agentmods.dev

mcp-coolify copilot-instructions.md

mcp-coolify copilot-instructions.md is an instructions file for GitHub Copilot from hecateq/mcp-coolify. It costs 1,308 tokens per session, scanned A, original, MIT.

A set of project instructions for GitHub Copilot, an AI coding assistant, when it works on the Coolify MCP server repository. MCP is a standard way for software to provide tools and context to AI assistants.

In plain words
What is it for?
Use it to guide code changes, reviews, tests, linting, builds, package publishing, and English-language documentation in that repository.
Why use it?
It gives the assistant the repository's constraints, terminology, and required checks so suggested changes fit the project.

Instructions file for GitHub Copilot

not rated 1 16d ago A scan 1,308 tokens original MIT
View the source file hecateq/mcp-coolify
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/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/hecateq/mcp-coolify

Made for: GitHub Copilot.

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 copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hecateq/mcp-coolify/copilot-instructions.svg)](https://agentmods.dev/instructions/hecateq/mcp-coolify/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/hecateq/mcp-coolify/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hecateq/mcp-coolify/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,308 This file is loaded in full into every session.
When invoked 1,308 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 $0.01308 $0.01308
Opus 5 $0.00654 $0.00654
Sonnet 5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 3d ago against content hash 86a7c7fdee9c, 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 copilot-instructions.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.

.github/copilot-instructions.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot — Project Context

This file is auto-loaded by GitHub Copilot Code Review, Copilot Chat, and Copilot Workspace when working in this repository. It complements AGENTS.md (the project-wide AI recovery document).

TL;DR

  • Package: @imhecateq/mcp-coolify (npm scope MUST match authenticated npm account)
  • Type: Model Context Protocol (MCP) server wrapping the Coolify self-hosted PaaS API
  • Build: tsup → dist/index.js (NOT .mjs)
  • Test: vitest, must stay at 221/221 passing
  • Lint: ESLint, must pass clean
  • Pre-publish: prepublishOnly runs lint+typecheck+test+build — do NOT skip with --ignore-scripts

Mandatory constraints

  1. Package scope is @imhecateq/*, NEVER @hecateq/*. The latter requires membership in the hecateq npm organization, which the maintainer does not have. If you see a code change suggesting @hecateq/mcp-coolify, reject it.
  2. All prose must be in English. No Turkish in commit messages, PR titles, PR descriptions, code reviews, or .md files (except docs/GLOSSARY.md which is a translation reference). Code blocks may contain legacy Turkish comments — leave them alone.
  3. Don't add new runtime dependencies without explicit user request. The 9-dep budget is @fastify/cors, @fastify/static, @modelcontextprotocol/sdk, dotenv, express, fastify, pino, pino-pretty, uuid, zod.
  4. dist/ is git-ignored and build-generated. Never edit files inside dist/. Edit src/*.ts and run npm run build.
  5. Build output filename is dist/index.js, not dist/index.mjs. Despite ESM format, the file ends in .js because the CLI has a shebang. If you suggest an example or doc, use this exact filename.
  6. bin field is mcp-coolify (unscoped). npm install -g registers the binary as mcp-coolify. Local installs reference node_modules/@imhecateq/mcp-coolify/dist/index.js.
  7. No bypasses: no as any, no @ts-ignore, no @ts-expect-error, no empty catch, no deleted failing tests. Fix root causes.

Read the full file on GitHub · 88 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 · 88 lines · 1,308 tokens per session scan A 86a7c7fdee9c

Subscribe to this mod's changes

mcp-coolify copilot-instructions.md is an instructions file published in the GitHub repository hecateq/mcp-coolify (1 stars, last pushed 16d ago), licensed MIT. It adds 1,308 tokens to every session, about $0.0065 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.

ai-agentcoolifymcpmcp-servermcp-serversself-hosted
Related

Other instructions, from other repositories

daz-mcp-server CLAUDE.md

Claude Code instructions for bluemoonfoundry/daz-mcp-server, covering claude.md (project index), primary commands, skill modules (reference with @), architecture summary and render api (dazscriptserver native endpoints).

bluemoonfoundry/daz-mcp-server · 1,530 tokens

mcpscore AGENTS.md

Instructions for mcp-box/mcpscore, covering agent instructions for mcpscore and gotchas (learned the hard way).

mcp-box/mcpscore · 1,268 tokens

vector_mcp AGENTS.md

AGENTS.md instructions for sergiobayona/vector_mcp, covering agents.md, project overview, essential commands, development setup and testing and quality.

sergiobayona/vector_mcp · 4,505 tokens

PBP CLAUDE.md

Instructions for MadGapun/PBP, covering pbp — claude-code-memory, stand 2026-08-25 (v1.7.23 stable) — ehrliche zahlen, stand 2026-07-16 (v1.8.0-beta.6, prerelease) — hotfix #760, stand 2026-07-14 (v1.7.7) — scoring-fairness & praxis-funde and stand 2026-07-03 (v1.7.6) — alltags-fuehrung.

MadGapun/PBP · 22,232 tokens

mcp-scribe CLAUDE.md

Instructions for The-Swarm-Corporation/mcp-scribe, covering claude.md, what this is, commands, formatting: black only. do not run ruff format and architecture.

The-Swarm-Corporation/mcp-scribe · 2,113 tokens

mcp-router CLAUDE.md

Claude Code instructions for mcp-router/mcp-router, a project described as: A Unified MCP Server Management App (MCP Manager).

mcp-router/mcp-router · 515 tokens