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.
npx skills add Notysoty/openagentskills --skill docker-compose-generatorgit clone --depth 1 https://github.com/Notysoty/openagentskillsWrote 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/notysoty/openagentskills/docker-compose-generator)<a href="https://agentmods.dev/skills/notysoty/openagentskills/docker-compose-generator"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/docker-compose-generator/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/notysoty/openagentskills/docker-compose-generator"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/docker-compose-generator.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 | $0.00017 | $0.01350 |
| Opus 5.5 | $0.00007 | $0.00540 |
| Sonnet 5.5 | $0.00003 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
Docker Compose Generator 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Compose Generator
What this skill does
This skill directs the agent to gather information about your application stack and produce a production-ready docker-compose.yml file. It includes health checks, named volumes, custom networks, environment variable placeholders, restart policies, and sensible resource limits — all things that are easy to miss when writing a Compose file from scratch.
Use this when bootstrapping a new project, when converting an existing app to run in containers, or when you want a solid starting point to customize from.
How to use
Claude Code / Cline
Copy this file to .agents/skills/docker-compose-generator/SKILL.md in your project root.
Then ask:
- "Use the Docker Compose Generator skill to create a docker-compose.yml for my Node.js app with PostgreSQL and Redis."
- "I have a Python FastAPI backend, a React frontend, and a Postgres database. Use the Docker Compose Generator skill."
The agent will ask clarifying questions before generating the file if your description is incomplete.
Cursor / Codex
Paste the instructions from the section below into your session along with a description of your stack.
The Prompt / Instructions for the Agent
When asked to generate a docker-compose.yml, follow these steps:
-
Gather requirements. If not already provided, ask for:
- The application services (e.g., web server, worker, frontend build)
- The data stores (PostgreSQL, MySQL, MongoDB, Redis, etc.) and their versions
- The runtime environment (Node.js, Python, Go, etc.) and version
- Whether this is for development or production (they differ significantly)
- Any custom ports, domains, or volume paths
-
Apply these rules to every service:
- Always set a
restartpolicy (unless-stoppedfor production,on-failurefor dev) - Add a
healthcheckfor every database or cache service - Use named volumes (not bind mounts) for persistent data in production
- Use a custom named network — do not rely on the default bridge network
- Put secrets and credentials in environment variables with
${VAR_NAME}placeholders, never hardcoded values - Set
depends_onwithcondition: service_healthyfor services that require a healthy DB before starting
- Always set a
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.
- 1mo ago First seen · 165 lines · 17 tokens per session scan A 0d3c2aeb948b
Docker Compose Generator is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,350 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
release-ota-promote
Publish signed Electron UI/daemon bundles to a local OTA feed with atomic manifest switch and digest readback, while dry-running the K8s drainrespawn rollout. Prod is refused before writes; feed publication is not client apply.
performing-container-image-hardening
This skill covers hardening container images by minimizing attack surface, removing unnecessary packages, implementing multi-stage builds, configuring non-root users, and applying CIS Docker Benchmark recommendations to produce secure production-ready images.
diag-container-oom
A diagnostic runbook for containers stopped by an out-of-memory condition. A container is an isolated process environment, and OOM means the operating system or container limit stopped it because it used too much memory.
diag-k8s-pod-crashloop
A diagnostic runbook for Kubernetes Pods stuck in CrashLoopBackOff. A Pod is a Kubernetes unit that runs one or more containers; CrashLoopBackOff means a container keeps failing and Kubernetes waits longer between restart attempts.
diag-k8s-node-pressure
A diagnostic runbook for Kubernetes node resource pressure. Kubernetes is a system that runs containers; a node is one machine in that system, and pressure means it is short on CPU, memory, disk space, or process IDs.
base-cn-registry-mirror-strategy
A set of guidelines for speeding up Docker images and programming-language package downloads in mainland China or other unstable cross-border networks. It covers sources and proxies for Docker, Debian, Alpine, Node, Python, Maven, Gradle, and Go.