docker

docker is a skill for Claude Code, Codex from wrsmith108/claude-code-docker-skill. It costs 56 tokens per session (2,029 once invoked), scanned A, original, MIT.

A Docker-based development setup that runs package installs, code, and project commands inside isolated containers instead of directly on your computer.

In plain words
What is it for?
Use it when installing npm packages, running builds or servers, executing code, or managing project dependencies with Docker.
Why use it?
It keeps project tools and dependencies separate from your host system and helps different developers use the same environment. It also checks that the development container is running before commands are executed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is COPY scripts/ ./scripts/.

Good fit Use it when installing npm packages, running builds or servers, executing code, or managing project dependencies with Docker.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wrsmith108/claude-code-docker-skill
agentmods
npx agentmods add skills/wrsmith108/claude-code-docker-skill/docker

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/wrsmith108/claude-code-docker-skill/docker/github.svg)](https://agentmods.dev/skills/wrsmith108/claude-code-docker-skill/docker)
Your own site
<a href="https://agentmods.dev/skills/wrsmith108/claude-code-docker-skill/docker"><img src="https://agentmods.dev/badge/skills/wrsmith108/claude-code-docker-skill/docker/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 docker

Your own site · 80×15
<a href="https://agentmods.dev/skills/wrsmith108/claude-code-docker-skill/docker"><img src="https://agentmods.dev/badge/skills/wrsmith108/claude-code-docker-skill/docker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.02029
Opus 5.5 $0.00022 $0.00812
Sonnet 5.5 $0.00011 $0.00406
Haiku 4.5 $0.00006 $0.00203

Measured 1mo ago against content hash 3a35aa9eade1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docker scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

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

curl -s http://localhost:3000 > /dev/null && echo "Server running" || echo "Server not running"
skills/docker/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docker Development Skill

Execute all package installations and code execution inside Docker containers. This keeps the host machine clean and ensures consistent environments across projects.

Core Principle

NEVER run npm, node, npx, or project scripts directly on the host machine.

Instead, use docker exec or ensure the container is running the dev server.

Pre-Flight Check (MANDATORY)

Before running ANY npm/node command, Claude Code MUST verify the container is running.

Run this check first:

docker ps --filter "name=<project-name>" --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}"

Expected output:

NAMES                  STATUS          PORTS
<project-name>-dev-1   Up X minutes    0.0.0.0:3000->3000/tcp

If container is NOT running:

# Navigate to project root first
cd /path/to/your/project

# Start container
docker-compose --profile dev up dev -d

# Verify it started
docker ps --filter "name=<project-name>"

If container shows "Exited":

# Check why it exited
docker logs <project-name>-dev-1 --tail 20

# Remove and restart
docker-compose --profile dev down
docker-compose --profile dev up dev -d

Quick Reference

Check Container Status

# List running containers for current project
docker ps --filter "name=<project-name>"

# Check container logs
docker logs <project-name>-dev-1 --tail 50

# Check if dev server is responding
curl -s http://localhost:3000 > /dev/null && echo "Server running" || echo "Server not running"

Start/Stop Containers

# Start development container (from project root)
docker-compose --profile dev up dev -d

# Stop container
docker-compose --profile dev down

# Restart container
docker-compose --profile dev restart dev

# Rebuild after Dockerfile changes
docker-compose --profile dev up dev -d --build

Execute Commands Inside Container

# Install a package
docker exec -it <project-name>-dev-1 npm install <package-name>

# Install dev dependency
docker exec -it <project-name>-dev-1 npm install -D <package-name>

# Run tests
docker exec -it <project-name>-dev-1 npm test

# Run type checking
docker exec -it <project-name>-dev-1 npm run typecheck

# Run linting
docker exec -it <project-name>-dev-1 npm run lint

# Run build
docker exec -it <project-name>-dev-1 npm run build

# Open shell inside container
docker exec -it <project-name>-dev-1 /bin/sh

# Run any arbitrary command
docker exec -it <project-name>-dev-1 <command>

Read the full file on GitHub · 315 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. 1mo ago First seen · 315 lines · 56 tokens per session scan A 3a35aa9eade1

Subscribe to this mod's changes

docker is a skill published in the GitHub repository wrsmith108/claude-code-docker-skill (4 stars, last pushed 10mo ago), licensed MIT. It adds 56 tokens to every session and 2,029 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories