Claude Code Plugin
Spawn autonomous agents that run in the background.
Taskpilot launches long-running Claude Code sessions in tmux. Each task gets its own channel for real-time communication. Crash recovery built in.
Some tasks take hours. You shouldn't have to watch.
Research projects, monitoring jobs, multi-step workflows -- they need an agent that can run autonomously, report back, and recover from crashes without your intervention.
Taskpilot spawns each task in its own tmux session with a dedicated channel MCP. Send it an operating brief and walk away. Check status, send messages, or kill tasks from your main session.
/taskpilot:spawn
what should this agent do?
> research competitor pricing for B2B invoicing tools
creating task: competitor-pricing-research
allocating port 9102, registering channel...
agent spawned. running autonomously.
use /taskpilot:status to check progress.
How autonomous tasks work.
Create
Define the task with objectives, workflows, success criteria, and boundaries. An operating brief gives the agent everything it needs to work independently.
Spawn
Launches a tmux session running Claude with its own channel MCP. The initial prompt is posted to the channel. The agent starts working immediately.
Monitor
Check status dashboards, send messages, read logs. The agent writes state after each major action. On crash, it auto-respawns and picks up where it left off.
Capabilities declared in the operating brief are auto-resolved via softwaresoftware. The agent's instructions are dynamically generated.
Built for reliability.
Reboot persistence
Services (kind=service) get a systemd user service that auto-starts on boot. Agents survive reboots and come back up without intervention.
Crash recovery
Each tmux session has a respawn loop. If the agent crashes, it restarts automatically with context from its last saved state.
Real-time channels
Each task gets a unique port. Messages flow via HTTP POST, replies come back on SSE. Full bidirectional communication.
Capability auto-resolution
Declare capabilities in the operating brief. softwaresoftware resolves them to installed providers. The agent's CLAUDE.md is generated with the right sections.
Sandboxed environment
Each spawned agent runs in its own isolated $HOME -- not your daily-driver Claude config. No global CLAUDE.md, rules, personal skills, or MCPs leak in. The agent starts with a clean slate.
Per-task plugins
The caller picks exactly which plugins load for each task. Everything else stays installed but inert -- its skills and tools never reach the agent, keeping its context lean.
Persistent pane logs
Tmux pane output is teed to ~/.taskpilot/<id>/pane.log via tmux pipe-pane. Read agent history with get_task_log long after the session has ended. Soft size cap with head-truncation; configurable via TASKPILOT_PANE_LOG_MAX_BYTES.
SQLite + local storage
Task database, configs, and state files all live in ~/.taskpilot/. Everything on your machine, nothing in the cloud.
Install
Requires Claude Code, Python 3.11+, Node.js, and tmux.
Add the marketplace
claude plugin marketplace add softwaresoftware-dev/softwaresoftware-plugins
Run in your terminal.
Install the installer
claude plugin install softwaresoftware@softwaresoftware-plugins
Run in your terminal.
Launch Claude Code
claude
Start a new session so the installer is available.
Install taskpilot + dependencies
/softwaresoftware:install taskpilot
Run inside Claude Code. Run /reload-plugins when done.
Spawn your first agent
/taskpilot:spawn
Run inside Claude Code after reloading plugins.