by WenyuChiou
A local dashboard for AI agents that shows what each one is doing and which one is waiting on you. Works with Claude Code, Codex, Antigravity, Cursor, OpenCode, Grok Build and Hermes Agent. Runs on your computer, keeps everything in one Markdown file, no account.
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
# Add to your Claude Code skills
git clone https://github.com/WenyuChiou/agent-boardGuides for using ai agents skills like agent-board.
See how agent-board compares with popular alternatives.
You have Claude Code on one project, Codex on another and Antigravity on a third, and when one of them stops to ask you something, you only find out when you happen to switch back. Agent Board puts that question in front of you the moment it's asked, with a button for each answer. It runs on your computer and keeps everything in one Markdown file.
Major changes in 0.24.3. In an agent, /agent-board opens the live page ($agent-board in Codex); the plain terminal command below opens the terminal board or page. The live page replaces the old static HTML and the plain text board for people; Claude Code keeps its /progress pane. Agents use the JSON read (--json). Old board commands and --chat still work in this version; running setup again refreshes the installed commands. Send works where there is a delivery path; other surfaces can still require Copy.
With Node.js 22+, in any terminal:
npx @wenyuchiou/agent-board setup
npx @wenyuchiou/agent-board
The first command finds the agents on this computer, shows what setup would change, and asks once: Set these up? [Y/n]. A yes writes the files, approves the board's hooks in Codex and Hermes Agent, and installs the Claude Code plugin when Claude Code is on this computer; a no writes nothing. Without a terminal to answer in, such as in an agent's chat, setup only previews: setup --apply then writes the files and lists the approval and plugin commands to run yourself. The second command opens the live terminal board over SSH or in an interactive terminal without a display, and the page otherwise. In an agent's chat, /agent-board opens the same page. If nothing is set up yet, the second command alone asks the same question first. To stop the board's page, run npx @wenyuchiou/agent-board stop. To start the page without opening a browser window, add --no-open (npx @wenyuchiou/agent-board --no-open). For the shorter agent-board command, install it once with npm install -g @wenyuchiou/agent-board. To set up one agent only, add --agent and its name, such as --agent codex. To remove touched agent setups in one go, run npx @wenyuchiou/agent-board remove (or setup --remove); see Update and uninstall. More in the setup guide. An agent that needs the board's status reads agent-board --json; the Board JSON reference describes its versioned, redacted fields.
The board follows your system language when it is Traditional or Simplified Chinese, and English otherwise. To choose one, add --lang en, --lang zh-TW or --lang zh-CN to the setup command; the board, its page and stop then use it. An account connected through the Claude Code plugin uses /progress lang instead. A language picked in Settings on the board's page wins over both; its Automatic follows the system language.
Scan the QR code from npx @wenyuchiou/agent-board --lan with a phone on the same Wi-Fi. Use it only on a network you trust: the link is not encrypted and anyone who has it can open the page. Details: the board's page.
Then:
claude plugin marketplace add WenyuChiou/agent-board, then claude plugin install agent-board@agent-board./hooks (how).In the new session, open the board with its entry:
/agent-board$agent-board/agent-board (checked in a synthetic home, not run live yet)/agent-boardTo add a task of your own, write a ### title with - [ ] step lines in progress.md (a fresh install uses ~/.agent-board/progress.md; the format). With the Claude Code plugin, you can instead type + project: title; step; step in the pane's box, or /progress add … in Claude Code's chat.
To install from a clone of this repository instead, with Node.js 18+:
git clone https://github.com/WenyuChiou/agent-board.git
cd agent-board
node scripts/setup-agent.mjs
node scripts/setup-agent.mjs --apply
setup-agent.mjs takes the same options as npx @wenyuchiou/agent-board setup, such as --agent codex. On Windows, use the exact paths it prints. What each one writes: setup guide.
Paste this into the agent you already use:
Install Agent Board from https://github.com/WenyuChiou/agent-board on this computer.
Read its AGENTS.md, README and setup guide. Identify my current host and the other installed coding agents, then preview the common installer: node scripts/setup-agent.mjs.
Preserve existing settings and the shared progress path. Follow my approval requirements for persistent changes, then apply the applicable hooks, plugins and board command. Do not require or call another AI product to bootstrap this one.
Complete any required scoped host trust, read the settings back, and have this session report its own real task progress. Open the interactive board.
Verify actual hook events separately for CLI, desktop App and IDE. Installed files, transport acceptance and an ACK are different from a working progress connection.
Tell me which existing sessions need reload and which adapters remain unsupported or unverified. Never scan private conversations or silently skip a blocker.
| Agent | Board command | |
|---|---|---|
| Claude Code | /progress |
|
| Codex CLI and App | $agent-board |
|
| Antigravity | /agent-board (checked in a synthetic home, not run live yet) |
|
| OpenCode | /agent-board |
|
| Cursor | /agent-board (checked in a synthetic home, not run live yet) |
|
| Grok Build | /agent-board (checked in a synthetic home, not run live yet) |
|
| Muse Code | /agent-board (checked in a synthetic home, not run live yet) |
|
| Hermes Agent | /agent-board |
|
| OpenClaw | /agent-board |
|
| <img src="docs/images/agents/deepseek-ha |
agent-board is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by WenyuChiou. A local dashboard for AI agents that shows what each one is doing and which one is waiting on you. Works with Claude Code, Codex, Antigravity, Cursor, OpenCode, Grok Build and Hermes Agent. Runs on your computer, keeps everything in one Markdown file, no account. It has 50 GitHub stars.
agent-board's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/WenyuChiou/agent-board" and add it to your Claude Code skills directory (see the Installation section above).
agent-board is primarily written in TypeScript. It is open-source under WenyuChiou on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agent-board against similar tools.
No comments yet. Be the first to share your thoughts!