What is vaults-diagram-tools AGENTS.md?

Repository instructions for vaults-diagram-tools, a local package for rendering Mermaid diagrams, generating diagrams from source code, and exposing these tools through MCP.

Use them to render Mermaid into SVG or JPG files, map source-code trees, serve diagram tools to agents, and validate diagram-related Markdown.

They define the package’s scope and identify the commands and agent files that should be used for diagram work.

vaults-diagram-tools AGENTS.md — Instructions file for Codex and OpenCode by Malnati: Repository instructions for vaults-diagram-tools, a lo

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/malnati/vaults-diagram-tools/agents-md

Clone the repo

git clone --depth 1 https://github.com/Malnati/vaults-diagram-tools

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/malnati/vaults-diagram-tools/agents-md.svg)](https://agentmods.dev/instructions/malnati/vaults-diagram-tools/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/malnati/vaults-diagram-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/malnati/vaults-diagram-tools/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,130 This file is loaded in full into every session.

When invoked 1,130 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.

Model	Per session	Once invoked
Fable 5.1	$0.01130	$0.01130
Opus 5	$0.00565	$0.00565
Sonnet 5	$0.00226	$0.00226
Haiku 4.5	$0.00113	$0.00113

Measured 5d ago against content hash a27f2f7da493, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

vaults-diagram-tools 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 5d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Escopo operacional

Este repositório é o pacote standalone vaults-diagram-tools, extraído para concentrar ferramentas portáveis de diagramas Mermaid, diagramas derivados de código-fonte e MCP.

Use este repositório para:

Renderizar fontes Mermaid para artefatos .svg e .jpg.
Gerar diagramas Mermaid a partir de árvores de código-fonte.
Expor as ferramentas de diagramação por MCP stdio.
Validar a política Markdown de diagramas.

Mantenha este repositório limitado ao tooling portável de diagramas; fluxos de conteúdo externo ficam fora do escopo operacional deste pacote.

Artefatos de agentes identificados no projeto

Codex

AGENTS.md: orientação operacional do projeto para agentes.

Cursor

.cursor/rules/mermaid-renderer-tooling.mdc
.cursor/rules/source-diagrams-tooling.mdc
.cursor/skills/mermaid-renderer-tooling.md
.cursor/skills/source-diagrams-tooling.md
.cursor/hooks.json: superfície explícita sem hooks configurados.

Tooling real do repositório

vaults-mermaid-render: CLI pública para renderização Mermaid.
vaults-source-diagrams: CLI pública para geração de diagramas a partir de código-fonte.
vaults-diagram-mcp: servidor MCP stdio do pacote.
vaults-markdown-diagram-policy: checker da política Markdown de diagramas.
packages/renderer/render-mermaid-assets.mjs: implementação principal do renderer.
packages/renderer/render-mermaid-assets.sh: wrapper de compatibilidade do renderer.
packages/renderer/check-markdown-diagram-policy.py: implementação do checker Markdown.
packages/source-diagrams/source-diagrams.mjs: implementação principal do gerador source-diagrams.
packages/mcp/server.mjs: servidor MCP.
packages/mcp/tools.mjs: adaptação MCP para os CLIs reais.

Regras obrigatórias

Ao renderizar Mermaid, cada fonte .mmd ou .mermaid deve gerar .svg e .jpg no mesmo ciclo.
Em Markdown, exibir o código Mermaid em bloco cercado com linguagem mermaid; não usar mmd como linguagem do bloco.
Em Markdown, manter .mmd, .svg e .jpg como links relativos; não embutir SVG/JPEG com sintaxe de imagem por padrão.
Usar vaults-mermaid-render ou packages/renderer/render-mermaid-assets.mjs para renderização canônica.
Usar vaults-source-diagrams ou packages/source-diagrams/source-diagrams.mjs para diagramas derivados de código-fonte.
Para fluxos MCP, manter a superfície explícita de três tools: render_mermaid_text, render_mermaid_file, generate_source_diagrams.
Para lógica e testes rápidos de source-diagrams, usar --render-mode placeholder quando a fidelidade visual não estiver em escopo.
Para entrega real de assets, usar renderização canônica e validar presença de .mmd, .svg, .jpg e manifest quando aplicável.

Read the full file on GitHub · 85 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.

5d ago First seen · 85 lines · 1,130 tokens per session scan A a27f2f7da493

Subscribe to this mod's changes

vaults-diagram-tools AGENTS.md is an instructions file published in the GitHub repository Malnati/vaults-diagram-tools (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,130 tokens to every session, about $0.0056 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.

diagrams docker github-actions jpeg mcp mermaid

MCP-Sentinel AGENTS.md

AGENTS.md instructions for BashaarJavaid/MCP-Sentinel, covering agents.md, project, where things live, conventions and commands.

BashaarJavaid/MCP-Sentinel · 2,438 tokens

mdg CLAUDE.md

Instructions for HighDesertWizard/mdg, covering project rules and frozen mermaid code blocks.

HighDesertWizard/mdg · 88 tokens

frankenmermaid AGENTS.md

AGENTS.md instructions for Dicklesworthstone/frankenmermaid, covering agents.md — frankenmermaid, rule 0 - the fundamental override prerogative, rule number 1: no file deletion, never use github actions — releases are via /dsr only and demo site deployment: cloudflare pages (wrangler).

Dicklesworthstone/frankenmermaid · 9,699 tokens

vaults-diagram-tools AGENTS.md