agentmods.dev

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.

In plain words
What is it for?
Developing or testing DockaShell, including unit and integration tests, container management, secure command execution, and its local or remote MCP server.
Why use it?
They give an agent the context needed to work safely with container creation, command validation, project configuration, and server behavior.

Instructions file

30 1y ago A scan 656 tokens original Apache-2.0
View the source file anzax/dockashell
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/anzax/dockashell/claude-md
Clone the repo
git clone --depth 1 https://github.com/anzax/dockashell
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. 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 $0.00656 $0.00656
Opus 5 $0.00328 $0.00328
Sonnet 5 $0.00131 $0.00131
Haiku 4.5 $0.00066 $0.00066

Measured 3d ago against content hash 50184c80edea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

  1. 3d 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 $0.0033 per session on Opus 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.

agentcoding-agentdockermcpmodel-context-protocolvibe-coding
Related

Other instructions, from other repositories

vibesdk AGENTS.md

AGENTS.md instructions for cloudflare/vibesdk, covering agents.md, tooling, verification, frontend ui and frontend data fetching.

cloudflare/vibesdk · 1,600 tokens

ironcurtain CLAUDE.md

Instructions for provos/ironcurtain, covering claude.md, general workflow, git & worktrees, git workflow and platform considerations.

provos/ironcurtain · 5,773 tokens

ironcurtain security-boundary.instructions.md

Instructions for provos/ironcurtain, covering security boundary review rules, mandatory checks and structural invariant order.

provos/ironcurtain · 747 tokens

senpi AGENTS.md

Instructions for code-yeongyu/senpi, covering senpi repository guide, mandatory execution protocols — non-negotiable, protocol 1 — explicitly requested modifications, protocol 2 — user-requested pr reviews and structure.

code-yeongyu/senpi · 4,113 tokens

ironcurtain types.instructions.md

Instructions for provos/ironcurtain, covering types review rules and mandatory checks.

provos/ironcurtain · 434 tokens

sortie copilot-instructions.md

Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).

sortie-ai/sortie · 1,030 tokens