An architecture-documentation skill that creates high-level Mermaid diagrams of a software system, its surrounding systems, and its major parts. It also maps bounded contexts, which are areas of a system with their own business rules and terms.

Use it to create or update system-context, container, and domain-boundary diagrams in a project’s architecture documentation without showing implementation details.

It turns existing product and architecture documents into diagrams that make system boundaries, relationships, and communication easier to understand.

diagramar — Skill for Claude Code by igoruehara: An architecture-documentation skill that creates high-level Mermaid diagrams of…

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 skills/igoruehara/spec-driven/diagramar

Any agent

npx skills add igoruehara/spec-driven --skill diagramar

Clone the repo

git clone --depth 1 https://github.com/igoruehara/spec-driven

Made for: Claude Code.

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/skills/igoruehara/spec-driven/diagramar.svg)](https://agentmods.dev/skills/igoruehara/spec-driven/diagramar)

Your own site

<a href="https://agentmods.dev/skills/igoruehara/spec-driven/diagramar"><img src="https://agentmods.dev/badge/skills/igoruehara/spec-driven/diagramar.svg" alt="Measured on agentmods" height="20"></a>

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 730 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00088	$0.00730
Opus 5	$0.00044	$0.00365
Sonnet 5	$0.00018	$0.00146
Haiku 4.5	$0.00009	$0.00073

Measured 6d ago against content hash b6ccee62f5a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

diagramar 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.

template/.claude/skills/diagramar/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Diagramar arquitetura (Mermaid, alto nível)

Gera os diagramas de arquitetura em Mermaid (renderizam no GitHub e no Claude Code) a partir dos artefatos de discovery. Mantenha alto nível: atores, sistemas, containers e contextos — nunca classes, tabelas ou detalhe de implementação (isso é escopo do design.md da feature).

Insumos (puxe só o que existir e cite a origem)

docs/product/vision.md — atores/personas e propósito do sistema.
docs/architecture/context-map.md — bounded contexts e relações (DDD).
specs/*/design.md — containers, serviços e integrações.
docs/architecture/assessment.md — as-is, no brownfield.
Lacunas → pergunte (AskUserQuestion): atores externos, sistemas vizinhos, principais containers (UI/serviços/dados/filas) e a jornada crítica a ilustrar.

Diagramas (alto nível, alinhado a C4 + DDD)

Contexto do sistema (C4 L1): o sistema no centro + personas + sistemas externos.
Containers (C4 L2): apps/serviços, dados, filas e como conversam.
Mapa de bounded contexts (DDD): contextos e padrões de relação (ACL, Customer/Supplier, Conformist, Shared Kernel).
(opcional) Fluxo-chave: uma jornada crítica em sequenceDiagram.

Use flowchart (renderiza em todo lugar) ou os diagramas C4 nativos do Mermaid (C4Context, C4Container) se o renderizador suportar. Rótulos na linguagem ubíqua do glossary.md.

Saída

Escreva/atualize docs/architecture/diagrams.md (já existe como placeholder; mantenha o frontmatter alwaysApply: false). Cada diagrama num bloco ```mermaid, com título e 1 linha de contexto.
Garanta o link de volta em context-map.md. Regenere quando a arquitetura mudar — diagrama desatualizado engana mais que ajuda.

Regras

Alto nível only. Pediram detalhe de classe/tabela? Diga que é escopo do design.md.
Valide a sintaxe antes de entregar — rode o gate determinístico (não confie só no olho):
```
node scripts/validate-mermaid.mjs .
```
Pega bloco vazio, tipo de diagrama ausente/desconhecido e aspas/delimitadores desbalanceados. Corrija os erros antes de salvar; é o mesmo gate que roda na CI (esteira.yml).
Não invente componentes que não estão nos insumos — pergunte (ver verificação de conhecimento no CLAUDE.md).

Read the full file on GitHub · 46 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.

6d ago First seen · 46 lines · 88 tokens per session scan A b6ccee62f5a3

Subscribe to this mod's changes

diagramar is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 730 once invoked, about $0.0004 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.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens