install-founderclaw

Install FounderClaw — a complete multi-agent system for OpenClaw. Adds 6 agents, 29 skills, creates communication channels, configures models. Interactive setup. Requires user input for model selection and channel setup. Triggered by: "install founderclaw", "setup founderclaw", "get founderclaw".

3,891 stars

Best use case

install-founderclaw is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Install FounderClaw — a complete multi-agent system for OpenClaw. Adds 6 agents, 29 skills, creates communication channels, configures models. Interactive setup. Requires user input for model selection and channel setup. Triggered by: "install founderclaw", "setup founderclaw", "get founderclaw".

Teams using install-founderclaw should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/install-founderclaw/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/ashish797/founderclaw/install-founderclaw/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/install-founderclaw/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How install-founderclaw Compares

Feature / Agentinstall-founderclawStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Install FounderClaw — a complete multi-agent system for OpenClaw. Adds 6 agents, 29 skills, creates communication channels, configures models. Interactive setup. Requires user input for model selection and channel setup. Triggered by: "install founderclaw", "setup founderclaw", "get founderclaw".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Install FounderClaw

This is an INTERACTIVE system install. Guide the user through setup. One step at a time. Don't rush.

## Rules
- Explain each step before doing it
- Ask before modifying config
- Batch your messages — don't send 20 rapid-fire updates
- If something fails, say so clearly

## Step 1: Install files

Tell the user:

> Setting up FounderClaw. This takes about 30 seconds.

Run:

```bash
# Clone if not exists, update if exists
if [ -d ~/.agents/skills/founderclaw ]; then
    cd ~/.agents/skills/founderclaw && git stash 2>/dev/null && git fetch origin && git reset --hard origin/main
else
    git clone --single-branch --depth 1 https://github.com/ashish797/FounderClaw.git ~/.agents/skills/founderclaw
fi

# Symlink skills
cd ~/.agents/skills/founderclaw
INSTALLED=0
for skill_dir in */; do
    [ ! -f "$skill_dir/SKILL.md" ] && continue
    skill_name=$(basename "$skill_dir")
    target=~/.agents/skills/"$skill_name"
    [ -e "$target" ] && continue
    ln -sf "$(pwd)/$skill_dir" "$target"
    INSTALLED=$((INSTALLED + 1))
done

# Create workspace
if [ ! -d ~/.openclaw/founderclaw ]; then
    cp -r workspace-template ~/.openclaw/founderclaw
fi

echo "FILES_DONE:$INSTALLED"
```

Report: "✅ X skills installed. ✅ Workspace ready."

## Step 2: Ask for model selection

Tell the user:

> FounderClaw uses 3 model tiers:
> - **Fast** — quick tasks (code review, safety checks)
> - **Best** — deep thinking (strategy, architecture)
> - **Vision** — image analysis
>
> Which models do you want? Pick one for each, or say "use defaults" to use your current primary model for all.

List available models from `agents.defaults.models` in config.

Wait for user's choices. Record them.

## Step 3: Ask for interaction setup

Tell the user:

> How do you want to interact with FounderClaw?
>
> **Option A: One chat** — Talk to the CEO. CEO handles everything internally. Simplest.
>
> **Option B: Multiple topics** — Separate topic for each department (CEO, Strategy, Shipper, Tester, Safety, Observer). More visibility.
>
> **Option C: Both** — CEO is main entry point, plus specialist topics available.

Wait for user's choice.

## Step 4: Create channels (platform-specific)

Based on what platform the user is on (check current session — it shows the channel):

### Telegram

If user chose "one chat" or "both":
- Create topic "🎯 FounderClaw CEO" in the group they're talking from
- Bind `founderclaw-main` to that topic

If user chose "multiple topics" or "both":
- Create topics for each department
- Bind each agent to its topic

```bash
# Topic IDs will be returned by the message tool
# Record them for config binding
```

### WhatsApp

WhatsApp can't create groups or topics via API.
- Bind `founderclaw-main` to the current WhatsApp account
- CEO handles everything in one chat
- Departments work internally, invisible to user

### Discord

If user has a Discord server:
- Create channels for each department
- Bind agents to channels

### Slack

Similar to Discord — create channels, bind agents.

## Step 5: Apply config

Build the config patch with:
- 6 agents (with correct models from Step 2)
- Bindings (from Step 4)

Apply via `gateway config.patch`.

## Step 6: Verify

```bash
# Check agents exist
python3 -c "
import json, re, os
with open(os.path.expanduser('~/.openclaw/openclaw.json'), 'r') as f:
    c = re.sub(r',\s*([}\]])', r'\1', re.sub(r'//.*$', '', f.read(), flags=2))
config = json.loads(c)
ids = [a['id'] for a in config.get('agents',{}).get('list',[])]
fc = ['founderclaw-main','fc-strategy','fc-shipper','fc-tester','fc-safety','fc-observer']
found = sum(1 for a in fc if a in ids)
print(f'Agents: {found}/6')
"

# Check workspace
[ -d ~/.openclaw/founderclaw/ceo ] && echo "Workspace: OK" || echo "Workspace: MISSING"
```

## Step 7: Report

Tell the user:

> **FounderClaw is live!**
>
> ✅ 29 skills installed
> ✅ 6 agents configured
> ✅ Workspace created
> ✅ Channels set up
>
> **Go to [topic/group/channel name] to start.**
>
> Quick start:
> - "I have an idea" — start office-hours
> - "review my code" — code review
> - "test this site" — QA testing
>
> Gateway will restart now.

## Uninstall

```bash
# Remove skills
for link in ~/.agents/skills/*; do
    [ -L "$link" ] || continue
    target=$(readlink "$link")
    echo "$target" | grep -q "founderclaw" && rm "$link"
done
rm -rf ~/.agents/skills/founderclaw
```

Then remove agents from config via `gateway config.patch`.

Related Skills

skill-safe-install-l0-strict

3891
from openclaw/skills

Strict secure-install workflow for ClawHub/OpenClaw skills. Use when asked to install a skill safely, inspect skill permissions, review third-party skill risk, or run a pre-install security audit. Enforce full review + sandbox + explicit consent gates, with no author-based trust bypass.

Security

remote-install

3891
from openclaw/skills

Remote software installation via automated installer detection and GUI automation. Use when: user needs to install software packages (.exe/.msi) on Windows machines, automate Office/Adobe/Chrome installations, or handle unattended software deployment. NOT for: Linux/macOS installations, package manager installs (apt/yum/brew), or containerized deployments.

linux-installer

3891
from openclaw/skills

Installs, launches, and uninstalls Linux desktop apps by resolving the safest supported source first, then running a local helper CLI. Use when the user asks to install software like GIMP, Notepad++, or other desktop apps on Linux and wants the install command plus the command to launch or remove it.

gate-mcp-installer

3891
from openclaw/skills

One-click installer and configurator for Gate MCP (mcporter) in OpenClaw. Use when the user wants to (1) Install mcporter CLI tool, (2) Configure Gate MCP server connection, (3) Verify Gate MCP setup, or (4) Troubleshoot Gate MCP connectivity issues.

OpenClaw Install Guide (WSL2 Windows)

3891
from openclaw/skills

Complete step-by-step installation guide for OpenClaw on Windows 10/11 with WSL2, includes common pitfalls and solutions from real installation experience.

founderclaw-upgrade

3891
from openclaw/skills

Upgrade founderclaw to the latest version. Detects install location, pulls updates, and shows what's new. Use when: "upgrade founderclaw", "update founderclaw", "get latest version", "update skills".

founderclaw-status

3891
from openclaw/skills

Check FounderClaw installation status. Verifies skills, workspace, and multi-agent config are all properly set up. Use when: "founderclaw status", "is founderclaw working", "check founderclaw", "founderclaw health".

founderclaw

3891
from openclaw/skills

FounderClaw — Multi-agent engineering team for OpenClaw. 29 skills, 6 agents (CEO + 5 departments), structured workspace, auto mode, vision sub-agent routing. Build startups with AI agents.

openstoryline-install

3891
from openclaw/skills

Install, configure, and start FireRed-OpenStoryline from source on a local machine. Use when a user asks to set up OpenStoryline, troubleshoot installation, download required resources, fill config.toml API keys, or launch the MCP and web services, as well as Chinese requests like “安装 OpenStoryline”, “配置 OpenStoryline”, “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “修复 OpenStoryline 安装问题”, or “排查 OpenStoryline 启动失败”.

install-then-update-trap-detector

3891
from openclaw/skills

Helps detect the install-then-update attack pattern — where a skill passes initial security review cleanly, then silently introduces malicious behavior through an automatic update that bypasses re-audit. v1.1 adds cryptographic chain-of-custody verification for update sequences.

clawhub-quarantine-installer

3891
from openclaw/skills

Instala e audita skills do ClawHub em um ambiente de quarentena isolado para análise de segurança, permitindo revisar riscos antes de promover para produção. Use esta skill para testar habilidades de terceiros que o ClawHub sinaliza como suspeitas, investigar suas dependências e comportamento, e gerar relatórios de auditoria básicos.

openclaw-workspace-governance-installer

3891
from openclaw/skills

Install OpenClaw WORKSPACE_GOVERNANCE in minutes. Get guided setup, upgrade checks, migration, and audit for long-running workspaces.