Use this skill when the user wants to provision, spawn, or birth a new OpenClaw agent on the Agentbot platform.
Scanned 6/4/2026
Install via CLI
Skills Directoryopenskills install Eskyee/agentbot-opensourceAre you the author of Provisioning V1?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/eskyee-provisioning-v1)More formats (shields.io, HTML) on the badges page.
# provision-agent Skill
## Trigger
Use this skill when the user wants to provision, spawn, or birth a new OpenClaw agent on the Agentbot platform.
## Usage
`provision-agent --token <TELEGRAM_TOKEN> --provider <AI_PROVIDER> --key <API_KEY> --plan <PLAN>`
## Workflow
1. **Pre-flight Check:**
- Verify `<TELEGRAM_TOKEN>` is valid with the Telegram API.
- Check `<API_KEY>` for minimum balance (if applicable).
2. **Instance Creation:**
- Call the `infra/scripts/provision.sh` script to allocate a port and spin up the Docker container.
3. **Verification Hook:**
- Ping the new instance at `https://<USER_ID>.agents.agentbot.sh/api/health`.
- Wait for a 200 OK.
4. **Handoff:**
- Return the `userId`, `subdomain`, and `url` to the requester.
## Parameters
- `token`: Telegram Bot Token (required)
- `provider`: AI Provider (e.g., openrouter, anthropic, google)
- `key`: API Key for the chosen provider
- `plan`: Subscription plan (free, pro, custom)
---
*Status: v1.0.0-draft | Operator: Atlas*
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
