By sheeeng
Generates self-contained HTML visualizations from markdown implementation plans showing BEFORE/AFTER architecture, diff-marked components, key decisions, and risks
Generates HTML visualizations from markdown implementation plans. Opens in any browser — shows BEFORE/AFTER architecture with diff-marked components, mermaid architecture diagrams, key decisions, risks, and interactive feedback annotations.

Add the marketplace to Claude Code:
/plugin marketplace add omril321/claude-plan-visualizer
Then install the plugin:
/plugin install plan-visualizer@claude-plan-visualizer
Create ~/.claude/plan-visualizer.json to customize the URL protocol for plan file links:
{"url_protocol": "open-cursor"}
Supported protocols: file (default), open-cursor, vscode, or any custom protocol handler.
If this file doesn't exist, the plugin defaults to file:// links.
Invoke the agent manually by asking Claude to visualize a plan:
Visualize the plan at plans/my-plan.md
Or use it programmatically from a planning skill by invoking the plan-visualizer:plan-visualizer agent with the plan file path.
~/.claude/plan-visualizer.json for URL protocol preferenceplan-basename.visualization.html alongside the plan fileA single HTML file with:
The generated HTML includes an interactive annotation system:
Feedback about the plan:
1. About `<selected text>`: <your comment>
2. About `<another selection>`: <your comment>
When a plan has 3+ components with relationships, the agent generates a mermaid architecture overview diagram showing:
Mermaid.js is loaded from unpkg CDN (requires internet connection).
Works best with plans containing:
## Summary with a **Goal:** line**What changes:** bullet list of files/components**Key decisions:** and **Risks:** sub-fields## Steps with ### Step N headings and verify criteria## Assumptions and ## Success Criteria## Scope Definition with In Scope / Out of ScopeAlso handles plans without these sections via graceful fallback.
The agent skips visualization when the plan:
| Component | Purpose |
|---|---|
plan-visualizer agent | Reads plan markdown, generates HTML visualization |
knowledge/plan-visualizer-template.html | HTML/CSS/JS template with mermaid support and feedback system |
~/.claude/plan-visualizer.json | User config file for URL protocol (outside plugin) |
MIT
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub sheeeng/omril321-claude-plan-visualizer --plugin plan-visualizerDirect browser control via CDP. Drives the user's real Chrome (or a Browser Use cloud browser) with coordinate clicks, screenshots, and Python helpers — no selector hunting. Requires the one-time `browser-harness` CLI install (see the skill's references/install.md).
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification