Agtx Task Sweep
fynnfluegge/agtx
Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.
Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.
Install Agent Manager Fleet TUI
$ npx skills add YoanWai/agent-manager --skill agent-manager -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install YoanWai/agent-manager agent-manager --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/YoanWai/agent-manager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-manager .claude/skills/agent-manager && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-manager" agent skill from https://github.com/YoanWai/agent-manager/tree/main/skills/agent-manager into .claude/skills/agent-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-manager", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/YoanWai/agent-manager/tree/main/skills/agent-managerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add YoanWai/agent-manager --skill agent-manager -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install YoanWai/agent-manager agent-manager --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YoanWai/agent-manager.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-manager .agents/skills/agent-manager && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-manager" agent skill from https://github.com/YoanWai/agent-manager/tree/main/skills/agent-manager into .agents/skills/agent-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-manager", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add YoanWai/agent-manager --skill agent-manager -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install YoanWai/agent-manager agent-manager --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YoanWai/agent-manager.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-manager .cursor/skills/agent-manager && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-manager" agent skill from https://github.com/YoanWai/agent-manager/tree/main/skills/agent-manager into .cursor/skills/agent-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-manager", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/YoanWai/agent-manager.git --path skills/agent-manager--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add YoanWai/agent-manager --skill agent-manager -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install YoanWai/agent-manager agent-manager --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YoanWai/agent-manager.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-manager .gemini/skills/agent-manager && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-manager" agent skill from https://github.com/YoanWai/agent-manager/tree/main/skills/agent-manager into .gemini/skills/agent-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-manager", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install YoanWai/agent-manager agent-managerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add YoanWai/agent-manager --skill agent-manager -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/YoanWai/agent-manager.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-manager .github/skills/agent-manager && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-manager" agent skill from https://github.com/YoanWai/agent-manager/tree/main/skills/agent-manager into .github/skills/agent-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-manager", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add YoanWai/agent-manager --skill agent-manager -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install YoanWai/agent-manager agent-manager --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YoanWai/agent-manager.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-manager .opencode/skills/agent-manager && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-manager" agent skill from https://github.com/YoanWai/agent-manager/tree/main/skills/agent-manager into .opencode/skills/agent-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-manager", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-manager- GitHub stars
- 576
- Token cost
- ~1k tokens
- SKILL.md length
- 480 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.
- Watching several coding agents at once to see which is blocked
- SKILL.md covers When to use this, Install, The keys that matter and Status colours, plus 2 more sections
- Calls brew
- Spawning a new agent on an independent task without losing another
What it does
This skill operates agent-manager, a single Go binary built on tmux where every row is a genuine tmux session running the developer's own coding CLI install, login, config and MCP servers - it starts and reads those CLIs rather than wrapping or reimplementing them. Eleven CLIs ship with working status profiles out of the box, including Claude Code, OpenCode, Codex and Gemini CLI; Claude Code reports status through hook events while the rest are read from their pane output with regular expressions.
From the terminal UI a prompt bar can spawn a new agent on a group row or answer one already running on a session row, cycle which CLI the next spawn starts and pick its model, reasoning effort and profile, toggle spawning into a fresh git worktree and branch, open a full-screen diff whose line comments go back to the agent as one review prompt, revive a dead session on the conversation it held, or copy an agent's newest reply to the clipboard without attaching to it.
It needs tmux 3.1 or later and git, runs on macOS and Linux natively and on Windows through WSL2, and is meant to sit alongside the coding CLIs already installed rather than replace any of them.
When your agent uses it
- Watching several coding agents at once to see which is blocked
- Spawning a new agent on an independent task without losing another
- Reviewing an agent's diff and sending comments back without leaving the terminal
Example prompts
- “Spawn a new Claude Code agent in a fresh worktree for the auth fix.”
- “Show me which of my running agents is currently blocked.”
- “Open the diff for the session on branch feature/search and leave comments.”
Requirements
- tmux 3.1+
- git
What it can do on your machine
Read from SKILL.md and the folder at commit cf9ed0d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
brew
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
agent-manager.dev
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Manager Fleet TUI loads about 1k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 480 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from YoanWai/agent-manager at commit cf9ed0d, republished under its Apache-2.0 licence (© YoanWai). 480 words, ~1,008 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-manager/SKILL.md (or your agent's skills folder).- name
- agent-manager
- description
- 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.
- license
- Apache-2.0
- homepage
- https://agent-manager.dev
- repository
- https://github.com/YoanWai/agent-manager
<!--
Why this skill exists: it packages the operating procedure for agent-manager (spawn,
status, answer-without-attaching, diff review) so an AI agent can install the knowledge
once instead of re-deriving it from the docs on every session. The site serves this file,
digest-sealed, at https://agent-manager.dev/skills/agent-manager/SKILL.md; the copy in
this repository is what makes it installable through skills.sh.
-->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.
brew install agent-managerOther 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+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. |
Show full SKILL.md (159 more words)Show less
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. Eleven
CLIs ship with working profiles: Claude Code, OpenCode, Codex, Grok Build, Gemini CLI,
Antigravity CLI, Pi, Command Code, Hermes Agent, Muse Code and Oh My Pi. 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
© YoanWai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/agent-manager of YoanWai/agent-manager.
Open the folder on GitHubat commit cf9ed0d
Compare with similar skills
Agent Manager Fleet TUI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Manager Fleet TUI this skillYoanWai/agent-manager | 576 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Agtx Task Sweepfynnfluegge/agtx | 1.7k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Orca CLIstablyai/orca | 87k | 2 repos | ~593 | Automated safety check: Pass | MIT | |
| Agent of Empires Session Manageragent-of-empires/agent-of-empires | 3.3k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Chrome Performance Optimizernwjs/chromium.src | 160 | — | ~4.2k | Automated safety check: Pass | BSD-3-Clause | |
| QAarcee-ai/nac | 280 | — | ~6.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Orca CLI
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
Agent of Empires Session Manager
agent-of-empires/agent-of-empires
Starts, monitors and organizes coding agent sessions that run in tmux through the aoe command, including groups, profiles and worktree-based parallel work.
Chrome Performance Optimizer
nwjs/chromium.src
Autonomous multi-agent performance optimization loop for Chromium and V8.
QA
arcee-ai/nac
Run scalable, isolated live QA for nac development. An agent skill from arcee-ai/nac.
MemPalace Task Handoff
MemPalace/mempalace
Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.
More from YoanWai/agent-manager
Agent-Manager Reference API
YoanWai/agent-manager
Looks up agent-manager.dev's own documentation, agents and MCP tools through its JSON API, Markdown pages and MCP server instead of scraping its marketing site.
Related
Works with
Categories
Questions about Agent Manager Fleet TUI
What does Agent Manager Fleet TUI do?
Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked. This skill operates agent-manager, a single Go binary built on tmux where every row is a genuine tmux session running the developer's own coding CLI install, login, config and MCP servers - it starts and reads those CLIs rather than wrapping or reimplementing them. Eleven CLIs ship with working status profiles out of the box, including Claude Code, OpenCode, Codex and Gemini CLI; Claude Code reports status through hook events while the rest are read from their pane output with regular expressions.
When should I use Agent Manager Fleet TUI?
Agent Manager Fleet TUI fits situations like: watching several coding agents at once to see which is blocked; spawning a new agent on an independent task without losing another; reviewing an agent's diff and sending comments back without leaving the terminal.
How do I install Agent Manager Fleet TUI in Claude Code?
Run `npx skills add YoanWai/agent-manager --skill agent-manager -a claude-code`. Or copy the skill folder (skills/agent-manager in YoanWai/agent-manager) into .claude/skills/agent-manager in your project. Claude Code loads it when a task matches its description.
How do I install Agent Manager Fleet TUI in Codex?
Run `npx skills add YoanWai/agent-manager --skill agent-manager -a codex`. Or copy the skill folder (skills/agent-manager in YoanWai/agent-manager) into .agents/skills/agent-manager in your project. Codex loads it when a task matches its description.
Can I use Agent Manager Fleet TUI in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add YoanWai/agent-manager --skill agent-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-manager, .gemini/skills/agent-manager, .github/skills/agent-manager and .opencode/skills/agent-manager in your project.
What does Agent Manager Fleet TUI need to run?
Going by SKILL.md and its folder, Agent Manager Fleet TUI needs the command-line tools its instructions call (brew). Our summary lists: tmux 3.1+; git.
Does Agent Manager Fleet TUI access the network?
SKILL.md names 1 domain. As links in the text: agent-manager.dev. This is read from the text; nothing was executed.
Is Agent Manager Fleet TUI safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agent Manager Fleet TUI use?
Agent Manager Fleet TUI is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Manager Fleet TUI use?
About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Agent Manager Fleet TUI?
Skills that share tags, products or a category with Agent Manager Fleet TUI: Agtx Task Sweep (fynnfluegge/agtx, 1.7k stars), Orca CLI (stablyai/orca, 87k stars), Agent of Empires Session Manager (agent-of-empires/agent-of-empires, 3.3k stars) and Chrome Performance Optimizer (nwjs/chromium.src, 160 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Manager Fleet TUI?
YoanWai (a GitHub user) maintains it in YoanWai/agent-manager, which has 576 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.
Source: YoanWai/agent-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.