Plugin

c4m

Interactive C4 architecture diagrams (Simon Brown's model) for Claude Code. Five mode-driven workflows — Design (greenfield), Document-code (retro-doc from a repo), Document-prose (from README/ADR/spec), Review (critique an existing diagram), Update (evolve one) — accessed via /c4m:auto, /c4m:design, /c4m:code, /c4m:prose, /c4m:review, /c4m:update. Output is one Markdown document per C4 level with embedded Mermaid; format negotiable (Structurizr DSL, PlantUML) and destination negotiable (filesystem or MCP — Notion, Linear, Drive). Enforces the editorial invariants: technology mandatory on every Container/Component, intent-specific relationship labels, protocol on inter-container links, assumptions kept explicit.

• Published source
• Repository

Analysed

11 October 2026

Last observed

12 October 2026

What the code does

Static analysis found none of the capabilities we track, such as shell commands, network requests or file writes, in the latest version.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.