rvtdocs-mcp: Instructions file for Codex

AGENTS.md

rvtdocs-mcp AGENTS.md is an instructions file for Codex, OpenCode from trgiangv/rvtdocs-mcp. It costs 975 tokens per session, scanned A, original, MIT.

A set of instructions for rvtdocs-mcp, a local server for exploring Revit API documentation. Revit is software used for building design, and an API is the interface programmers use to control or extend it.

In plain words
What is it for?
Finding Revit API entries, browsing namespaces and class members, comparing two Revit versions, and fetching documentation pages.
Why use it?
It lets an agent search cached Revit documentation, browse API members, compare versions, and fetch detailed pages without repeatedly downloading the full index.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is trgiangv/rvtdocs-mcp's own configuration. It tells Codex and OpenCode how to work on rvtdocs-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 rvtdocs-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to trgiangv/rvtdocs-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/trgiangv/rvtdocs-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/trgiangv/rvtdocs-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 rvtdocs-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/trgiangv/rvtdocs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/trgiangv/rvtdocs-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 975 This file is loaded in full into every session.
When invoked 975 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 $0.00975 $0.00975
Opus 5.5 $0.00390 $0.00390
Sonnet 5.5 $0.00195 $0.00195
Haiku 4.5 $0.00097 $0.00097

Measured 2mo ago against content hash 13c2ef4e649f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rvtdocs-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 2mo 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Overview

rvtdocs-mcp is a local-first MCP server for Revit API documentation exploration. Downloads the full API tree index from rvtdocs.com once per version, caches in AppData, then provides instant keyword search, namespace browsing, version comparison, and page fetching — all offline after initial download.

Architecture

rvtdocs.com/static/json_trees/sidebar_{year}.json (7MB per year)
    ↓ (download once)
%APPDATA%/rvtdocs-mcp/revit_{year}.json (cached permanently)
    ↓ (load ~350ms)
In-memory index (28K entries per year)
    ↓
Tools: search (7ms) | scan (1ms) | diff (1ms) | fetch (network)

Tools (4 total)

Tool Purpose Mode Latency
rvtdocs_search Keyword search across 28K API entries Local index ~7ms
rvtdocs_scan Browse namespace or class members Local index ~1ms
rvtdocs_diff Compare API between two Revit versions Local index ~1ms
rvtdocs_fetch Fetch detailed page content by URL Network + cache 50-500ms

Project Structure

src/
  server.py           # MCPServer entry point (wiring only)
  config.py           # Constants (BASE_URL, years, limits)
  cache_store.py      # In-memory LRU page cache
  fetcher.py          # HTTP client with cache
  extractor.py        # HTML -> text (trafilatura)
  search/
    __init__.py
    tree_index.py     # Core: download, index, search, scan, scoring
  tools/
    __init__.py       # Tool registration
    search.py         # rvtdocs_search (sync, local)
    scan.py           # rvtdocs_scan (sync, local)
    diff.py           # rvtdocs_diff (sync, local)
    fetch.py          # rvtdocs_fetch (async, network)

Commands

uvx --from . rvtdocs-mcp       # Run server (MCP stdio)
uv run python -c "..."          # Quick test

Data

  • Source: https://rvtdocs.com/static/json_trees/sidebar_{year}.json
  • Local cache: %APPDATA%/rvtdocs-mcp/revit_{year}.json (Win) or ~/.cache/rvtdocs-mcp/ (Unix)
  • Supported years: 2022, 2023, 2024, 2025, 2026, 2027
  • Entries per year: ~28,000 (namespaces, classes, methods, properties, enums, etc.)
  • Download: lazy (first query per year triggers download)

Read the full file on GitHub · 96 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. 2mo ago First seen · 96 lines · 975 tokens per session scan A 13c2ef4e649f

Subscribe to this mod's changes

rvtdocs-mcp AGENTS.md is an instructions file published in the GitHub repository trgiangv/rvtdocs-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 975 tokens to every session, about $0.0039 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.

Related

rvtdocs-mcp AGENTS.md compared with instructions from other repositories

rvtdocs-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rvtdocs-mcp AGENTS.mdtrgiangv/rvtdocs-mcpInstructions file23mo agoMITA975Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode