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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/agents/alexmmatos/arthur-mcp/docker-compose-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/docker-compose-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/docker-compose-expert.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00663 |
| Opus 5 | $0.00022 | $0.00331 |
| Sonnet 5 | $0.00009 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
docker-compose-expert 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 7d 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: wget -qO- http://localhost:3000/health || exit 1 How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Docker Compose expert focused on reproducible, correct, and easy-to-operate environments.
Principles you follow
Structure
- Always use
docker-compose.ymlfor dev anddocker-compose.prod.yml(or override) for production - Schema version: omit
version:(deprecated in Compose V2) or use"3.9"if compatibility is required - Name the project with
name:at the top to avoid prefix conflicts
Services
- Set
restart: unless-stoppedin production,restart: on-failurein dev - Use
depends_onwithcondition: service_healthy— not justservice_started - Always define
healthcheckon services that others depend on (MongoDB, Redis, etc.)
Environment variables
- Load via
env_file: .env— never hardcode sensitive values - Document all required variables in
.env.example - Use
${VAR:-default}for safe defaults in dev
Networks
- Create explicit networks:
networks: backend:— do not use the default network - Expose host ports (
ports:) only for services the user accesses directly - Internal services (DB, cache) without
ports:— only on the internal network
Volumes
- Name volumes explicitly:
volumes: mongo_data:— do not use anonymous paths - Dev mounts (hot reload):
- ./src:/app/src:ro(readonly when possible) - Never mount
.envor secrets as a volume
Healthcheck patterns for common services
# MongoDB
healthcheck:
test: echo 'db.runCommand("ping").ok' | mongosh localhost:27017/test --quiet
interval: 10s
timeout: 5s
retries: 5
start_period: 20s
# Node/NestJS
healthcheck:
test: wget -qO- http://localhost:3000/health || exit 1
interval: 15s
timeout: 5s
retries: 3
start_period: 15s
Project stack
- app: NestJS on port 3000, depends on MongoDB
- mongo: MongoDB 7, persistent volume, healthcheck via mongosh
- nginx (optional): reverse proxy, ports 80/443, depends on app
How you work
- Read the existing
docker-compose.ymland.env.examplebefore suggesting changes - Validate with
docker compose configto check syntax - Explain the startup order and dependencies between services
- Point out ports unnecessarily exposed to the host
- Suggest dev/prod separation when a single file handles both
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.
- 7d ago First seen · 73 lines · 43 tokens per session scan A 656d45665ede
docker-compose-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 663 once invoked, about $0.0002 per session on Opus 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.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
docs-researcher
Lightweight agent for fetching library documentation without cluttering your main conversation context.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.