coolify

coolify is a skill for Claude Code, Codex from StuMason/coolify-mcp. It costs 156 tokens per session (2,138 once invoked), scanned A, original, MIT.

A guide for operating Coolify, a self-hosted platform for deploying and managing applications, databases, services, and servers.

In plain words
What is it for?
Use it when managing Coolify projects, environments, applications, databases, services, deployments, environment variables, servers, or private keys.
Why use it?
It provides the required approach for inspecting, deploying, restarting, and debugging resources managed by Coolify, including how those resources are organized.

Skill for Claude CodeCodex

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 skills/stumason/coolify-mcp/coolify
Any agent
npx skills add StuMason/coolify-mcp --skill coolify
Clone the repo
git clone --depth 1 https://github.com/StuMason/coolify-mcp

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 coolify

README.md
[![agentmods](https://agentmods.dev/badge/skills/stumason/coolify-mcp/coolify.svg)](https://agentmods.dev/skills/stumason/coolify-mcp/coolify)
Your own site
<a href="https://agentmods.dev/skills/stumason/coolify-mcp/coolify"><img src="https://agentmods.dev/badge/skills/stumason/coolify-mcp/coolify.svg" alt="Measured on agentmods" height="20"></a>
Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00156 $0.02138
Opus 5 $0.00078 $0.01069
Sonnet 5 $0.00031 $0.00428
Haiku 4.5 $0.00016 $0.00214

Measured 4d ago against content hash 050b1f4555f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coolify 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 4d 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.

Use it for any user request that touches a Coolify-managed resource, even when the user phrases the request in product terms ("redeploy the API", "restart postgres", "check why staging is unhealthy") rather than naming C
skills/coolify/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coolify MCP Skill

This skill teaches Claude how to use the Coolify MCP server (@masonator/coolify-mcp) effectively. The server exposes ~38 token-optimized tools that wrap the Coolify API for managing self-hosted apps, databases, services, and infrastructure.

When to use this skill

Use it for any user request that touches a Coolify-managed resource, even when the user phrases the request in product terms ("redeploy the API", "restart postgres", "check why staging is unhealthy") rather than naming Coolify explicitly. If a Coolify MCP tool exists for the job, prefer it over curl, the Coolify HTTP API directly, SSH, or generic shell access — the MCP tools return summarized, token-cheap responses and include _actions hints for the natural next step.

If the Coolify MCP server is not configured in the current session, tell the user how to install it (see "Setup" below) instead of guessing.

Mental model

Coolify resources form a hierarchy: Server → Project → Environment → (Application | Database | Service). Most "smart lookup" tools accept either a UUID or a human-friendly identifier (name, domain, IP), so you usually don't need to look up UUIDs first. Start broad (get_infrastructure_overview, find_issues) and narrow down with diagnose_app / diagnose_server before taking action.

The API splits "list" (cheap, summarized) from "get" (full detail). Always start with a list/overview call and only fetch full details for the specific resource you care about — this keeps responses small and fast.

Core workflow

  1. Orient. If you don't already know the relevant resource, call get_infrastructure_overview (one call returns a summary of everything) or find_issues (scans for unhealthy resources). For a known target, jump straight to diagnose_app or diagnose_server.
  2. Diagnose before acting. For application problems, diagnose_app <name|domain|uuid> returns status, recent logs, env vars, and deployment history in one shot. Read it before restarting or redeploying — the cause is often visible there.
  3. Act. Use control to start/stop/restart, deploy to trigger a build, application / database / service for CRUD, and env_vars for environment variables.
  4. Verify. After a deploy or restart, call deployment for status, then application_logs (or diagnose_app again) to confirm the resource came back healthy.
  5. Report back. Summarize what you changed, link the resource by name, and surface anything from _actions that the user might want to do next.

Read the full file on GitHub · 148 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. 4d ago First seen · 148 lines · 156 tokens per session scan A 050b1f4555f7

Subscribe to this mod's changes

coolify is a skill published in the GitHub repository StuMason/coolify-mcp (575 stars, last pushed yesterday), licensed MIT. It adds 156 tokens to every session and 2,138 once invoked, about $0.0008 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 2026-08-30.