Borrowing it
Nothing to install: this file belongs to Vanderjohnny/solibri-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/Vanderjohnny/solibri-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Vanderjohnny/solibri-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/vanderjohnny/solibri-mcp/claude-md)<a href="https://agentmods.dev/instructions/vanderjohnny/solibri-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vanderjohnny/solibri-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00926 | $0.00926 |
| Opus 5 | $0.00463 | $0.00463 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
solibri-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 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruções para agentes (Claude Code, Claude Desktop)
Este projeto expõe o Solibri como ferramentas MCP. As regras abaixo existem para evitar desperdício de tokens e resultados imprecisos.
1. Regra geral: dados, não pixels
Use captura de tela o mínimo possível. Sempre que existir uma via de dados — API, MCP, arquivo, linha de comando — use ela em vez de olhar a tela.
Um screenshot custa de 1.500 a 2.500 tokens. Uma sessão feita por prints e cliques consome dezenas de milhares. A mesma informação por API costuma custar de 50 a 200 tokens. E o custo é o menor dos problemas: um GUID, uma cota ou um nome de parâmetro lido de imagem pode vir errado, e o erro se propaga em silêncio para o resto da tarefa.
Antes de capturar a tela, pergunte-se: existe uma ferramenta que me dá esse dado como texto? Se existir, use-a.
| Em vez de | Prefira |
|---|---|
| Print da janela do Solibri | mcp__solibri__* (REST API) |
| Print da viewport do Revit | Ferramentas que retornam dados/elementos, não imagem |
| Print de página web | Leitura da árvore de acessibilidade / texto da página |
| Print de terminal ou log | Ler o arquivo de log direto |
| Print de planilha ou PDF | Ler o arquivo com a ferramenta do formato |
Quando um print é legítimo
Capturar a tela é aceitável em três casos, e vale dizer ao usuário por que está fazendo:
- O programa não tem via de dados para o que se precisa.
- O usuário pediu explicitamente uma conferência visual (aparência, layout, render).
- Diagnóstico de última instância, depois que a via de dados falhou e você já explicou ao usuário o que falhou.
Fora disso, não capture. E nunca entre em laço de print → clique → print: é o padrão que mais queima tokens, e o mais frágil.
2. Solibri: use a API, nunca a tela
Para qualquer tarefa envolvendo o Solibri, use exclusivamente as ferramentas
mcp__solibri__*. Não opere a interface por mouse, teclado ou imagem.
Se as ferramentas falharem
Quando solibri_ping responder que não conseguiu falar com a REST API, o problema é
como o Solibri foi aberto, não a ferramenta.
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.
- 6d ago First seen · 89 lines · 926 tokens per session scan A 4800f0692811
solibri-mcp CLAUDE.md is an instructions file published in the GitHub repository Vanderjohnny/solibri-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 926 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
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.
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.
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 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).
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.