claw.v1

A command for deploying and monitoring an OpenClaw gateway on Amazon Lightsail, a cloud hosting service, with Stakpak Autopilot for health checks and alerts.

In plain words
What is it for?
Launching an OpenClaw gateway, connecting Telegram, WhatsApp, Discord, or Slack, applying production security settings, and configuring Telegram or Discord alerts.
Why use it?
It guides the setup of the gateway, messaging connection, security hardening, and ongoing monitoring, including checks for configuration mistakes.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/stakpak/agent/claw.v1
Clone the repo
git clone --depth 1 https://github.com/stakpak/agent
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,909 The whole file, excluding the scripts and references it only reads on demand.
Security scan F 4 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.11909
Opus 5 $0.00007 $0.05955
Sonnet 5 $0.00003 $0.02382
Haiku 4.5 $0.00001 $0.01191

Measured 2d ago against content hash 2a2c0f94731a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

claw.v1 scanned grade F with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

* **Service management**: `sudo systemctl {start|stop|status} openclaw-gateway`

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -sSL https://stakpak.dev/install.sh | sh

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

'TOKEN=$(curl -s -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 21600"); curl -s -H "X-aws-ec2-metadata-token: $TOKEN" http://169.254.169.254/latest/meta-data/instance-id')

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> - Validate API: `curl -s "https://api.telegram.org/bot<TOKEN>/getMe" | jq .ok` must return `true`
libs/api/src/commands/claw.v1.md · 1,041 lines

How it starts

The opening of the file, as written. The whole thing — 1,041 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy & Monitor OpenClaw Gateway with AWS Lightsail Blueprint + Stakpak Autopilot

Goals

  • Deploy a fully functional OpenClaw AI gateway using the AWS Lightsail OpenClaw blueprint (one-click)
  • Connect a messaging channel (Telegram, WhatsApp, Discord, or Slack) with security hardening
  • Harden the deployment for production beyond Lightsail defaults
  • Configure Stakpak Autopilot for continuous health monitoring with Telegram or Discord alerts

Core Principles

  • Collect ALL tokens and API keys before starting — every phase has blocking dependencies
  • The Lightsail blueprint handles Docker, Node.js, systemd, HTTPS, and gateway token generation — do NOT manually install these
  • Never share a Telegram bot token between OpenClaw and Stakpak — causes 409 Conflict polling errors (only applies if both use Telegram)
  • The blueprint uses Amazon Bedrock (not auth-profiles.json) — only write auth-profiles.json if you want a non-Bedrock provider
  • Use openclaw CLI directly via SSH (not docker exec) — the Lightsail blueprint runs OpenClaw as a native systemd service, not Docker
  • Always verify with openclaw channels status --probe and openclaw models status after configuration changes
  • Write scripts locally and SCP to remote hosts — never create scripts via SSH heredoc (shell escaping breaks)
  • The blueprint locks SSH to browser-only (lightsail-connect) by default — you MUST open port 22 to your IP before any CLI-based SSH access (Phase 1.4)
  • Channel plugins (telegram, discord, slack, whatsapp, etc.) are disabled by default — you MUST run openclaw plugins enable <channel> and restart the gateway before openclaw channels add will recognize the channel. Without this, channels add --channel telegram returns Unknown channel: telegram.
  • The Bedrock IAM role name must match LightsailRoleFor-<EC2-instance-id> (get via instance metadata), and the trust policy must allow Lightsail's managed account (002204026182)

Prerequisites

Mandatory User Prompt: Deployment Target

Read the full file on GitHub · 1,041 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 1,041 lines · 14 tokens per session scan F 2a2c0f94731a

Subscribe to this mod's changes

claw.v1 is a command published in the GitHub repository stakpak/agent (1,766 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 11,909 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.