Borrowing it
Nothing to install: this file belongs to bimwright/rvt-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.
curl -O https://raw.githubusercontent.com/bimwright/rvt-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/bimwright/rvt-mcpWrote 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.
[](https://agentmods.dev/instructions/bimwright/rvt-mcp/claude-md)<a href="https://agentmods.dev/instructions/bimwright/rvt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bimwright/rvt-mcp/claude-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.
<a href="https://agentmods.dev/instructions/bimwright/rvt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bimwright/rvt-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03534 | $0.03534 |
| Opus 5.5 | $0.01414 | $0.01414 |
| Sonnet 5.5 | $0.00707 | $0.00707 |
| Haiku 4.5 | $0.00353 | $0.00353 |
Grade A, and why
rvt-mcp CLAUDE.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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RvtMcp-MCP
Open-source (Apache-2.0) MCP gateway that lets Claude Code (and any MCP-capable client) drive Autodesk Revit 2022–2027.
Architecture
Full C# stack. No TypeScript. Single language, single build system. Multi-version: one plugin shell per Revit 2022–2027.
MCP client (Claude Code / Cursor / Cline / …) → stdio → C# MCP Server (.NET 8 Console App) → TCP or Named Pipe → per-version C# plugin shell → Revit 2022–2027 API
Two processes:
- RvtMcp.Server.exe — MCP Server, runs as separate process, stdio transport (ModelContextProtocol NuGet)
- RvtMcp.Plugin.dll — Revit addin, loads inside Revit.exe, TCP listener (Revit 2022–2024) or Named Pipe (Revit 2025–2027) + ExternalEvent marshalling. Each Revit version gets its own shell DLL compiled from the same
src/shared/source glob.
Communication: newline-delimited JSON (NDJSON). Discovery files written per Revit instance in %LOCALAPPDATA%\Bimwright\rvt-mcp\:
revit-<year>-<pid>.json— per-instance descriptor (schema 3) for every instance, plus the legacyrevit-<year>.jsonfor older serversrevit-2022.json/revit-2023.json/revit-2024.json— legacy per-year files: TCP transport (port OS-assigned) + auth token + PIDrevit-2025.json/revit-2026.json/revit-2027.json— legacy per-year files: Named Pipe transport + auth token + PID
Discovery file format (schema_version=3):
{
"schema_version": 3,
"host_app": "revit",
"host_year": 2024,
"revit_year": 2024,
"target_id": "revit-2024-67890",
"pid": 67890,
"process_start_utc": "2026-10-06T08:00:00.000Z",
"transport": "tcp",
"port": 49891,
"pipe_name": null,
"auth_token": "...",
"capabilities": ["tool_catalog", "controlled_failures_v1"]
}
window_title is not in the descriptor — the server reads it live from the process. The server binds to exactly one instance by scanning these files (skipping any whose pid is dead, deduplicating per-instance vs legacy by pid). Use --target 2022 / pid:<n> / id:revit-<year>-<pid> (4-digit calendar year, NOT legacy R-codes) to pin a specific instance when multiple Revits run. Agents should call revit_list_available_targets to enumerate live instances and revit_get_current_target to inspect the pinned target rather than guessing version strings — revit_switch_target hard-fails with an educational error if passed an R-code like R24.
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.
- 7d ago Changed · +76 tokens per session bdb8109e6248
- 9d ago Changed · +25 lines · +857 tokens per session c94a8d015619
- 20d ago Changed · +6 lines · +161 tokens per session 1a1e8f6ad739
- 24d ago Changed · +105 tokens per session 5f4ba7a7ba05
- 29d ago Changed 82ba1e3c6cd6
- 1mo ago Changed · +32 tokens per session 33776e894e2d
- 1mo ago First seen · 135 lines · 2,303 tokens per session scan A 2e9d3b0cdaaf
rvt-mcp CLAUDE.md is an instructions file published in the GitHub repository bimwright/rvt-mcp (103 stars, last pushed 5d ago), licensed Apache-2.0. It adds 3,534 tokens to every session, about $0.0141 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.