ClawsomeFlow documentation

ClawsomeFlow lets you describe a goal, lay it out as a graph of tasks, and have a team of AI agents carry it out — in parallel, each in its own isolated workspace, with every step visible to you. This guide walks you through using the product from its web console.

You don't write any glue code. You define Flows in the browser, press Run, watch the agents work live, and approve the result. Everything below is something you can do from the console.

ClawsomeFlow 使用文档

ClawsomeFlow 让你只需描述目标、把它编排成一张任务图，然后由一支 AI Agent 团队来执行—— 并行推进、彼此隔离，且每一步都对你可见。本指南将带你从 Web 控制台开始上手这款产品。

你无需编写任何胶水代码。你在浏览器里定义 Flow，点击 运行， 实时观看 Agent 工作，并确认最终结果。下文介绍的一切，都可以在控制台中完成。

Install & open the console

ClawsomeFlow runs on your own machine (Linux or macOS). Install it with one line:

Start the background service (already running by default):

Open the console in your browser — by default that's:

The web console is where you do everything else in this guide. A few commands are handy:

• csflow status — check whether the service is running.
• csflow stop — stop the service.
• csflow doctor — run a health check if something looks off.

安装并打开控制台

ClawsomeFlow 运行在你自己的机器上（Linux 或 macOS）。一行命令即可安装：

启动后台服务（默认已开启）：

在浏览器中打开控制台——默认地址为：

本指南后续的所有操作都在 Web 控制台中完成。几个常用命令：

• csflow status——查看服务是否在运行。
• csflow stop——停止服务。
• csflow doctor——遇到异常时做一次健康检查。

Key concepts

Five words explain almost the entire interface. Learn these and the rest is obvious.

核心概念

五个词几乎就能解释整个界面。理解了它们，其余一目了然。

Your first Flow in 5 minutes

There are two ways to create a Flow. Pick whichever fits how you think.

Option A — Describe it in natural language

On the Flow List page, use AI Decompose: type your goal in plain language and ClawsomeFlow drafts a Flow for you — tasks, dependencies and a leader summary task included. You then open it in the editor to fine-tune.

Option B — Build it by hand

1. On the Flow List page, click New Flow.
2. Give it a name and an overall goal (include what "done" looks like).
3. Pick a Leader and its agent source. The Leader will summarize the run.
4. Add tasks: for each, write what to do, choose an agent source, and set which tasks it depends on.
5. Save the Flow.
6. Back on the Flow List, click Run. Fill in any parameter fields, then start.
7. You're taken to the Run Details page — watch the agents work live.

5 分钟创建你的第一个 Flow

创建 Flow 有两种方式，选你习惯的那种即可。

方式 A——用自然语言描述

在 Flow 列表 页面使用 AI 拆解：用自然语言输入你的目标， ClawsomeFlow 会为你起草一个 Flow——包含任务、依赖关系以及 Leader 的汇总任务。随后你可以 打开编辑器进行微调。

方式 B——手动编排

1. 在 Flow 列表 页面，点击 新建 Flow。
2. 填写 名称 与 总体目标（写清楚「完成」的标准）。
3. 选择一个 Leader 及其 Agent 来源。Leader 负责汇总整次运行。
4. 添加 任务：为每个任务写明要做什么、选择 Agent 来源，并设置它依赖哪些任务。
5. 保存 Flow。
6. 回到 Flow 列表，点击 运行。填写参数字段后启动。
7. 页面会跳转到 执行详情——实时观看 Agent 工作。

Building a Flow (the editor)

The Flow editor has two parts: the basics at the top, and the task graph below.

Flow basics

• Flow name & Overall goal — describe the goal and your acceptance criteria. Agents read this.
• Leader — pick the leader agent, its source, the workspace repo path, and the target branch its summary merges into.
• Parameter fields (optional) — define inputs like "target project" so the same Flow can be reused with different values. You fill these in each time you run.

Task orchestration

For each task you set:

• What to do — the instruction for that task.
• Agent source — which CLI runs it (OpenClaw, Claude Code, Codex, …).
• Dependencies — which tasks must finish first. Tasks with no unmet dependency run in parallel.

A task automatically receives the outputs of the tasks it directly depends on, so you can chain work without copy-pasting between agents.

Reuse: merge an existing Flow

Merge existing Flow imports another Flow's worker tasks into this one (and de-duplicates parameter fields) — a quick way to combine building blocks you've already made.

编排一个 Flow（编辑器）

Flow 编辑器分为两部分：顶部的基础信息，以及下方的任务图。

Flow 基础信息

• Flow 名称 与 总体目标——描述目标和验收标准，Agent 会读取这些内容。
• Leader——选择 Leader Agent、其来源、工作区仓库路径，以及其汇总结果要合并到的目标分支。
• 参数字段（可选）——定义诸如「目标项目」之类的输入，让同一个 Flow 能用不同取值复用。每次运行时填写它们。

任务编排

每个任务需要设置：

• 要做什么——该任务的指令。
• Agent 来源——由哪个 CLI 执行（OpenClaw、Claude Code、Codex……）。
• 依赖关系——必须先完成哪些任务。没有未满足依赖的任务会并行执行。

任务会自动收到它直接依赖的那些任务的产出，因此你无需在 Agent 之间手动复制粘贴即可串联工作。

复用：合并已有 Flow

合并已有 Flow 会把另一个 Flow 的工作任务导入当前 Flow（并对参数字段去重）—— 是把你已经做好的「积木」快速组合起来的便捷方式。

Running & monitoring a Run

When you run a Flow you land on Run Details. This is your live control room.

• Task Execution Board — the graph of tasks, showing which are running, done, or waiting. Switch between a list view and a terminal view.
• Terminal — peek into any agent's live terminal output as it works.
• Live events — a running log of every dispatch, completion and failure. Each Run is fully traceable.
• Stop flow execution — abort the Run if you need to. Changes are rolled back on termination.

You can run the same Flow several times at once — each Run gets its own isolated team and workspaces, so concurrent Runs never interfere with each other.

运行与监控一次 Run

运行 Flow 后会进入 执行详情 页面。这是你的实时指挥室。

• 任务执行看板——任务图，显示哪些在运行、已完成或在等待。可在列表视图与终端视图间切换。
• 终端——实时查看任意 Agent 工作时的终端输出。
• 实时事件——记录每一次派发、完成与失败的运行日志。每次 Run 都完全可追溯。
• 停止流程执行——需要时可中止 Run。中止后改动会被回滚。

同一个 Flow 可以同时运行多次——每次 Run 拥有各自隔离的团队与工作区，因此并发的 Run 之间互不干扰。

Reviewing & merging results

When the work is done, the Leader Work Report on the Run Details page is your single summary of what happened and what was delivered. Read it first.

Human checkpoints (review mid-run)

You don't have to wait until the very end to review. In the Flow editor, toggle Require post-task checkpoint (the ⛳ flag) on any task. When that task finishes, the whole Run pauses — its status becomes Awaiting your checkpoint decisions — and no task that depends on it starts until you act.

On the Run Details page, the checkpoint panel lets you:

• Read the latest output of the checkpoint task.
• Approve it — downstream tasks are then dispatched and the Run continues.
• Rerun it with written feedback if it's not good enough — the same agent redoes the task. While a rerun is in progress, other checkpoints wait their turn.
• Abort the flow from here if you want to stop entirely.

Approving merges

Because agents work on isolated branches, their results need to be merged into your target branch. How that happens depends on the agent source:

• TUI agents (Claude Code, Codex, Gemini, …) default to manual merge. The Run pauses in Awaiting review and lists Pending merges. Read the Leader's merge advice, then click Merge into Target Branch — or Dismiss if you don't want it.
• OpenClaw agents merge themselves as the last step of each task, so there's usually nothing for you to approve.

审阅与合并结果

工作完成后，执行详情页上的 Leader 工作报告 是对「发生了什么、交付了什么」 的唯一汇总。请先阅读它。

人工检查点（运行中途审阅）

你不必等到最后才审阅。在 Flow 编辑器中，可为任意任务开启 启用任务后检查点 （⛳ 标记）。当该任务完成时，整次 Run 会暂停——状态变为 等待你的检查点决定——在你处理之前，依赖它的任务都不会开始。

在执行详情页的检查点面板中，你可以：

• 查看该检查点任务的最新产出。
• 批准——随后下游任务被派发，Run 继续运行。
• 若不够好，则附上文字反馈并重跑——由同一个 Agent 重做该任务。重跑进行期间，其他检查点会排队等待。
• 如需彻底停止，也可从这里中止流程。

确认合并

由于 Agent 都在隔离分支上工作，它们的成果需要合并到你的目标分支。具体方式取决于 Agent 来源：

• TUI 类 Agent（Claude Code、Codex、Gemini……）默认采用 手动 合并。此时 Run 会停在 等待审阅 状态，并列出 待合并 项。阅读 Leader 给出的合并建议后，点击 合并到目标分支——若不需要则点击 忽略。
• OpenClaw 类 Agent 会在每个任务的最后一步自行合并，因此通常无需你来确认。

The improvement loop (complaints)

After a Run completes, ClawsomeFlow gives you one more chance to push back before things are cleaned up. This is the complaint step.

• Happy with the result? Confirm, and the Run wraps up.
• Not happy? Submit a complaint describing what's wrong or what to improve.

On a complaint, the relevant agents reflect, rework, and write their improvements back into their workspaces — so the deliverable gets better without you starting over.

改进闭环（投诉）

一次 Run 完成后，在清理之前，ClawsomeFlow 还会给你一次「提要求」的机会。这就是 投诉 环节。

• 对结果满意？确认即可，本次 Run 收尾结束。
• 不满意？提交一条 投诉，说明哪里不对、需要怎样改进。

收到投诉后，相关 Agent 会反思、返工，并把改进写回各自的工作区——让交付物变得更好， 而你无需从头再来。

Timed Flows

The Timed Flows page lets you schedule Flows to run automatically.

• Set a run time, and choose one-time or recurring (with an interval in days).
• Add one or more Flows to the schedule, and supply each Flow's input fields.
• Choose how multiple Flows execute: parallel (all at once) or serial (one after another).
• Review past runs under Execution Records.

定时 Flow

定时 Flow 页面让你安排 Flow 自动运行。

• 设置 运行时间，并选择 一次性 或 周期性（以天为间隔）。
• 向计划中添加一个或多个 Flow，并填写每个 Flow 的输入字段。
• 选择多个 Flow 的执行方式：并行（同时运行）或 串行（依次运行）。
• 在 执行记录 中查看历史运行。

Your Team (Agents)

The My Team section lets you chat directly with your OpenClaw agents in natural language. Use it to:

• Ask an agent to take on expert skills or set up its own scheduled tasks.
• Give feedback, share complaints, or suggest improvements — conversationally.
• Get to know an agent before you put it to work inside a Flow.

The "my-desktop" button

Every OpenClaw agent has a my-desktop/ folder in its workspace — its long-term working area for user-facing materials and deliverables, which the agent organizes to suit its role. On an agent's chat page, the my-desktop button opens that folder right on your computer, so you can browse everything the agent has produced and accumulated.

我的团队（Agent）

我的团队 区域让你用自然语言直接与你的 OpenClaw Agent 对话。你可以用它来：

• 让 Agent 掌握专家 技能，或为它设置自己的定时任务。
• 以对话方式给出反馈、提出投诉或改进建议。
• 在把某个 Agent 投入 Flow 之前，先熟悉它。

「my-desktop」按钮

每个 OpenClaw Agent 的工作区里都有一个 my-desktop/ 文件夹——它是该 Agent 用于 存放面向用户的材料与交付物的长期工作区，由 Agent 按自身角色来组织。在 Agent 的对话页面上， my-desktop 按钮会直接在你的电脑上打开该文件夹，便于你浏览 Agent 产出与沉淀的内容。

Keeping ClawsomeFlow updated

When a new version is available, the console shows an upgrade badge in the sidebar — click it and follow the prompt to upgrade in place. Prefer the terminal? Run:

Your existing Flows, runs and settings are preserved across upgrades.

保持 ClawsomeFlow 更新

有新版本时，控制台侧边栏会出现 升级提示——点击它并按提示原地升级。 更喜欢用终端？运行：

升级过程中，你已有的 Flow、运行记录和设置都会被保留。

Frequently asked questions

The points people most often misread — clearing these up saves a lot of confusion.

常见问题解答

大家最常误解的几个地方——把它们弄清楚能省去很多困惑。