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.
git clone --depth 1 https://github.com/h4vzz/awesome-ai-agent-skillsnpx agentmods add skills/h4vzz/awesome-ai-agent-skills/docker-compose-setupWrote 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.
[](https://agentmods.dev/skills/h4vzz/awesome-ai-agent-skills/docker-compose-setup)<a href="https://agentmods.dev/skills/h4vzz/awesome-ai-agent-skills/docker-compose-setup"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-agent-skills/docker-compose-setup/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.
<a href="https://agentmods.dev/skills/h4vzz/awesome-ai-agent-skills/docker-compose-setup"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-agent-skills/docker-compose-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.02528 |
| Opus 5 | $0.00015 | $0.01264 |
| Sonnet 5 | $0.00006 | $0.00506 |
| Haiku 4.5 | $0.00003 | $0.00253 |
Grade A, and why
docker-compose-setup 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 10d 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.
test: ["CMD", "curl", "-f", "http://localhost/health"] This is a copy
97% identical to docker-compose-setup — 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.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Compose Setup
This skill enables the agent to design and configure multi-container application stacks using Docker Compose. The agent can orchestrate services including web servers, databases, caches, background workers, and reverse proxies with proper networking, volume management, health checks, and environment-specific overrides. The agent understands both development and production configurations and can generate compose files that follow Docker best practices.
Workflow
-
Analyze the Application Stack: The agent reviews the project's architecture to identify all required services and their dependencies. This includes the primary application container, databases (PostgreSQL, MySQL, MongoDB), caches (Redis, Memcached), message queues (RabbitMQ, Kafka), background workers, and reverse proxies (Nginx, Traefik). The agent maps inter-service dependencies to determine startup order and health check requirements.
-
Define Services and Images: For each service, the agent specifies the Docker image or build context, exposed ports, environment variables, and resource constraints. Application services typically use a
builddirective pointing to a local Dockerfile, while infrastructure services use official images with pinned version tags. The agent avoids usinglatesttags in production to ensure reproducible deployments. -
Configure Networking and Service Discovery: The agent creates named Docker networks to isolate traffic between service tiers (e.g., a
frontendnetwork for the proxy and app, abackendnetwork for the app and database). Services communicate using their compose service names as DNS hostnames, eliminating the need for hardcoded IP addresses. -
Set Up Volumes and Persistence: The agent defines named volumes for data that must persist across container restarts, such as database storage and file uploads. For development, bind mounts map the host source code into containers to enable hot reloading. The agent ensures that volume permissions and ownership are configured correctly for the container's runtime user.
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.
- 10d ago First seen · 277 lines · 30 tokens per session scan A bacc9a76cc45
docker-compose-setup is a skill published in the GitHub repository h4vzz/awesome-ai-agent-skills (34 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 2,528 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 97% identical to docker-compose-setup, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
fly
Fly.io transforms Docker containers into microVMs running globally. The Machines API allows you to programmatically spawn, pause, and destroy VMs in milliseconds.
rabbitmq
Skill "rabbitmq" from ashish7802/awesome-api-skills, covering rabbitmq skill, ecosystem graph preview, recommended next skills, quick start and production patterns.
traefik
Skill "traefik" from ashish7802/awesome-api-skills, covering traefik skill, ecosystem graph preview, recommended next skills, quick start and production patterns.
docker
Skill "docker" from ashish7802/awesome-api-skills, covering docker skill, ecosystem graph, quick start, production patterns and multi-stage builds.
helm
Skill "helm" from ashish7802/awesome-api-skills, covering helm skill, ecosystem graph, quick start, production patterns and umbrella charts.
kubernetes
Skill "kubernetes" from ashish7802/awesome-api-skills, covering kubernetes skill, ecosystem graph, quick start, production patterns and operators.