yoanwai/agent-manager/agent-manager
Claude Code and agent skill by yoanwai/agent-manager
- community
Checking that the SKILL.md file is still in the repository.
Run a fleet of AI coding agents as live tmux sessions with agent-manager. Use when a developer is running more than one coding agent, needs to see which one is working or blocked, wants to spawn another on an independent task, or wants to review an agent's diff without leaving the terminal.
Install
npx vskill@latest install yoanwai/agent-manager/agent-managerSKILL.md
Run a fleet of coding agents with agent-manager
agent-manager is a single Go binary on top of tmux. Every row in its list is a real tmux session running a real coding CLI: the developer's own installation, login, config and MCP servers. It never wraps or re-implements an agent; it reads the same pane a human would and colours the row by what that pane is doing.
When to use this
- The developer is running more than one coding agent and cannot tell which is blocked.
- They want to spawn an agent on an independent task without losing the one already running.
- They want an agent's conversation to survive a crash, a reboot, or a closed terminal.
- They want to review a diff and send line comments back into the agent's prompt.
Do not reach for it to replace a coding CLI. It starts the CLIs that are already installed.
Install
macOS and Linux, amd64 and arm64. Windows runs it inside WSL2. Needs tmux 3.1+ and git.
Other routes: the install script, the AUR (yay -S agent-manager-bin), mise use -g ubi:YoanWai/agent-manager, go install github.com/YoanWai/agent-manager@latest, or a prebuilt binary from the releases page.
The keys that matter
| Key | What it does | |
|---|---|---|
space | Opens quick prompt mode, a prompt bar docked in the footer. On a group row it spawns a new agent with that prompt; on a session row it answers the agent already running there. | |
tab / alt+m | Cycles which CLI the next spawn starts. | |
shift+tab | Steps the CLI back one. | |
ctrl+l / ctrl+x / ctrl+y | Picks the spawn's model, reasoning effort and profile from the ones the CLI reports. | |
ctrl+g | Steps the environment profile the spawn launches under, starting from the target group's. | |
ctrl+t / alt+w | Toggles spawning the agent into a fresh git worktree and branch. | |
ctrl+r | Opens a full-screen whole-file diff whose line comments go back to the agent as one review prompt. | |
v | Revives a dead session on the conversation it held. | |
y | Copies the selected session's newest reply to the system clipboard, without attaching. |
Status colours
A row is coloured working, waiting, finished, idle or errored. Claude Code reports through hook events; every other CLI is read from its pane with regexes. Twelve CLIs ship with working profiles: Claude Code, OpenCode, Codex, Grok Build, Gemini CLI, Antigravity CLI, Pi, Command Code, Hermes Agent, Muse Code, Oh My Pi and Cursor CLI. Every profile ships in the binary, so an upgrade brings the current rules for all of them. A CLI outside that list is a feature request, and the CLIs row in Settings ends with request CLI support, which opens one prefilled.
Driving it from inside an agent
Sessions of MCP-capable CLIs carry agent-manager's own MCP server over stdio, so an agent can create_session to spawn a peer, send_session to message one, wait_for_session to block on one, task to claim shared work, and reserve_files to declare what it is editing.
Reference
- Documentation: https://agent-manager.dev/docs/
- Every page as Markdown: https://agent-manager.dev/llms.txt
- Reference API: https://agent-manager.dev/openapi.json
- Documentation MCP server: https://agent-manager.dev/mcp
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/agent-manager/SKILL.md
Popularity
- Repository stars
- 496
- Repository forks
- 51
- 7-day trend score
- 31
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/yoanwai/agent-manager/agent-manager)