npx skills add adarshmishra07/claw-beacon@latest

User Request → Create Task → Spawn Agent → Agent Works → Review → Complete

[#TASK_ID] Brief description

Example:
[#129] Add workflow enforcement to SKILL.md

curl -X POST <BACKEND_URL>/api/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: <API_KEY>" \
  -d '{"agent_id": 1, "message": "✅ Task #X completed: Brief summary"}'

1. Check recent git commits - do they all have [#TASK_ID]?
2. Check for PRs without linked tasks
3. Check for completed work not reflected on board
4. If orphan found → CREATE TASK RETROACTIVELY

npx skills list | grep claw-beacon

cd /path/to/claw-beacon
git fetch origin main
git status | grep "behind"

undefined

**Services started:**
- Backend API on port 3001
- Frontend on port 5173
- PostgreSQL database on port 5432 (or use external)

**To update:**
```bash
git pull
docker compose down
docker compose up -d --build

---

undefined

**Services:**
- Backend: http://localhost:3001
- Frontend: http://localhost:3000

**To update:**
```bash
git pull
npm install
npm run dev

---

undefined

**After deployment, collect:**
- Backend URL (e.g., https://claw-beacon-backend-xxx.up.railway.app)
- Frontend URL (e.g., https://claw-beacon-frontend-xxx.up.railway.app)
- API Key (if they set one)

---

I need your Claw Beacon backend URL to connect.
Example: https://claw-beacon-backend-xxxx.up.railway.app

What's your backend URL?

Did you set an API_KEY when deploying? 
If yes, share it. If no or unsure, we'll try without.

undefined

4. **Test the connection:**
```bash
curl -s <BACKEND_URL>/api/agents

undefined

Verify it's running: `curl http://localhost:6333/health`

**Step 2: Install mem0**

```bash
pip install mem0ai

from mem0 import Memory

config = {
    "llm": {
        "provider": "anthropic",
        "config": {
            "model": "claude-sonnet-4-20250514",
            "api_key": "your-anthropic-key"
        }
    },
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "host": "localhost",
            "port": 6333
        }
    }
}

memory = Memory.from_config(config)

config = {
    "llm": {
        "provider": "openai",
        "config": {
            "model": "gpt-4o",
            "api_key": "your-openai-key"
        }
    },
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "host": "localhost",
            "port": 6333
        }
    }
}

config = {
    "llm": {
        "provider": "google",
        "config": {
            "model": "gemini-2.0-flash",
            "api_key": "your-google-key"
        }
    },
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "host": "localhost",
            "port": 6333
        }
    }
}

config = {
    "llm": {
        "provider": "ollama",
        "config": {
            "model": "llama3.2",
            "ollama_base_url": "http://localhost:11434"
        }
    },
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "host": "localhost",
            "port": 6333
        }
    }
}

from mem0 import Memory

memory = Memory.from_config(config)

---

undefined

**In AGENTS.md, add:**
```markdown

---

services:
  # ... existing services ...
  
  qdrant:
    image: qdrant/qdrant
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - qdrant_storage:/qdrant/storage
    restart: unless-stopped

volumes:
  qdrant_storage:

Great choice! Here's your Team Avatar:

| Role | Character | Why |
|------|-----------|-----|
| Coordinator | Aang | The Avatar, brings balance |
| Developer | Toph | Earthbender, solid foundation |
| Architect | Iroh | Wise, sees the big picture |
| Research | Sokka | Strategist, plans everything |
| PM | Katara | Waterbender, keeps things flowing |
| Designer | Suki | Kyoshi warrior, visual precision |
| QA | Azula | Perfectionist, finds every flaw |
| Deploy | Zuko | Redeemed, handles the heat |

Sound good?

undefined

**Verify changes applied:**
```bash
curl -s <BACKEND_URL>/api/agents

As [Main Character], you're the COORDINATOR:

✅ What you DO:
- Delegate tasks to your specialists
- Review and verify their work
- Make decisions and communicate with humans
- Move tasks to "completed" after quality checks

❌ What you DON'T do:
- Execute tasks yourself (that's what your team is for!)
- Skip the board (every task gets tracked)
- Mark things complete without reviewing

Think of yourself as the team lead, not the coder.

⚠️ Browser access is CRITICAL for your agents to be useful!

Without it, they literally cannot:
- 🔍 Research or look anything up
- 📸 Take screenshots to verify work
- 🌐 Interact with any web app
- ✅ Complete most real-world tasks

🚀 PLUS - Browser + GitHub Login unlocks FULL AUTOMATION:
- 🔑 Auto-create accounts on Railway, Vercel, Supermemory via GitHub OAuth
- 📋 Auto-retrieve API keys by navigating to dashboards
- ⚡ Zero-click setup - I handle EVERYTHING through the browser!

I can automatically set up ANY service that supports "Sign in with GitHub":

1. I navigate to the service (Railway, Supermemory, Vercel, etc.)
2. I click "Sign in with GitHub"
3. OAuth auto-authorizes (you're already logged in!)
4. I navigate to the API keys / settings page
5. I create and copy the credentials
6. I store them and configure everything

= TRUE hands-free automation!

undefined

Then restart OpenClaw and the managed browser should work.

---

Browser Priority:
1. Check if Chrome extension attached → use profile="chrome"
2. Check if managed browser available → use profile="openclaw"  
3. Suggest user install Chromium if neither works

browser action=status

browser action=snapshot profile="chrome"

browser action=snapshot profile="openclaw"

🚫 I can't complete this task - browser access is required.

Quick fixes (try in order):
1. Click the OpenClaw extension icon in your browser toolbar
   → Make sure a tab is attached (badge shows "ON")
   → Tell me to retry with profile="chrome"

2. Say "use managed browser" 
   → I'll use the built-in headless browser with profile="openclaw"

3. If managed browser fails, install Chromium:
   - Ubuntu/Debian: sudo apt install chromium-browser
   - macOS: brew install --cask chromium
   Then restart and retry.

With GitHub access, I become your full development team:
- 🚀 Deploy Claw Beacon to Railway AUTOMATICALLY
- 📦 Fork repos, create projects, manage code
- 💻 Commit and push changes
- 🔀 Handle issues and pull requests
- 🔑 Generate and configure API keys

You literally just give me GitHub access and I handle the rest.
No clicking buttons. No copying URLs. I do it all.

Let's create a GitHub token:

1. Go to: github.com/settings/tokens
2. Click "Generate new token (classic)"
3. Name it: "OpenClaw Agent"
4. Select scopes: repo, workflow
5. Click "Generate token"
6. Share the token with me (starts with ghp_...)

🔐 I'll store it securely and NEVER share it.

1. User is logged into GitHub in browser (Chrome extension attached)
2. Bot navigates to Railway/Supermemory/Vercel dashboard
3. Bot clicks "Sign in with GitHub"  
4. OAuth authorizes automatically (user already authenticated)
5. Bot navigates to API keys / tokens page
6. Bot copies credentials directly from the dashboard
7. Done - fully automated! 🎉

openclaw hooks enable session-memory

openclaw hooks list

Go to console.supermemory.ai → API Keys → Create New Key
(Free tier: 1M tokens, 10K searches)

openclaw plugins install @supermemory/openclaw-supermemory

openclaw config set plugins.entries.openclaw-supermemory.enabled true
openclaw config set plugins.entries.openclaw-supermemory.config.apiKey "sm_your_key_here"

{
  "plugins": {
    "slots": {
      "memory": "openclaw-supermemory"
    },
    "entries": {
      "openclaw-supermemory": {
        "enabled": true,
        "config": {
          "apiKey": "sm_...",
          "autoRecall": true,
          "autoCapture": true,
          "maxRecallResults": 10
        }
      }
    }
  }
}

openclaw gateway restart

{
  "plugins": {
    "slots": {
      "memory": "memory-lancedb"
    },
    "entries": {
      "memory-lancedb": {
        "enabled": true
      }
    }
  }
}

curl -fsSL https://bun.sh/install | bash

undefined

</details>

---

**The bottom line:**

| Feature | Without | With |
|---------|---------|------|
| mem0 + Qdrant | Agents forget everything between sessions | Agents have true long-term memory |
| Supermemory | Manual memory management | Auto-recall and auto-capture |
| QMD | I can only search the web | I can search YOUR personal knowledge base |

mem0 + Qdrant is **required** (Step 2). Supermemory and QMD are optional enhancements.

---

curl -X POST <BACKEND_URL>/api/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: <API_KEY>" \
  -d '{
    "agent_id": 1,
    "message": "Hey @Vegeta, I need you to review this PR: #42"
  }'

undefined

Returns messages where the specified agent was @mentioned.

**Real-time mention notifications (SSE):**
```bash

Events emitted:
- `message-created` — New message posted (includes mentioned_agent_ids)
- `agent-mentioned` — An agent was @mentioned (includes agent_id and message)
- `task-created` / `task-updated` / `task-deleted` — Task lifecycle
- `agent-created` / `agent-updated` / `agent-deleted` — Agent lifecycle

undefined

for mention in mentions:
    if not mention.get("acknowledged"):
        # Process the mention
        handle_mention(mention)
        
        # Acknowledge it (post a response)
        respond_to_mention(mention)

undefined

@Goku: Task #42 complete. @Vegeta please review the PR.

@Piccolo: I'm designing the new auth system. What's the recommended architecture pattern?

@Bulma: Infrastructure is ready. @Trunks you can proceed with deployment.

@Goku: I'm blocked on #45. Need @Gohan to complete the research first.

curl -X POST <BACKEND_URL>/api/tasks \
  -H "Content-Type: application/json" \
  -H "x-api-key: <API_KEY>" \
  -d '{
    "title": "🙋 @{{HUMAN_NAME}}: [What you need]",
    "description": "I need your help with...\n\n**Why I am stuck:**\n[Explanation]\n\n**What I need you to do:**\n1. [Step 1]\n2. [Step 2]\n\n**Once done:**\nMove this task to Done and tell me to continue.",
    "status": "todo",
    "agent_id": null
  }'

I've hit a blocker that needs your help! 🙋

I created a task for you on the dashboard:
→ {{FRONTEND_URL}}

Check your To-Do column - there's a task tagged with your name.
Complete it and let me know when you're done!

undefined

You are [ROLE] in a high-agency team. ALWAYS follow these rules BEFORE acting:

1. IDENTIFY subtasks and DELEGATE to relevant agents
   (e.g., "Delegate UI design to {{DEVOPS}}", "Delegate research to {{RESEARCH}}")

2. QUERY peers for input if uncertain
   (e.g., "Query {{ARCHITECTURE}}: Is this design sound?")

3. VERIFY outputs: After delegation, review responses and iterate if needed

4. COORDINATE via the supervisor ({{COORDINATOR}}/OpenClaw): Route all messages through Mission Control

Do NOT proceed alone—violate this and the task fails.

node scripts/update_dashboard.js --agent "{{AGENT}}" --status "working" --message "Starting: [Task]"

node scripts/update_dashboard.js --agent "{{AGENT}}" --status "idle" --message "Complete: [Task]"

undefined

**Rule of thumb:** If it's worth doing, it's worth posting about. The feed keeps the human informed and the team connected!

undefined

undefined

undefined

---

curl -s <BACKEND_URL>/api/agents \
  -H "x-api-key: <API_KEY>"

curl -X POST <BACKEND_URL>/api/tasks \
  -H "Content-Type: application/json" \
  -H "x-api-key: <API_KEY>" \
  -d '{"title": "👋 Team Introductions", "description": "Introduce the team and explain how the system works.", "status": "completed", "agent_id": 1}'

curl -X POST <BACKEND_URL>/api/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: <API_KEY>" \
  -d '{
    "agent_id": 1,
    "message": "# 👋 Meet Your Team!\n\n## The Squad (8 agents)\n- **[Coordinator]** (me!) - Team lead, delegates, reviews\n- **[Developer]** - Backend APIs, databases, code reviews\n- **[Architect]** - System design, technical decisions\n- **[Researcher]** - Analysis, documentation, research\n- **[PM]** - PRDs, requirements, user stories\n- **[Designer]** - UX research, wireframes, visual specs\n- **[QA]** - Adversarial reviews, testing, quality gates\n- **[Deployment]** - Releases, hotfixes, CI/CD\n\n## How We Work\n1. All tasks go through this board\n2. I delegate to the right specialist\n3. They do the work and report back\n4. I review and mark complete\n\nReady to work! 🦞"
  }'

undefined

✅ Should return `{"status":"ok"}`

I just completed the Team Introductions task! 

Please check your dashboard: <FRONTEND_URL>

You should see:
- ✅ Your themed agent names in the sidebar
- ✅ A "👋 Team Introductions" task marked complete
- ✅ A welcome message in the feed explaining your team

Can you confirm everything looks right?

🦞 Claw Beacon Setup Complete!

Dashboard: {{FRONTEND_URL}}
Coordinator: {{COORDINATOR}}
Team: {{AGENT_LIST}}

✅ Task management configured
✅ Agent behavior updated
✅ mem0 + Qdrant running - agents have long-term memory!
✅ Session memory hook enabled - conversations auto-save!
{{#if browser}}✅ Browser access ready{{/if}}
{{#if github}}✅ GitHub integration ready{{/if}}
{{#if supermemory}}✅ Supermemory connected - cloud memory active!{{/if}}
{{#if qmd}}✅ QMD search ready - I can search your docs!{{/if}}

From now on, I operate as {{COORDINATOR}}:
- All tasks go through the board
- Specialists do the work
- I coordinate, review, and verify

Let's build something awesome! What's our first task?

undefined

**Look for:**
- Tasks stuck in "in_progress" with no recent activity
- Completed tasks that should be archived
- Tasks assigned to wrong agents (e.g., backend task assigned to DevOps)
- Tasks in "review" that have been waiting too long

**Fix Wrongly Placed Tasks:**
```bash

undefined

undefined

If you have unacknowledged mentions, respond to them!

cd /path/to/claw-beacon
git fetch origin main
BEHIND=$(git rev-list HEAD..origin/main --count)
if [ "$BEHIND" -gt 0 ]; then
  echo "⚠️ Claw Beacon is $BEHIND commits behind. Consider updating."
  # Optionally auto-update:
  # git pull && docker compose up -d --build
fi

docker compose restart backend

**3. Check skill version:**
```bash

**4. Check mem0 + Qdrant health:**
```bash
curl -s http://localhost:6333/health

**5. Auto-fix missing components:**
If something is broken, fix it or create a task:
- Qdrant down? → Restart: `docker start qdrant`
- Migrations failed? → Check logs, restart backend
- Skill outdated? → Update: `npx skills add adarshmishra07/claw-beacon@latest`

undefined

---

undefined

**If deployed:**
- Read existing configuration from TOOLS.md
- Verify connection works
- Skip deployment steps

**If NOT deployed:**
- Guide through deployment (Step 1)

curl -X POST <BACKEND_URL>/api/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: <API_KEY>" \
  -d '{
    "agent_id": 1,
    "message": "🔄 Skill updated to latest version!\n\n**Status:**\n- ✅ Backend connected\n- ✅ 8 agents configured\n- ✅ mem0 + Qdrant running\n- ⚠️ [List any missing components]\n\n**Action needed:** [If any]"
  }'