horizun-revit-mcp: Instructions file for Codex

AGENTS.md

horizun-revit-mcp AGENTS.md is an instructions file for Codex, OpenCode from HorizunGroup/horizun-revit-mcp. It costs 6,163 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for Horizun Revit MCP, a bridge between an MCP-compatible coding assistant and Autodesk Revit running on the same machine.

In plain words
What is it for?
Use it when installing or configuring the bridge, connecting an assistant to Revit, or writing user-facing documentation and tool references.
Why use it?
It documents the required product naming, installation, configuration, and client setup rules for this Revit connection.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex; built for cline.

This is HorizunGroup/horizun-revit-mcp's own configuration. It tells Codex and OpenCode how to work on horizun-revit-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything horizun-revit-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HorizunGroup/horizun-revit-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HorizunGroup/horizun-revit-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/HorizunGroup/horizun-revit-mcp

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 horizun-revit-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/horizungroup/horizun-revit-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/horizungroup/horizun-revit-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/horizungroup/horizun-revit-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/horizungroup/horizun-revit-mcp/agents-md/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.

agentmods 80×15 button for horizun-revit-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/horizungroup/horizun-revit-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/horizungroup/horizun-revit-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,163 This file is loaded in full into every session.
When invoked 6,163 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.06163 $0.06163
Opus 5 $0.03082 $0.03082
Sonnet 5 $0.01233 $0.01233
Haiku 4.5 $0.00616 $0.00616

Measured 6d ago against content hash 3b376e37e399, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

horizun-revit-mcp 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 6d 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 · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Horizun Revit MCP — guide for agents / guía para agentes

English · Español

You are in the repository of Horizun Revit MCP: the MCP bridge between a client (Claude Code, Codex, any MCP client) and an Autodesk Revit running on this machine. Part of the Horizun Hub ecosystem.

Estás en el repositorio de Horizun Revit MCP: el puente MCP entre un cliente (Claude Code, Codex, cualquier cliente MCP) y un Autodesk Revit corriendo en esta máquina. Parte del ecosistema Horizun Hub.

The name is written Horizun — capital H, the rest lower case — every time it appears to a user, in any language. Never HORIZUN, never horizun as a word. It is a brand, not an acronym and not shouting. The only upper-case forms that exist are the tool names (horizun_*, always lower case) and the environment-variable prefix (HORIZUN_REVIT_YEAR and friends) — those are code identifiers, never how you refer to the product in prose.

El nombre se escribe Horizun — H mayúscula, el resto en minúscula — cada vez que aparece ante un usuario, en cualquier idioma. Nunca HORIZUN, nunca horizun como palabra. Es una marca, no una sigla ni un grito. Las únicas formas en mayúscula que existen son los nombres de las herramientas (horizun_*, siempre en minúscula) y el prefijo de variables de entorno (HORIZUN_REVIT_YEAR y demás) — esos son identificadores de código, no cómo te refieres al producto.


English

If the user asked you to install it, this is the whole procedure.

Install

Everything is compiled from this tree, against the Revit already installed on this machine. No executable is downloaded.

Prerequisites — check them first; the script checks them too:

  • Windows with at least one Revit 2023–2027 installed (C:\Program Files\Autodesk\Revit <year>\RevitAPI.dll exists).
  • The exact .NET SDK 10.0.400 on PATH (dotnet --version answers), fixed by global.json so release bytes do not depend on the latest installed patch. Revit ≤ 2024 still builds against .NET Framework 4.8 — the SDK-style projects restore the reference assemblies from NuGet, so the Visual Studio targeting pack is NOT required when NuGet restore is available. Verified on a machine without the pack: 2024 compiled with zero warnings. Only a fully offline machine needs the pack itself.
  • Revit closed. The script refuses to run with Revit open and changes nothing when it refuses.

Read the full file on GitHub · 466 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. 6d ago Changed · +40 lines · +489 tokens per session 3b376e37e399
  2. 12d ago First seen · 426 lines · 5,674 tokens per session scan A c5b7434da200

Subscribe to this mod's changes

horizun-revit-mcp AGENTS.md is an instructions file published in the GitHub repository HorizunGroup/horizun-revit-mcp (18 stars, last pushed 6d ago), licensed Apache-2.0. It adds 6,163 tokens to every session, about $0.0308 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens