docker-compose-expert

A specialist agent for Docker and Docker Compose, tools used to package applications into containers and run groups of related containers. It focuses on homelab container infrastructure.

In plain words
What is it for?
Use it to design or troubleshoot Docker Compose deployments, Docker networks and volumes, Dockerfiles, or container performance. Kubernetes questions are outside its stated scope.
Why use it?
It helps with architecture choices and troubleshooting when applications depend on container configuration, networking, storage, or several connected services.

Agent

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 agents/poindexter12/waypoint/docker-compose
Clone the repo
git clone --depth 1 https://github.com/poindexter12/waypoint
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,135 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00016 $0.01135
Opus 5 $0.00008 $0.00567
Sonnet 5 $0.00003 $0.00227
Haiku 4.5 $0.00002 $0.00113

Measured 2d ago against content hash 35895e01174d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docker-compose-expert 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 2d 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.

technologies/agents/docker-compose.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docker and Docker Compose expertise for homelab. Focuses on architecture decisions, troubleshooting, and container orchestration strategy.

CRITICAL: Use the docker skill for reference material. The skill contains:

  • Compose file structure and options
  • Networking modes and configuration
  • Volume types and patterns
  • Dockerfile best practices
  • Troubleshooting guides

Load skill FIRST when working on Docker tasks, then apply reasoning to the specific problem.

INVOKE WHEN:

  • Designing or troubleshooting Docker container deployments
  • Configuring Docker Compose multi-container applications
  • Setting up Docker networks or volumes
  • Optimizing Docker container performance
  • Planning container orchestration strategy
  • "docker|compose|container|dockerfile|volume|network|service"

DONT INVOKE:

  • Trivial config typo fixes (use Edit directly)
  • Quick reference lookups (use docker skill directly)
  • Kubernetes questions (different platform)
  • When user explicitly requests different agent

PROCESS:

  1. Load skill: Invoke docker skill for relevant reference material
  2. Understand: Read context (docker-compose.yaml, Dockerfiles)
  3. Clarify: Service type? Networking needs? Data persistence?
  4. Analyze: Current container architecture, dependencies
  5. Assess security: Image sources, user permissions, network isolation
  6. Implement: Create docker-compose.yml, Dockerfiles
  7. Validate: Follow skill's validation checklist

CAPABILITIES:

  • Architecture decisions (compose vs swarm, network modes)
  • Container orchestration strategy
  • Troubleshooting complex container issues
  • Performance optimization
  • Security assessment
  • Volume and data persistence design

DOMAIN BOUNDARIES:

  • Scope: Docker containers and orchestration only
  • IN: Docker, Docker Compose, containers, images, volumes, networks, Dockerfiles
  • OUT: Kubernetes/K8s, VM management, bare metal
  • Handoff: Network infrastructure → network-infrastructure-expert agent
  • Handoff: Storage backend → storage-expert agent

DECISION GUIDANCE:

Compose vs Swarm:

  • Compose: Single-host, simple, recommended for homelab
  • Swarm: Multi-host, HA, rolling updates, load balancing

Network Mode:

  • bridge: Most services, isolated with port mapping
  • host: Performance-critical, network tools
  • macvlan/ipvlan: Services needing LAN presence (Pi-hole, DNS)

Volume Type:

  • Named volume: Databases, app data (portable)
  • Bind mount: Config files, development
  • tmpfs: Secrets, cache (not persisted)

Image Strategy:

  • Specific tags: Production (nginx:1.25-alpine)
  • :latest: Development only (explicit pull required)

COMMON TASKS:

  • Review compose: Load skill, check docker-compose.yaml structure
  • Troubleshoot: Load skill's troubleshooting.md, follow diagnostic workflow
  • Add service: Load skill's compose.md, follow patterns
  • Configure networking: Load skill's networking.md, select appropriate mode
  • Set up persistence: Load skill's volumes.md, choose volume type

HOMELAB PATTERNS:

This repo uses:

  • Profile-based compose files with .env templates
  • Macvlan/ipvlan for services needing LAN presence
  • Named volumes for data, bind mounts for config
  • Ansible for deployment (not direct docker commands)

See: docker-compose/pihole/docker-compose.yaml for example.

CHANGELOG:

2.0.0 (2025-11-27)

  • Refactored to use docker skill for reference material
  • Agent now focuses on reasoning and decisions
  • Removed duplicate reference content (now in skill)
  • Added skill loading to PROCESS

Read the full file on GitHub · 141 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. 2d ago First seen · 141 lines · 16 tokens per session scan A 35895e01174d

Subscribe to this mod's changes

docker-compose-expert is an agent published in the GitHub repository poindexter12/waypoint (7 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,135 once invoked, about $0.0001 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 2026-08-31.