workflowadvancedOpenCLAW

Implement a Coordinated Multi-Agent Team with OpenCLAW

This workflow configures a team of specialized AI agents that collaborate on projects using shared files and a chat interface like Telegram. Each agent has a specific role (e.g., strategist, developer), allowing a single user to manage a comprehensive, autonomous workforce for business or software development.

AI SETUP PROMPT

Paste into Claude Code or Codex CLI — it will scan your project and set everything up

# Set Up Workflow: Implement a Coordinated Multi-Agent Team with OpenCLAW

## What This Is
This workflow configures a team of specialized AI agents that collaborate on projects using shared files and a chat interface like Telegram. Each agent has a specific role (e.g., strategist, developer), allowing a single user to manage a comprehensive, autonomous workforce for business or software development.

Source: https://www.youtube.com/watch?v=52kOmSQGt_E

## Before You Start

Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)

Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?

## Source Access Note

The source URL (https://www.youtube.com/watch?v=52kOmSQGt_E) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.

## What to Implement

This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.

- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files

## Additional Context

- Scan the user's project for an OpenCLAW configuration. Create a `team/` directory with the following structure: `GOALS.md`, `DECISIONS.md`, `PROJECT_STATUS.md`, and an `agents/` subdirectory for private agent files.
- Generate an `AGENTS.md` configuration file to map Telegram handles (e.g., `@milo`, `@dev`) to specific agent session names. Then, create a `SOUL.md` file for a lead agent (e.g., 'Milo') defining its personality, role as 'Strategy Lead', and specifying a powerful model like Claude 3 Opus.
- Install the required OpenCLAW skills for this workflow by running the ClawHub commands for 'telegram' and 'shared-fs'. Configure the Telegram skill by prompting the user for their bot token and chat ID from their environment variables or asking them to provide it.

## Reference Implementation

```
team/
├── GOALS.md
├── DECISIONS.md
├── PROJECT_STATUS.md
└── agents/  # Private folders per agent
```

## Guidelines

- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it

3,330 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Scan the user's project for an OpenCLAW configuration. Create a `team/` directory with the following structure: `GOALS.md`, `DECISIONS.md`, `PROJECT_STATUS.md`, and an `agents/` subdirectory for private agent files.
02Generate an `AGENTS.md` configuration file to map Telegram handles (e.g., `@milo`, `@dev`) to specific agent session names. Then, create a `SOUL.md` file for a lead agent (e.g., 'Milo') defining its personality, role as 'Strategy Lead', and specifying a powerful model like Claude 3 Opus.
03Install the required OpenCLAW skills for this workflow by running the ClawHub commands for 'telegram' and 'shared-fs'. Configure the Telegram skill by prompting the user for their bot token and chat ID from their environment variables or asking them to provide it.

CODE INTELLIGENCE

bash

team/
├── GOALS.md
├── DECISIONS.md
├── PROJECT_STATUS.md
└── agents/  # Private folders per agent

FIELD OPERATIONS

Automated SaaS Product Launch Team

Deploy an agent team to execute a product launch. A 'Strategist' agent defines the GTM plan in `GOALS.md`, a 'Marketer' agent generates landing page copy and social media posts, and a 'Developer' agent scaffolds the initial web application, all coordinated via a shared project status file.

24/7 Codebase Maintenance & Security Crew

Create a team of agents to autonomously maintain a git repository. A 'Reviewer' agent monitors for new pull requests and provides feedback, a 'Tester' agent runs checks, and a 'Security' agent scans for vulnerabilities, reporting all findings into a dedicated Discord or Telegram channel.

STRATEGIC APPLICATIONS

→A solo founder can deploy an autonomous team to handle marketing content creation, customer support ticket triage, business metric analysis, and development task planning, effectively outsourcing entire departments to a managed AI system.
→An enterprise R&D group can use a multi-agent workflow to rapidly prototype new software ideas. A 'Product Manager' agent defines requirements, a 'Developer' agent writes the code, and a 'QA' agent tests it, drastically shortening the innovation and validation cycle.