +43,7 @@
     (ToolCategory.KEYBOARD, ["type", "press", "key-down", "key-up"]),
     (ToolCategory.MOUSE, ["scroll", "mouse-click", "mouse-move", "mouse-drag", "mouse-down", "mouse-up"]),
     (ToolCategory.WAIT, ["wait"]),
-    (ToolCategory.CAPTURE, ["screenshot", "pdf"]),
+    (ToolCategory.CAPTURE, ["screenshot", "pdf", "downloads", "wait-download"]),
     (ToolCategory.NETWORK, ["network-start", "network", "network-stop", "wait-network"]),
     (ToolCategory.DIALOG, ["dialog-setup", "dialog", "dialog-remove"]),
     (ToolCategory.STORAGE, ["cookies", "cookie-set", "cookies-clear", "storage-save", "storage-load"]),
@@ -115,6 +115,8 @@
     "close-tab": (ToolCategory.TABS, "Close a tab by page_id (or current tab if omitted); run 'tabs' first to list page IDs"),
     "screenshot": (ToolCategory.CAPTURE, "Save a screenshot to PATH [--full-page]"),
     "pdf": (ToolCategory.CAPTURE, "Save the current page as PDF"),
+    "downloads": (ToolCategory.CAPTURE, "List all files downloaded in this session"),
+    "wait-download": (ToolCategory.CAPTURE, "Wait up to SECONDS for the next download to complete (default: 30)"),
     "console-start": (ToolCategory.DEVELOPER, "Start capturing browser console output"),
     "console-stop": (ToolCategory.DEVELOPER, "Stop capturing browser console output"),
     "console": (ToolCategory.DEVELOPER, "Get captured console messages [--filter TYPE] [--no-clear]"),
@@ -219,6 +221,8 @@
     "video-stop": "stop_video",
     "close": "close",
     "resize": "browser_resize",
+    "downloads": "get_downloaded_files_text",
+    "wait-download": "wait_for_next_download",
 }
 
 # CLI commands that are informational and not backed by Browser tool methods.
diff --git a/bridgic/browser/cli/_commands.py b/bridgic/browser/cli/_commands.py
index c860173..af68352 100644
--- a/bridgic/browser/cli/_commands.py
+++ b/bridgic/browser/cli/_commands.py
@@ -1009,6 +1009,32 @@ def cmd_video_stop(path: str | None) -> None:
         _err(exc)
 
 
+# ── Downloads ─────────────────────────────────────────────────────────────────
+
+@cli.command("downloads", context_settings=CONTEXT_SETTINGS)
+def cmd_downloads() -> None:
+    """List all files downloaded in this browser session."""
+    try:
+        _ok(send_command("downloads", {}, start_if_needed=False))
+    except Exception as exc:
+        _err(exc)
+
+
+@cli.command("wait-download", context_settings=CONTEXT_SETTINGS)
+@click.argument("seconds", type=float, required=False, default=30.0)
+def cmd_wait_download(seconds: float) -> None:
+    """Wait up to SECONDS for the next download to complete (default: 30).
+
+    Run this immediately after clicking a download link or button.
+    Returns the file name, size, and path when the download finishes,
+    or an error message if the timeout expires with no download.
+    """
+    try:
+        _ok(send_command("wait_download", {"timeout": seconds}, start_if_needed=False))
+    except Exception as exc:
+        _err(exc)
+
+
 # ── Lifecycle ─────────────────────────────────────────────────────────────────
 
 @cli.command("close", context_settings=CONTEXT_SETTINGS)
diff --git a/bridgic/browser/cli/_daemon.py b/bridgic/browser/cli/_daemon.py
index a597846..9b5872c 100644
--- a/bridgic/browser/cli/_daemon.py
+++ b/bridgic/browser/cli/_daemon.py
@@ -527,6 +527,17 @@ async def _handle_resize(browser: "Browser", args: Dict[str, Any]) -> str:
     return await browser.browser_resize(args.get("width", 1280), args.get("height", 720))
 
 
+# ── Downloads ─────────────────────────────────────────────────────────────────
+
+async def _handle_downloads(browser: "Browser", _args: Dict[str, Any]) -> str:
+    return await browser.get_downloaded_files_text()
+
+
+async def _handle_wait_download(browser: "Browser", args: Dict[str, Any]) -> str:
+    timeout = float(args.get("timeout", 30.0))
+    return await browser.wait_for_next_download(timeout=timeout)
+
+
 _HANDLERS = {
     # Navigation
     "open": _handle_open,
@@ -611,6 +622,9 @@ async def _handle_resize(browser: "Browser", args: Dict[str, Any]) -> str:
     # ("close" is intercepted in the connection handler — see comment above
     # the lifecycle section.)
     "resize": _handle_resize,
+    # Downloads
+    "downloads": _handle_downloads,
+    "wait_download": _handle_wait_download,
 }
 
 
diff --git a/bridgic/browser/session/_browser.py b/bridgic/browser/session/_browser.py
index 0c2da74..d281b2e 100644
--- a/bridgic/browser/session/_browser.py
+++ b/bridgic/browser/session/_browser.py
@@ -588,10 +588,11 @@ def __init__(
         # than hit a misleading NO_ACTIVE_PAGE when `_page` is mid-teardown.
         self._closing: bool = False
 
-        # Download manager - handles saving files with correct filenames
-        self._download_manager: Optional[DownloadManager] = None
-        if self._downloads_path:
-            self._download_manager = DownloadManager(downloads_path=self._downloads_path)
+        # Download manager - always active so CLI can query/wait for downloads.
+        # Uses the configured path if provided, otherwise defaults to ~/Downloads.
+        self._download_manager: Optional[DownloadManager] = DownloadManager(
+            downloads_path=self._downloads_path or None
+        )
 
         # CDP-borrowed download infrastructure. Populated in `_start()` when
         # connecting via CDP without owning the context. The renamer is the
@@ -723,6 +724,32 @@ def downloaded_files(self) -> List[DownloadedFile]:
             return self._download_manager.downloaded_files
         return []
 
+    async def get_downloaded_files_text(self) -> str:
+        """Return a human-readable summary of all downloads in this session."""
+        files = self.downloaded_files
+        if not files:
+            return "No downloads in this session."
+        lines = []
+        for i, f in enumerate(files, 1):
+            size_kb = f.file_size / 1024
+            size_str = f"{size_kb / 1024:.2f} MB" if size_kb >= 1024 else f"{size_kb:.1f} KB"
+            lines.append(f"[{i}] {f.file_name} — {size_str} — {f.path}")
+        return "\n".join(lines)
+
+    async def wait_for_next_download(self, timeout: float = 30.0) -> str:
+        """Wait up to *timeout* seconds for the next download to complete.
+
+        Returns a one-line summary of the downloaded file, or a timeout message.
+        """
+        if not self._download_manager:
+            return "Download manager not available."
+        file = await self._download_manager.wait_for_next_download(timeout=timeout)
+        if file is None:
+            return f"No download completed within {timeout:.0f}s timeout."
+        size_kb = file.file_size / 1024
+        size_str = f"{size_kb / 1024:.2f} MB" if size_kb >= 1024 else f"{size_kb:.1f} KB"
+        return f"Download complete: {file.file_name} — {size_str} — {file.path}"
+
     @property
     def headless(self) -> bool:
         """Whether the user requested a windowless (headless) browser.
@@ -1041,8 +1068,8 @@ def _get_context_options(self) -> Dict[str, Any]:
         if self._color_scheme is not None:
             options["color_scheme"] = self._color_scheme
 
-        # Auto-enable downloads if downloads_path is configured
-        if self._downloads_path and "accept_downloads" not in self._extra_kwargs:
+        # Always accept downloads so DownloadManager can track them
+        if "accept_downloads" not in self._extra_kwargs:
             options["accept_downloads"] = True
 
         # Extract context-specific kwargs (user values override everything)
diff --git a/bridgic/browser/session/_download.py b/bridgic/browser/session/_download.py
index 6c09a78..c404524 100644
--- a/bridgic/browser/session/_download.py
+++ b/bridgic/browser/session/_download.py
@@ -147,6 +147,11 @@ def __init__(
         # own Future; _handle_download fulfils the oldest pending waiter on
         # completion so callers do not stomp on each other's callbacks.
         self._pending_waiters: List[asyncio.Future[DownloadedFile]] = []
+        # Persistent FIFO of all successfully saved downloads. Drained by
+        # wait_for_next_download() — independent from _pending_waiters so the
+        # CLI's `wait-download` command can pick up completions that already
+        # happened before the agent asked.
+        self._completed_queue: asyncio.Queue[DownloadedFile] = asyncio.Queue()
 
     @property
     def downloads_path(self) -> Path:
@@ -348,6 +353,7 @@ async def _handle_download(self, download: "Download") -> None:
             )
 
             self._downloaded_files.append(downloaded_file)
+            self._completed_queue.put_nowait(downloaded_file)
             logger.info(f"Download saved: {target_path} ({file_size} bytes)")
 
             # Call complete callback if configured
@@ -546,9 +552,29 @@ async def wait_for_download(
             if not waiter.done():
                 waiter.cancel()
 
+    async def wait_for_next_download(self, timeout: float = 30.0) -> Optional[DownloadedFile]:
+        """Wait up to *timeout* seconds for the next download to complete.
+
+        Returns the DownloadedFile when one arrives, or None on timeout.
+        """
+        try:
+            return await asyncio.wait_for(self._completed_queue.get(), timeout=timeout)
+        except asyncio.TimeoutError:
+            return None
+
     def clear_history(self) -> None:
-        """Clear the download history."""
+        """Clear the download history.
+
+        Also drains :attr:`_completed_queue` so a subsequent
+        :meth:`wait_for_next_download` won't immediately yield a stale
+        completion from before the clear.
+        """
         self._downloaded_files.clear()
+        while not self._completed_queue.empty():
+            try:
+                self._completed_queue.get_nowait()
+            except asyncio.QueueEmpty:
+                break
 
     def get_downloads_by_type(self, file_type: str) -> List[DownloadedFile]:
         """Get all downloads of a specific file type.
diff --git a/docs/API.md b/docs/API.md
index 77b9ec2..c7bc25b 100644
--- a/docs/API.md
+++ b/docs/API.md
@@ -18,8 +18,10 @@ Short reference for the main session and download APIs. For tool lists and selec
 | `await browser.get_current_page_title()` | Get current page title string, or `None` if no page is open. |
 | `browser.get_current_page_url()` | Get current page URL string, or `None` if no page is open. (sync) |
 | `browser.get_config()` | Return dict of all current browser configuration options. |
-| `browser.download_manager` | `DownloadManager` instance (after `start()`) when `downloads_path` is set **and** the active pipeline uses it (non-CDP / CDP-owned). In **CDP-borrowed** mode the download manager is intentionally not attached — see [CdpDownloadRenamer](#cdp-borrowed-downloads-cdpdownloadrenamer). |
-| `browser.downloaded_files` | Shortcut for `browser.download_manager.downloaded_files`. Returns `[]` if no download manager (including CDP-borrowed). |
+| `await browser.get_downloaded_files_text()` | Numbered list of all files downloaded in this session, or `"No downloads in this session."` if none. Each line: `[N] filename — size — /path/to/file`. |
+| `await browser.wait_for_next_download(timeout=30.0)` | Block until the next download completes and return a one-line summary, or a timeout message. **Call immediately after the action that triggers the download.** Timeout unit is seconds. Not supported in CDP-borrowed mode (the manager isn't attached there). |
+| `browser.download_manager` | Always-created `DownloadManager` instance. Defaults to `~/Downloads` when `downloads_path` is not configured. In **CDP-borrowed** mode the manager is intentionally not attached to the borrowed context — `CdpDownloadRenamer` handles downloads instead. See [CdpDownloadRenamer](#cdp-borrowed-downloads-cdpdownloadrenamer). |
+| `browser.downloaded_files` | Shortcut for `browser.download_manager.downloaded_files`. Returns `[]` in CDP-borrowed mode because the manager isn't attached there. |
 | `browser.headless` | `bool` — whether the browser runs in headless mode. |
 | `browser.viewport` | `dict` or `None` — current viewport size configuration. |
 | `browser.channel` | `str` or `None` — browser distribution channel. |
@@ -37,18 +39,19 @@ bridgic has two download pipelines, picked by mode. The download path resolution
 
 | Mode | Pipeline | `downloads_path` unset → falls back to |
 |---|---|---|
-| non-CDP (`Browser()`) | `DownloadManager.save_as` from Playwright's `artifactsDir` | DownloadManager is **not** attached; files are lost when Playwright wipes `artifactsDir` on close. Always pass `downloads_path` in non-CDP mode. |
-| CDP-owned (rare — `Browser(cdp=...)` against a remote Chrome that has no contexts yet) | Same as non-CDP | Same caveat as non-CDP. |
+| non-CDP (`Browser()`) | `DownloadManager.save_as` from Playwright's `artifactsDir` | `~/Downloads` (DownloadManager auto-default). |
+| CDP-owned (rare — `Browser(cdp=...)` against a remote Chrome that has no contexts yet) | Same as non-CDP | Same as non-CDP. |
 | CDP-borrowed (`Browser(cdp=...)` against a user's running Chrome) | `CdpDownloadRenamer` (rename GUID → real name post-completion) via a page-level CDP session | `~/Downloads`. In daemon mode the CLI client's CWD (`os.getcwd()`) takes priority over the `~/Downloads` fallback — see [CLAUDE.md → Downloads](../CLAUDE.md#downloads). |
 
 ### DownloadManager (non-CDP / CDP-owned modes)
 
-`Browser` creates and manages a `DownloadManager` automatically when `downloads_path` is provided. Access it via `browser.download_manager` after the browser has started (via `navigate_to()`, `search()`, or `_start()`).
+`Browser` always creates a `DownloadManager`. It saves files to the configured `downloads_path`, or `~/Downloads` by default. Access it via `browser.download_manager` after the browser has started.
 
 | Method / property | Description |
 |------------------|-------------|
-| `browser.download_manager` | The auto-created `DownloadManager` (None when `downloads_path` is unset, or in CDP-borrowed mode regardless of `downloads_path`). |
+| `browser.download_manager` | The `DownloadManager` instance. Always non-`None` after `__init__`. In CDP-borrowed mode it is created but not attached to the context; downloads in that mode go through `CdpDownloadRenamer` instead. |
 | `browser.download_manager.downloaded_files` | List of `DownloadedFile` (`.url`, `.path`, `.file_name`, `.file_size`). |
+| `await browser.download_manager.wait_for_next_download(timeout=30.0)` | Wait up to *timeout* seconds for the next download to complete. Returns `DownloadedFile` or `None` on timeout. |
 
 `browser.wait_for_download(...)` is **not supported in CDP-borrowed mode** — Playwright's per-context `download` event does not fire when the file is routed away from `artifactsDir` by the page-session override.
 
diff --git a/docs/BROWSER_TOOLS_GUIDE.md b/docs/BROWSER_TOOLS_GUIDE.md
index 88cf1ce..6cc3dc4 100644
--- a/docs/BROWSER_TOOLS_GUIDE.md
+++ b/docs/BROWSER_TOOLS_GUIDE.md
@@ -14,7 +14,7 @@ This guide helps you choose the right tools for different browser automation sce
 | Keyboard | 4 | Keyboard typing and key state |
 | Mouse | 6 | Coordinate-based pointer control |
 | Wait | 1 | Time/text/selector waits |
-| Capture | 2 | Screenshot and PDF |
+| Capture | 4 | Screenshot, PDF, and file download tracking |
 | Network | 4 | Request capture and network idle waits |
 | Dialog | 3 | Alert/confirm/prompt handling |
 | Storage | 5 | Cookies and storage state |
@@ -352,7 +352,7 @@ builder = BrowserToolSetBuilder.for_categories(
 )
 tools = builder.build()["tool_specs"]
 
-# Full access (all 67 tools)
+# Full access (all 69 tools)
 builder = BrowserToolSetBuilder.for_categories(browser, ToolCategory.ALL)
 tools = builder.build()["tool_specs"]
 ```
@@ -428,6 +428,25 @@ await browser.select_dropdown_option_by_ref("8d4b03a9", "a")
 await browser.upload_file_by_ref("e10", "/path/to/file.pdf")
 ```
 
+### File Download
+
+Click (or otherwise trigger) the download, then immediately await `wait_for_next_download`. Downloads are always saved to `~/Downloads` unless `downloads_path` is configured.
+
+```python
+# Trigger the download
+await browser.click_element_by_ref("8d4b03a9")
+
+# Block until the file is saved (timeout in seconds)
+result = await browser.wait_for_next_download(timeout=30.0)
+# result: "Download complete: report.pdf — 261.0 KB — /home/user/Downloads/report.pdf"
+#         or "No download completed within 30s timeout."
+
+# Inspect all downloads in the session
+files = browser.downloaded_files  # List[DownloadedFile]
+for f in files:
+    print(f.file_name, f.file_size, f.path)
+```
+
 ### Handling Dialogs
 
 ```python
diff --git a/skills/bridgic-browser/references/cli-guide.md b/skills/bridgic-browser/references/cli-guide.md
index b80ce21..7b93236 100644
--- a/skills/bridgic-browser/references/cli-guide.md
+++ b/skills/bridgic-browser/references/cli-guide.md
@@ -50,7 +50,7 @@ bridgic-browser close
 | Keyboard | `press`, `type`, `key-down`, `key-up` |
 | Mouse | `scroll`, `mouse-click`, `mouse-move`, `mouse-drag`, `mouse-down`, `mouse-up` |
 | Wait | `wait` |
-| Capture | `screenshot`, `pdf` |
+| Capture | `screenshot`, `pdf`, `downloads`, `wait-download` |
 | Network | `network-start`, `network`, `network-stop`, `wait-network` |
 | Dialog | `dialog-setup`, `dialog`, `dialog-remove` |
 | Storage | `cookies`, `cookie-set`, `cookies-clear`, `storage-save`, `storage-load` |
@@ -104,6 +104,11 @@ bridgic-browser dialog-setup --action accept
 bridgic-browser open https://example.com    # any alert triggered will be auto-accepted
 bridgic-browser dialog-remove
 
+# File download workflow — click the trigger, then wait
+bridgic-browser click @37015433          # click a download button/link
+bridgic-browser wait-download 30         # block until download completes (default 30s)
+bridgic-browser downloads                # list all downloads in this session
+
 # Close the browser when everything is done
 bridgic-browser close
 ```
@@ -158,6 +163,7 @@ For how to enable CDP on the target Chrome (Chrome 144+ `chrome://inspect/#remot
   - `bridgic-browser wait --gone "Loading"` — wait until "Loading" disappears (`--gone` only works with a text argument)
 - **`type` requires a focused element**: `type` sends keystrokes at the current cursor position. Run `bridgic-browser click @<ref>` or `bridgic-browser focus @<ref>` on the target input first.
 - **`mouse-move`, `mouse-click`, `mouse-drag` use viewport pixel coordinates** measured from the top-left corner of the browser viewport. Example: `bridgic-browser mouse-click 500 300`.
+- **File downloads require two commands**: `click` (or whatever triggers the download) followed immediately by `wait-download [SECONDS]`. `wait-download` blocks until the browser signals completion and returns the file name, size, and path. After that, `downloads` lists all files saved in the session. Downloads are always saved to `~/Downloads` unless a `downloads_path` is set in config.
 - **`eval-on` CODE must be an arrow or named function** that accepts the element as its argument:
   - `bridgic-browser eval-on @8d4b03a9 "(el) => el.textContent"` ✓
   - `bridgic-browser eval-on @8d4b03a9 "el.textContent"` ✗ (not a function)
diff --git a/skills/bridgic-browser/references/cli-sdk-api-mapping.md b/skills/bridgic-browser/references/cli-sdk-api-mapping.md
index a2a7820..a6afe79 100644
--- a/skills/bridgic-browser/references/cli-sdk-api-mapping.md
+++ b/skills/bridgic-browser/references/cli-sdk-api-mapping.md
@@ -74,6 +74,8 @@ This model is the foundation of all correspondence in this guide.
 | `wait` | `wait_for` |
 | `screenshot` | `take_screenshot` |
 | `pdf` | `save_pdf` |
+| `downloads` | `get_downloaded_files_text` |
+| `wait-download` | `wait_for_next_download` |
 | `network-start` | `start_network_capture` |
 | `network` | `get_network_requests` |
 | `network-stop` | `stop_network_capture` |
@@ -137,6 +139,8 @@ This model is the foundation of all correspondence in this guide.
 - `pdf path.pdf` -> `save_pdf(filename="path.pdf")`
   - SDK-only params: `display_header_footer`, `print_background`, `scale`, `paper_width`, `paper_height`, `margin_top`, `margin_bottom`, `margin_left`, `margin_right`, `landscape`
 - `video-stop path.webm` -> `stop_video(filename="path.webm")`
+- `downloads` -> `get_downloaded_files_text()` — returns a numbered human-readable list of all files downloaded in the session, or `"No downloads in this session."` if none
+- `wait-download [SECONDS]` -> `wait_for_next_download(timeout=30.0)` — **unit is SECONDS** (default 30); blocks until the next download completes and returns a one-line summary (`"Download complete: filename — size — path"`), or a timeout message if no download arrives within the limit. Call immediately after the action that triggers the download.
 - `type TEXT [--submit]` -> `type_text(text, submit=False)` — **requires a focused element**; call `focus_element_by_ref` or `click_element_by_ref` on the target before `type`
 - `eval-on REF CODE` -> `evaluate_javascript_on_ref(ref, code)` — **CODE must be an arrow or named function** that accepts the element:
   - `"(el) => el.textContent"` ✓
@@ -196,6 +200,7 @@ These CLI behaviors have no direct SDK equivalent or work differently:
 | `fill-form` input format | JSON string on command line | Python list of dicts |
 | `take_screenshot` return value | CLI always writes to a file path | SDK: `filename=None` returns base64 data URL; `filename="path.png"` writes file |
 | Video file write timing | `video-stop` stops the recorder and saves the `.webm` file immediately | Same for SDK: `stop_video()` saves the file immediately — no page close needed |
+| Download workflow | `click @ref` then `wait-download [s]` as separate commands; `downloads` to list all | SDK: call `await browser.wait_for_next_download(timeout=30.0)` after the action that triggers the download; `browser.downloaded_files` for the full list |
 
 ## Practical Rule for Mixed Tasks
 
diff --git a/tests/unit/test_browser.py b/tests/unit/test_browser.py
index ef88e2b..ee57677 100644
--- a/tests/unit/test_browser.py
+++ b/tests/unit/test_browser.py
@@ -157,11 +157,11 @@ def test_downloads_path_creates_manager(self):
             assert browser.download_manager is not None
             assert browser.download_manager.downloads_path == Path(tmpdir)
 
-    def test_no_downloads_path_no_manager(self):
-        """Test that no downloads_path means no download manager."""
+    def test_no_downloads_path_uses_default_manager(self):
+        """Download manager is always created; defaults to ~/Downloads when no path given."""
         browser = Browser()
 
-        assert browser.download_manager is None
+        assert browser.download_manager is not None
         assert browser.downloaded_files == []
 
     def test_get_config(self):
diff --git a/tests/unit/test_browser_methods.py b/tests/unit/test_browser_methods.py
index 493b93c..fefc9d0 100644
--- a/tests/unit/test_browser_methods.py
+++ b/tests/unit/test_browser_methods.py
@@ -30,6 +30,7 @@
     "verify_element_visible", "verify_text_visible", "verify_value",
     "verify_element_state", "verify_url", "verify_title",
     "start_tracing", "stop_tracing", "start_video", "stop_video", "add_trace_chunk",
+    "get_downloaded_files_text", "wait_for_next_download",
 ]
 
 
diff --git a/tests/unit/test_cli.py b/tests/unit/test_cli.py
index 8be3c67..281cc81 100644
--- a/tests/unit/test_cli.py
+++ b/tests/unit/test_cli.py
@@ -176,6 +176,8 @@ def invoke_raw(args: list[str]):
     # Capture
     "screenshot": ["screenshot", "out.png"],
     "pdf": ["pdf", "out.pdf"],
+    "downloads": ["downloads"],
+    "wait-download": ["wait-download"],
     # Network
     "network-start": ["network-start"],
     "network": ["network"],
diff --git a/tests/unit/test_tools.py b/tests/unit/test_tools.py
index 4161e06..aecb27b 100644
--- a/tests/unit/test_tools.py
+++ b/tests/unit/test_tools.py
@@ -1762,7 +1762,7 @@ def test_for_categories_adds_tools(self):
         from bridgic.browser.tools import BrowserToolSetBuilder, ToolCategory
 
         browser = MagicMock()
-        for name in ("take_screenshot", "save_pdf"):
+        for name in ("take_screenshot", "save_pdf", "get_downloaded_files_text", "wait_for_next_download"):
             method = MagicMock()
             method.__name__ = name
             method.__doc__ = f"Mock {name} method."
@@ -1770,7 +1770,7 @@ def test_for_categories_adds_tools(self):
 
         builder = BrowserToolSetBuilder.for_categories(browser, ToolCategory.CAPTURE)
         names = {spec.to_tool().name for spec in builder.build()["tool_specs"]}
-        assert names == {"take_screenshot", "save_pdf"}
+        assert names == {"take_screenshot", "save_pdf", "get_downloaded_files_text", "wait_for_next_download"}
 
     def test_for_categories_accepts_string_aliases(self):
         """String aliases should map to ToolCategory values."""