What is dockashell CLAUDE.md?

Project instructions for DockaShell, an MCP server that gives AI agents isolated Docker containers for running code. They describe its testing commands and layers for tools, projects, containers, security, and the command line.

Developing or testing DockaShell, including unit and integration tests, container management, secure command execution, and its local or remote MCP server.

They give an agent the context needed to work safely with container creation, command validation, project configuration, and server behavior.

How anzax/dockashell configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to anzax/dockashell. 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/anzax/dockashell/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/anzax/dockashell

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/anzax/dockashell/claude-md/github.svg)](https://agentmods.dev/instructions/anzax/dockashell/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/anzax/dockashell/claude-md"><img src="https://agentmods.dev/badge/instructions/anzax/dockashell/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/anzax/dockashell/claude-md"><img src="https://agentmods.dev/badge/instructions/anzax/dockashell/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 656 This file is loaded in full into every session.

When invoked 656 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00656	$0.00656
Opus 5.5	$0.00262	$0.00262
Sonnet 5.5	$0.00131	$0.00131
Haiku 4.5	$0.00066	$0.00066

Measured 2mo ago against content hash 50184c80edea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dockashell 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 2mo 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 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.

Development Commands

Testing

npm test - Run all unit tests
npm run test:integration - Run integration tests
node --test test/specific-file.test.js - Run single test file

Architecture Overview

DockaShell is an MCP (Model Context Protocol) server that provides AI agents with isolated Docker containers for secure code execution. The architecture consists of several key layers:

Core Components

MCP Server Layer (src/mcp/):

mcp-server.js - Main MCP server implementation with tool registration
tools/ - MCP tool implementations (project, execution, logging tools)
remote/ - Remote MCP server with web authentication for multi-user scenarios

Core Management Layer (src/core/):

project-manager.js - Handles project configuration, validation, and devcontainer parsing
container-manager.js - Docker container lifecycle management and execution
security.js - Security policies and command validation

CLI Layer (src/cli/):

cli.js - Main CLI entry point with command registration
commands/ - Individual CLI commands (build, create, start, stop, logs, etc.)
utils/ - CLI utilities for Docker operations, validation, and output formatting

TUI Layer (src/tui/):

tui-launcher.js - Terminal UI entry point
app.js - Main TUI application component
components/ - React Ink UI components for project selection, log viewing, etc.
stores/ - State management using nanostores for project data, traces, filters

Key Design Patterns

Project Isolation: Each project runs in its own Docker container with persistent state, mounted directories, and port forwarding. Projects are configured via ~/.dockashell/projects/{name}/config.json.

Trace Logging: All agent actions are logged to JSONL files in ~/.dockashell/projects/{name}/traces/ for full auditability and TUI display.

Read the full file on GitHub · 78 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.

2mo ago First seen · 78 lines · 656 tokens per session scan A 50184c80edea

Subscribe to this mod's changes

dockashell CLAUDE.md is an instructions file published in the GitHub repository anzax/dockashell (30 stars, last pushed 1y ago), licensed Apache-2.0. It adds 656 tokens to every session, about $0.0026 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agent coding-agent docker mcp model-context-protocol vibe-coding

dockashell CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dockashell CLAUDE.mdanzax/dockashell	Instructions file	30	1y ago	Apache-2.0	A	656	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

dockashell: Instructions file for Claude Code