- Home
- Skills
- Agents & Orchestration
- agentview-chat
Agentview Chat
Run Claude Code's background sessions from a chat UI, not a terminal
Free
Works with the AI Agents you already use
agentview-chat
Example session with this skill installed
I have 5 background tasks running and the terminal view is too messy. Can you set up Agent View Chat in C:\tools\agentview?
- Read your context and instructions
- Compiled the agentview-chat
I have verified your environment (Node.js v20.11.0, Git, and Claude Code are present) and successfully deployed Agent View Chat to C:\tools\agentview. The local server is now running and healthy.
Agent View Chat Deployment Report
| Component | Status | Detail |
|---|---|---|
| Install Path | Success | C:\tools\agentview |
| Dependencies | Installed | npm ci completed in 74s |
| Service Port | Active | 127.0.0.1:4790 |
| Health Check | Passed | App: agentview-chat |
| Session Sync | Active | 5 background sessions detected |
The application is now open in a window. You can see your 5 background tasks grouped by their current state on the left sidebar.
Next steps
- Use Ctrl+K to search through your active sessions by content.
- If a session shows a tool-permission request, click Open in terminal in the header to approve it.
- To start a new task without leaving the UI, press Ctrl+Shift+O.
Connects securely to your tools. The creator never sees your data.
About this skill
Claude Code's background sessions (claude --bg) are great for running several tasks in parallel — but the terminal agent view is a list of one-line summaries, and reading or replying means keyboard gymnastics in a terminal.
Agent View Chat is a free, open-source Windows app that turns that into a normal chat experience: sessions grouped by waiting / working / error / finished, conversations rendered with tables and code blocks, questions answered with a click, replies typed into a box, full-text search across sessions.
This skill walks your agent through installing Agent View Chat from its public GitHub repo, verifying it actually started, and giving you a 60-second tour — plus the operational know-how that bites everyone later: why a Task Scheduler task set to "run whether logged on or not" makes the daemon unreachable, why a session can look "working" after it stopped, and why replies take a few seconds (stop + resume on official commands, same session ID).
Windows only. Requires Node.js 20+ and a logged-in Claude Code.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Windows only. Does not show interactive sessions. Cannot handle tool-permission or plan approvals in-UI. Requires Node.js 20+.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
- Software
Node.js
Git