mcp-coolify AGENTS.md

mcp-coolify AGENTS.md is an instructions file for Codex, OpenCode from hecateq/mcp-coolify. It costs 3,024 tokens per session, scanned A, original, MIT.

A persistent instruction file for AI coding assistants working in the hecateq/mcp-coolify repository. It explains the project, its rules, structure, and expected workflow so a new assistant can resume work quickly.

In plain words
What is it for?
Use it to guide assistants that develop or maintain an MCP server for Coolify, a self-hosted platform for running applications.
Why use it?
It prevents an assistant from starting without the project context or accidentally ignoring repository-specific rules.

Instructions file for CodexOpenCode

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 instructions/hecateq/mcp-coolify/agents-md
Clone the repo
git clone --depth 1 https://github.com/hecateq/mcp-coolify

Made for: Codex, OpenCode.

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 mcp-coolify AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hecateq/mcp-coolify/agents-md.svg)](https://agentmods.dev/instructions/hecateq/mcp-coolify/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hecateq/mcp-coolify/agents-md"><img src="https://agentmods.dev/badge/instructions/hecateq/mcp-coolify/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,024 This file is loaded in full into every session.
When invoked 3,024 The same file — it is already loaded in full.
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 $0.03024 $0.03024
Opus 5 $0.01512 $0.01512
Sonnet 5 $0.00605 $0.00605
Haiku 4.5 $0.00302 $0.00302

Measured 3d ago against content hash 976a0056e8d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-coolify AGENTS.md 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 3d 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.

AGENTS.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Coding Assistant — Save & Restore Instructions

Audience: AI coding assistants (GitHub Copilot, Claude, Cursor, opencode, Aider, etc.) working on this repository. Purpose: A persistent recovery document so any AI session that joins this repo cold — without prior conversation history, with no clue what this codebase is, and without reading every file — can get up to speed in under 60 seconds and start producing correct, scoped work.

⚠️ IMPORTANT: If you are an AI assistant reading this file, treat it as the highest-priority context after the user's current message. The project rules below are mandatory and override generic coding preferences you may have been trained on.


0. The 30-second elevator pitch

Name @imhecateq/mcp-coolify
What A Model Context Protocol (MCP) server that exposes Coolify (self-hosted PaaS) infrastructure to AI agents with a security/policy layer
Why Coolify's built-in MCP is a raw pass-through. This server adds operation-mode, scoped tokens, allowlists, production safeguards on top
Audience DevOps engineers and AI agent users managing Coolify deployments
GitHub https://github.com/hecateq/mcp-coolify
npm @imhecateq/mcp-coolify (scoped; do NOT use @hecateq/* — that scope requires org membership)
CLI bin mcp-coolify (after npm install -g)
License MIT

1. Hard rules — DO NOT violate

These are non-negotiable invariants. Violating any of them is a blocking error.

  1. Package name is @imhecateq/mcp-coolify, NOT @hecateq/mcp-coolify. The @hecateq npm scope requires membership in the hecateq npm organization, which the maintainer does not have. If you see code or docs using @hecateq/mcp-coolify, fix it to @imhecateq/mcp-coolify.

  2. Language of documentation and code comments: English. Turkish text MUST NOT appear in any documentation or inline code comments. Some shell-script comments in .env.example and bash snippets MAY remain in Turkish because they live inside code blocks (glossary rule: code blocks are untouched).

Read the full file on GitHub · 228 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. 3d ago First seen · 228 lines · 3,024 tokens per session scan A 976a0056e8d2

Subscribe to this mod's changes

mcp-coolify AGENTS.md is an instructions file published in the GitHub repository hecateq/mcp-coolify (1 stars, last pushed 17d ago), licensed MIT. It adds 3,024 tokens to every session, about $0.0151 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.