docker-moltbot-open CLAUDE.md

docker-moltbot-open CLAUDE.md is an instructions file for coding agents from inematds/docker-moltbot-open. It costs 3,533 tokens per session, scanned F, original, MIT.

A set of project instructions for running a Docker-based local personal assistant called Moltbot. It documents Docker Compose commands, configuration, security settings, supported chat channels, and supported language-model providers.

In plain words
What is it for?
Use it when developing or operating this Docker deployment, including rebuilding it, viewing logs, or managing its container lifecycle.
Why use it?
It gives the coding agent the repository context and commands needed to build, start, inspect, restart, or stop the containers.

Instructions file

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 instructions/inematds/docker-moltbot-open/claude-md
Clone the repo
git clone --depth 1 https://github.com/inematds/docker-moltbot-open

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for docker-moltbot-open CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inematds/docker-moltbot-open/claude-md.svg)](https://agentmods.dev/instructions/inematds/docker-moltbot-open/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/inematds/docker-moltbot-open/claude-md"><img src="https://agentmods.dev/badge/instructions/inematds/docker-moltbot-open/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,533 This file is loaded in full into every session.
When invoked 3,533 The same file — it is already loaded in full.
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 5.1 $0.03533 $0.03533
Opus 5 $0.01767 $0.01767
Sonnet 5 $0.00707 $0.00707
Haiku 4.5 $0.00353 $0.00353

Measured 5d ago against content hash 192f4bcc0c89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade F, and why

docker-moltbot-open CLAUDE.md 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 5d 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.

5. **Config written**: Final config saved as `~/.clawdbot/clawdbot.json` with `chmod 600`

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.

- ⚠️ AGENTS.md to block dangerous commands (rm -rf, curl | bash, etc.)

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- ⚠️ AGENTS.md to block dangerous commands (rm -rf, curl | bash, etc.)

Makes network callslowCapability

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

- Installs system dependencies: `ffmpeg`, `python3`, `git`, `curl`
CLAUDE.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Docker Moltbot is a Docker-based deployment of Moltbot (formerly Clawdbot), an AI personal assistant that runs locally with security hardening built-in. This repository provides a production-ready Docker setup with:

  • Security hardening by default (non-root user, loopback binding, pairing-based authentication)
  • Multi-channel support (Telegram, WhatsApp, Discord, Slack, Webchat)
  • Multi-LLM support (Claude, GPT, Gemini, OpenRouter)
  • Persistent storage with Docker volumes
  • Automated configuration via environment variables

Build and Run Commands

Basic Commands

# Build and start container
docker compose up -d

# Rebuild from scratch (pulls latest moltbot)
docker compose build --no-cache
docker compose up -d

# View logs
docker compose logs -f              # Follow logs
docker compose logs --tail 100      # Last 100 lines

# Container lifecycle
docker compose restart              # Restart container
docker compose stop                 # Stop without removing
docker compose down                 # Stop and remove container
docker compose down -v              # Remove container + volumes (deletes all data)

# Access container shell
docker compose exec moltbot bash

Moltbot CLI Commands

# Configuration and status
docker compose exec moltbot moltbot status          # Show gateway status
docker compose exec -it moltbot moltbot configure   # Interactive setup wizard
docker compose exec moltbot moltbot doctor --fix    # Auto-detect and fix config issues
docker compose exec moltbot moltbot doctor          # Check issues without fixing

# Security
docker compose exec moltbot moltbot security audit  # Run security audit

# Channel management
docker compose exec -it moltbot moltbot channels login whatsapp   # Login to WhatsApp
docker compose exec moltbot moltbot pairing approve telegram <code>  # Approve Telegram pairing

# Note: The CLI uses 'moltbot' commands, but the actual runtime currently uses 'clawdbot'
# This is due to the ongoing rebrand. Both work interchangeably.

Read the full file on GitHub · 335 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. 5d ago First seen · 335 lines · 3,533 tokens per session scan F 192f4bcc0c89

Subscribe to this mod's changes

docker-moltbot-open CLAUDE.md is an instructions file published in the GitHub repository inematds/docker-moltbot-open (2 stars, last pushed 7mo ago), licensed MIT. It adds 3,533 tokens to every session, about $0.0177 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.