agent-manager

agent-manager is a skill for Claude Code, Codex from YoanWai/agent-manager. It costs 63 tokens per session (861 once invoked), scanned A, original, Apache-2.0.

A terminal dashboard for running multiple AI coding agents in separate tmux sessions. It shows each session's current activity and keeps it available after a closed terminal or restart.

In plain words
What is it for?
Run agents on independent coding tasks, check which are working or blocked, start another session, and review an agent's code changes with line comments.
Why use it?
It removes the need to track several agents in separate terminal windows or guess which one is stuck. It also keeps their conversations available through crashes, reboots, or closed terminals.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/yoanwai/agent-manager/agent-manager
Any agent
npx skills add YoanWai/agent-manager --skill agent-manager
Clone the repo
git clone --depth 1 https://github.com/YoanWai/agent-manager

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/yoanwai/agent-manager/agent-manager.svg)](https://agentmods.dev/skills/yoanwai/agent-manager/agent-manager)
Your own site
<a href="https://agentmods.dev/skills/yoanwai/agent-manager/agent-manager"><img src="https://agentmods.dev/badge/skills/yoanwai/agent-manager/agent-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 861 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.00861
Opus 5 $0.00032 $0.00430
Sonnet 5 $0.00013 $0.00172
Haiku 4.5 $0.00006 $0.00086

Measured 5d ago against content hash b47516a1fef0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agent-manager/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 yoanwai/tap/agent-manager

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 Docks a prompt bar. On a group row it spawns a new agent with that prompt; on a session row it answers the agent already running there.
tab Cycles which CLI the next spawn starts.
alt+w Spawns 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.

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 74 lines · 63 tokens per session scan A b47516a1fef0

Subscribe to this mod's changes

agent-manager is a skill published in the GitHub repository YoanWai/agent-manager (391 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 861 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

cua-driver

Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…

QwenLM/qwen-code · 88 tokens

verify-pr

This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…

QwenLM/qwen-code · 89 tokens

codegraph

Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…

QwenLM/qwen-code · 0 tokens

stuck

Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.

QwenLM/qwen-code · 57 tokens

tmux-real-user-testing

This skill should be used when the user asks to "用 tmux 做真实测试", "保存 tmux 日志", "像真实用户一样测试 Qwen", "生成可复查的 TUI 测试报告", "测试 slash command 交互", or requests a tmux-based real user E2E run with complete readable logs. It guides real TUI usage with step-by-step capture-pane snapshots rather than ANSI raw pipe logs.

QwenLM/qwen-code · 98 tokens

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens