By tombelieber
Adds a web dashboard and MCP tools for monitoring Claude Code sessions, tracking costs, analyzing usage patterns, generating standup reports, and managing team activity — all accessible via slash commands like /session-recap, /daily-cost, and /standup.
Use when the user asks about improving their Claude Code usage, coaching rules, or best practices — e.g. 'how can I improve', 'coaching tips', 'my coaching rules', 'add a coaching rule'
Use when the user asks about cost, spending, or budget — e.g. 'how much did I spend today', 'daily cost', 'cost report', 'what's my spend'
Use when the user wants to export session data — e.g. 'export my sessions', 'download data', 'export to CSV', 'get my data'
Use when the user asks about patterns, insights, or behavioral analysis — e.g. 'what patterns do you see', 'insights', 'how am I doing', 'behavioral analysis'
Use when the user asks about a specific project or all projects — e.g. 'show me project X', 'project overview', 'what projects do I have', 'project summary'
Admin access level
Server config contains admin-level keywords
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.
Mission Control for Claude Code
You have 10 AI agents running. One finished 12 minutes ago. Another hit its context limit. A third needs tool approval. You're Cmd+Tab-bing through terminals, burning $200/mo blind.
English · 繁體中文 · 简体中文 · 日本語 · Español · Français · Deutsch · Português · Italiano · 한국어 · Nederlands
curl -fsSL https://get.claudeview.ai/install.sh | sh
One command. Every session visible. Real-time.
claude-view is an open-source dashboard that monitors every Claude Code session on your machine — live agents, past conversations, costs, sub-agents, hooks, tool calls — in one place. Rust backend, React frontend, ~10 MB binary. Zero config, zero accounts, 100% local.
50+ releases. 85 MCP tools. 9 skills. One npx claude-view.
See every running session at a glance. No more terminal tab-switching.
| Feature | What it does |
|---|---|
| Session cards | Each card shows the last message, model, cost, and status — instantly know what every agent is working on |
| Multi-session chat | Open sessions side-by-side in VS Code-style tabs (dockview). Drag to split horizontally or vertically |
| Context gauge | Real-time context window fill per session — see which agents are in the danger zone before they hit the limit |
| Cache countdown | Know exactly when prompt cache expires so you can time messages to save tokens |
| Cost tracking | Per-session and aggregate spend with token breakdown — hover for input/output/cache split by model |
| Sub-agent tree | See the full tree of spawned agents, their status, costs, and what tools they're calling |
| Notification sounds | Get pinged when a session finishes, errors, or needs your input — stop polling terminals |
| Multiple views | Grid, List, Kanban, Monitor, or Harness mode — pick what fits your workflow |
| Kanban swimlanes | Group sessions by project or branch — visual swimlane layout for multi-project workflows |
| Recently closed | Sessions that end appear in "Recently Closed" instead of vanishing — persists across server restarts |
| Queued messages | Messages waiting in the queue show as pending bubbles with a "Queued" badge |
| SSE-driven | All live data pushed via Server-Sent Events — eliminates stale-cache risks entirely |
Read, search, and interact with any session — live or historical.
npx claudepluginhub tombelieber/claude-viewBack up and restore your Claude Code environment
Kill orphan dev processes left by AI agent sessions
Real-time session dashboard for Claude Code — cost tracking, analytics, and smart alerts
Tracks Claude Code session usage (tokens, costs, skills, MCP, subagents) and sends data to a self-hosted dashboard.
Live TUI dashboard for monitoring all active Claude Code sessions, status, context usage, tokens, and latest messages at a glance.
Live multi-session dashboard for Claude Code — real-time visibility and control over every Claude Code session from a browser
A comprehensive statusline dashboard for Claude Code — session summary, quota bars, agent tracker, MCP health, message history, and more. All at a glance, no slash commands needed.
Observability platform for Claude Code and Agent SDK — monitor, debug, and control AI coding agents