Mermaid diagrams that parse the first time: syntax reference, SVG/PNG/ASCII rendering, real product icons, and a hook that checks every .mermaid write.
0 on GitHubby John Randallv1.0.0MITupdated 27 days agodiagrams
/
Plugin mermaid from marketplace johntrandall-plugins in johntrandall/claude-plugins. Commands read from the repo's manifest — 26 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
What it installs
Skills (3)
mermaid-architecture-iconify
Render Mermaid diagrams with real iconography using architecture-beta or flowchart icon shape (v11.3+) backed by Iconify icon packs. Auto-invoke when adding icons to a Mermaid diagram, when colored rectangles need real product/cloud logos (AWS, GCP, databases, languages), when mentioning architectur
mermaid-studio
Multi-format Mermaid rendering (SVG / PNG / ASCII) and domain references for non-flowchart Mermaid types. Auto-invoke when the user is working with Mermaid specifically AND any of: PNG / ASCII output, batch rendering across many `.mermaid` files, C4 architecture diagrams, AWS architecture-beta with
mermaid-syntax
Mermaid (mermaid-js) diagram syntax — special characters, reserved words, escaping rules, v11 breaking changes, per-diagram-type syntax (flowchart, sequence, class, state, ER, gantt, mindmap, class-diagram, architecture-beta). Auto-invoke when the user is working with Mermaid specifically — `.mermai
A role model for multi-agent work in herdr with a human in the loop: architect and steward seats, rules and run leads, crew sub-types, historians, paper trails and watchers. Optional: obsidian-track-changes-agent for collaborative drafting.
Lets AI agents take part in CriticMarkup review in Obsidian: agents propose and comment as tracked changes, and you accept or reject them with the Track Changes plugin.
Text from images and scanned PDFs on macOS: vision-language model versus OCR engine, an Apple Vision helper, why embossed cards defeat bitonal scans, and extraction without exposing sensitive values.
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Recommended: all published HyperFrames skills in one versioned bundle. Create and render videos from HTML: the contract, film, captions, overlays, motion and look references, the CLI, the registry, media, Figma, slideshows and Remotion ports.
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.