Skip to main content

Flow-Claude (Flow for Claude Code)

Flow-Claude is for Claude Code users working on long development tasks.

  • Break down requirements into parallel tasks,
  • execute them simultaneously without stopping,
  • auto-commit every change to Git,
  • and merge results automatically.

Related Paper

Niu, B., Song, Y., Lian, K., Shen, Y., Yao, Y., Zhang, K., & Liu, T. Flow: Modularized Agentic Workflow Automation. ICLR 2025

Paper PDF

Design Principle

We design Flow-Claude as a lightweight tool that lives within the Claude CLI. As the Claude code model evolves, the benefits of the framework will also continue to grow.

The framework itself should not become a blocker for future updates of the Claude model. Therefore our primary focus is communication efficiency and parallelism with minimum constraints.

Every new design should smoothly support the Claude CLI.

Contributing

Submit a GitHub issue or contact yu.yao@sydney.edu.au

Installation

Prerequisites

Claude Code must be installed first:

npm install -g @anthropic-ai/claude-code

See Claude Code Setup for more details.


Install Flow-Claude From PyPI

pip install flow-claude

Verify Installation:

flow --help

On Windows, if flow is not in your PATH, use:

python -m flow_claude.commands.flow_cli --help

Quick Start and Tips

1. Initialize Your Project

Navigate to your git repository and initialize Flow-Claude:

Linux / macOS

cd /path/to/your/project
flow

Windows

On Windows, if flow is not in your PATH, use:

cd /path/to/your/project
python -m flow_claude.commands.flow_cli

What happens during initialization:

  • Creates flow branch from your main branch
  • Creates .claude/ directory with skills, commands, agents
  • Creates/updates CLAUDE.md with Flow-Claude instructions
  • Commits all changes to flow branch

2. Launch Claude Code

claude

If you want to avoid frequent permission approval, use:

claude --dangerously-skip-permissions

3. Prompt Claude to use Flow-Claude

Because the current Claude model does not reliably invoke Skills automatically, you need to append a reminder at the end of your prompt.

For example:

Build a REST API for blog posts with CRUD operations. Remember to use your SKILLs.

Launch

4. Resume

When you return to a project after a break or session interruption, prompt Claude to understand the current state before continuing.

Step 1: Use the resume command to restore your previous conversation:

/resume

Select the past conversation from the list.

Step 2: Prompt Claude to check the current state and continue. For example:

Check the current plan and task branch status, then continue the unfinished task. Remember to use Skills.

ResumeWork


5. Commit Manual Changes

If you make local changes on the flow branch and want workers to use them, commit your changes first:

git add . && git commit -m "Your commit message"

Workers pull from the flow branch, so uncommitted changes won't be visible to them.

6. Delete Unwanted Branches

After a plan is finished and all tasks passed, you may want to clean up the created branches. Use a prompt like:

Delete the plan/<plan-name> branch and all its related task branches.

For example: Delete the plan/blog-api-crud branch and all its related task branches.

Delete


6. Commands

Command Description
\auto Toggle autonomous mode (ON = no approval needed)
\parallel N Set max parallel workers (1-10, default: 3)

MCP Servers and Skills

The main agent can automatically determine which MCP tools and agent skills the worker agents require.

MCP Servers Install

Flow-Claude uses MCP in the same way as Claude Code, except that MCP servers must be installed inside your project directory.

For detailed MCP setup instructions, see:

Example: Adding the Playwright MCP server

claude mcp add playwright -- npx --scope project @playwright/mcp@latest # Run this command inside your project directory

Or manually add to .mcp.json in your project root folder:

{
  "mcpServers": {
    "playwright": {
      "type": "stdio",
      "command": "npx",
      "args": ["@playwright/mcp@latest"]
    }
  }
}

Skill Install

Flow-Claude uses Skill in the same way as Claude Code, except that Skill must be added inside your project directory.

For detailed Skill adding instructions, see:

Example: Creating Skills

  • Created as SKILL.md files in specific directories (.claude/skills/)
.claude/skills/processing-pdfs/
└── SKILL.md

License

MIT License - see LICENSE for details.

Ready to supercharge your development?

pip install flow-claude && cd your-project && flow

Metadata

Release files for flow-claude 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for flow-claude 1.0.1
File Size Uploaded
flow_claude-1.0.1.tar.gz 45.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for flow-claude 1.0.1
File Interpreter ABI Platform
flow_claude-1.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 102.2 kB

Release files / flow_claude-1.0.1.tar.gz

Download URL flow_claude-1.0.1.tar.gz
Size 45.1 kB
Tags Source
SHA-256 checksum
How to use checksums
ab2f32d84300a656905f6ad886b6b0d32922adaf0ac1a813f32fc4a0ab9f387c
BLAKE2b-256 checksum
How to use checksums
ab025a96291a7f26f3c77cd04772eddfa1c650d861491c6ffdbd9c780eae6979
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Dec 19, 2025.

Transparency log

Release files / flow_claude-1.0.1-py3-none-any.whl

Download URL flow_claude-1.0.1-py3-none-any.whl
Size 57.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
90495c40aabe82580d902580e19e3a7bcd25778d48f1ffe5d66e5951b015962e
BLAKE2b-256 checksum
How to use checksums
fbda758e1b0415dea141c5da1c78a6b28cc8366f339583dd74467e67e61d8464
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Dec 19, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page