mcp-sandbox-computer-vm-for-ai: Instructions file for Claude Code

CLAUDE.md

mcp-sandbox-computer-vm-for-ai CLAUDE.md is an instructions file for Claude Code from flujo-app/mcp-sandbox-computer-vm-for-ai. It costs 370 tokens per session, scanned A, a copy of Kilntainers CLAUDE.md, MIT.

Project instructions for Kilntainers, secure agent sandboxes that run coding work in isolated computers such as Docker containers or Fly Machines.

In plain words
What is it for?
Understanding the sandbox tool interface, managing named temporary or permanent computers, following implementation phases, and working on the MCP server.
Why use it?
They define the project’s specifications, implementation process, security model, and development commands so changes follow the intended design.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is flujo-app/mcp-sandbox-computer-vm-for-ai's own configuration. It tells Claude Code how to work on mcp-sandbox-computer-vm-for-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-sandbox-computer-vm-for-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to flujo-app/mcp-sandbox-computer-vm-for-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/flujo-app/mcp-sandbox-computer-vm-for-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/flujo-app/mcp-sandbox-computer-vm-for-ai

Made for: Claude Code.

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 mcp-sandbox-computer-vm-for-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/flujo-app/mcp-sandbox-computer-vm-for-ai/claude-md/github.svg)](https://agentmods.dev/instructions/flujo-app/mcp-sandbox-computer-vm-for-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/flujo-app/mcp-sandbox-computer-vm-for-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/flujo-app/mcp-sandbox-computer-vm-for-ai/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-sandbox-computer-vm-for-ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/flujo-app/mcp-sandbox-computer-vm-for-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/flujo-app/mcp-sandbox-computer-vm-for-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 370 This file is loaded in full into every session.
When invoked 370 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod 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 $0.00370 $0.00370
Opus 5 $0.00185 $0.00185
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 6d ago against content hash a754d59cc072, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-sandbox-computer-vm-for-ai CLAUDE.md scanned grade A with 0 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 6d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

86% identical to Kilntainers CLAUDE.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 22 lines

What it actually says

Kilntainers: Secure Agent Sandboxes

This fork extends Kilntainers into named sandbox computers. terminal_execute supports stable computer IDs and temporary/permanent lifecycles; optional provider-neutral management tools and a stable MCP App dashboard manage Docker containers and Fly Machines. Set ENABLE_LIFECYCLE_TOOLS=true to expose the computer_* tools and dashboard; they are disabled by default.

Specs

This repository has detailed specs, and follows spec-driven design. Key files include:

  • [specs/functional_spec.md] External behavior — the MCP tool interface, server configuration, connection lifecycle, backend behavioral contract, and security model. Not an architecture or implementation document.
  • [specs/implementation_plan.md] our ordered implementation plan, including progress tracking
  • [specs/phase_instructions.md] A set of instructions to follow when asked to implement a phase of the implmentation plan
  • [specs/architecture/architecture_summary.md] A summary of architecture docs covering detailed technical designs. Additional architecture docs live in this path.
  • specs/decisions.md — design decisions with rationale (source of truth). However these are generally captured in functional_spec and architecture, and does not need to be reviewed.
  • specs/project_overview.md — original motivation and vision, but not maintained. Functional spec is generally more complete and up to date. Do not review unless looking for original motivation.
  • specs/spec_queue.md — tracking of items requiring specification

Commands & Tools

You have access ot a MCP server to running tools like lint, format, types, test.

Always use the MCP commands to perform these actions, not direct bash calls. Bash calls require approval and will stop our work.

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. 6d ago Changed · +29 tokens per session a754d59cc072
  2. 10d ago First seen · 22 lines · 341 tokens per session scan A 95657f2ee719

Subscribe to this mod's changes

mcp-sandbox-computer-vm-for-ai CLAUDE.md is an instructions file published in the GitHub repository flujo-app/mcp-sandbox-computer-vm-for-ai (4 stars, last pushed 3d ago), licensed MIT. It adds 370 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to Kilntainers CLAUDE.md, differing in 2 lines, and is treated as a copy.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens