🔍 Visualize any Claude Code agent harness — CLAUDE.md, subagents, skills, commands, hooks & MCP servers — as an interactive flow graph. Import from GitHub, ZIP, or local folder. 100% client-side.
Claude Code Flow Visualizer — See Your Entire Agent Harness as an Interactive Graph
Visualize any Claude Code configuration (CLAUDE.md, subagents, skills, slash commands, hooks, MCP servers, schedulers) as one interactive flow diagram — straight from a GitHub URL, a ZIP, or a local folder. No install for your target repo, no backend, 100% client-side.
Claude Code agent setups live as scattered markdown files: CLAUDE.md, .claude/agents/.md, .claude/skills//SKILL.md, commands, settings.json hooks, and .mcp.json connectors. To understand how an existing harness works — which agent delegates to which, what skills fire when, where Notion/database/MCP connections plug in — you'd normally have to open and read every single file.
This tool parses the whole project and renders it as a wired graph in seconds:
- 🤖 Agents with model + tool badges, delegation edges traced from prompt bodies - 📚 Skills attached to the agents and commands that actually reference them - ⌨️ Slash commands, 🪝 lifecycle hooks, ⏰ schedulers (GitHub Actions / cron) - 🔌 MCP connectors and 🗄️ memory / state stores drawn as distinct node types - 🚨 Pipeline lints: broken delegation references, duplicate agent names, circular delegation, orphan skills, reviewers with write access, orchestrators missing the Task tool, vague trigger descriptions
1. Paste a GitHub repo (owner/repo, full URL, or a /tree/branch/subfolder link) and hit VISUALIZE 2. Upload a ZIP (GitHub → Code → Download ZIP) — fully offline 3. Upload a folder — point it at any local clone 4. Or click LOAD DEMO HARNESS to explore a sample multi-agent
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/oyekamal--claude-code-flow-visualizer.html)
The task tracker your AI agents keep for each other: every task carries a case file, so the next agent picks up where the last one stopped. MCP server + live board. Self-hosted, one-line install.
zriyox/codex-supervisor-mcpCodex MCP server: run parallel Codex CLI workers in isolated git worktrees, state on disk, web dashboard, auto-update.
00200200/usagetrimKeep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
nettanvirdev/inertiainertia-ai: a desktop workspace for AI agents. Chat, built-in tools, MCP and OpenAPI integrations, Docker/Daytona sandboxes with a live desktop, routines and memory. Bring your own model and keys.
luckeyfaraday/frontier-orchestratorMulti-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi
LarryStanley/pi-delegateDelegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.