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.
npx agentmods add instructions/intelligentcode-ai/claude-code-vm/claude-mdgit clone --depth 1 https://github.com/intelligentcode-ai/claude-code-vmWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02379 | $0.02379 |
| Opus 5 | $0.01189 | $0.01189 |
| Sonnet 5 | $0.00476 | $0.00476 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade D, and why
claude-code-vm CLAUDE.md scanned grade D with 2 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.
3. Ensure target VM is Debian 12+ with sudo access Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- ✅ **Allowed**: Docker, Kubernetes, Git (branch/merge, no basic push), Make, npm, find, file operations, SSH to private networks (10.0.0.*, 192.168.*), project-safe rm -rf How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Claude Code VM Deployment System
This file guides Claude Code when working with this Ansible-based deployment system for setting up development environments on remote Debian VMs.
🎯 Project Purpose
This project automates the deployment of Claude Code and associated development tools to remote Debian VMs. It creates fully-configured development environments with Git, Docker, Kubernetes, and AI-enhanced capabilities through MCP servers.
Key Point: This runs on your LOCAL machine to deploy TO remote VMs. It does NOT run on the target VMs themselves.
🏗️ Architecture Overview
Project Structure
claude-code-vm/
├── config/ # Default configuration templates
│ ├── env.example # Template for credentials and API keys
│ ├── mcp-servers.template.json # MCP server definitions
│ ├── git-repos.env.example # Git repository management template
│ ├── CLAUDE.common.md # Base CLAUDE.md template (shared by all)
│ ├── CLAUDE.minimal.md # Minimal deployment template
│ ├── CLAUDE.enhanced.md # Enhanced deployment with MCP/Docker
│ ├── CLAUDE.containerized.md # Containerized with Docker Compose
│ └── CLAUDE.full.md # Full deployment with Kubernetes
├── ansible/
│ ├── playbooks/ # Main orchestration
│ │ ├── site.yml # Primary deployment playbook
│ │ └── validate.yml # Validation playbook
│ └── roles/ # Modular components
│ ├── common/ # System preparation
│ ├── git/ # Git + credential management
│ ├── docker/ # Docker CE installation
│ ├── nodejs/ # Node.js 22 LTS
│ ├── claude-code/ # Claude Code CLI
│ ├── kubernetes/ # k8s tools (kubectl, k3s/kind)
│ ├── mcp/ # MCP server configuration
│ └── claude-config/ # CLAUDE.md deployment and inheritance
└── Makefile # User interface for all operations
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.
- 2d ago First seen · 260 lines · 2,379 tokens per session scan D 942cd539fb81
claude-code-vm CLAUDE.md is an instructions file published in the GitHub repository intelligentcode-ai/claude-code-vm (34 stars, last pushed 1y ago), licensed MIT. It adds 2,379 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
outlook-mcp CLAUDE.md
Claude Code instructions for ryaker/outlook-mcp, covering claude.md, development commands, architecture overview, core structure and modules.
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
SeekMoney-ai CLAUDE.md
Instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
claude-sessions CLAUDE.md
Instructions for gapmiss/claude-sessions, covering claude sessions — obsidian plugin, development, file structure, code exploration (cymbal) and conventions.
robotics-mcp AGENTS.md
Instructions for sandraschi/robotics-mcp, covering robotics-mcp — agent guide, entry points, standards and key files.