sandboxer-tmuxDispatch coding tasks to tmux sessions via Sandboxer. Use when you need to spawn Claude Code, Gemini, OpenCode, bash, or lazygit sessions in workspace repos, monitor their progress, or send them commands.
Install via ClawdBot CLI:
clawdbot install chriopter/sandboxer-tmuxPower-user skill. Sandboxer gives agents full access to tmux sessions, workspace files, and terminal output on your server. Intended for dedicated AI machines where agents run with root access. Not for shared or untrusted environments.
Sandboxer runs on localhost:8081. No auth needed from localhost.
# 1. Spawn a Claude session in a repo
curl "localhost:8081/api/create?type=claude&dir=/root/workspaces/AGENT/data/repos/PROJECT"
# 2. Send it a task
curl "localhost:8081/api/send?session=SESSION_NAME&text=Fix+the+failing+tests"
# 3. Check progress
curl "localhost:8081/api/session-monitor?session=SESSION_NAME"
# 4. Kill when done
curl "localhost:8081/api/kill?session=SESSION_NAME"Session types: claude, bash, lazygit, gemini, opencode
Sandboxer manages /root/workspaces/ ā a single git repo containing all agent workspaces.
/root/workspaces/ ā git repo (Sandboxer commits this)
āāā .gitignore ā tracks only .md, .gitignore, cronjobs/
āāā <agent-name>/ ā one folder per OpenClaw agent
ā āāā AGENTS.md ā agent behavior rules
ā āāā SOUL.md, USER.md, TOOLS.md ā agent identity & config
ā āāā MEMORY.md ā curated long-term memory
ā āāā TODO.md ā workspace task list (P1/P2/P3)
ā āāā CLAUDE.md ā coding rules for this workspace
ā āāā memory/YYYY-MM-DD.md ā daily memory logs
ā āāā cronjobs/ ā cron configs (tracked by git)
ā āāā data/
ā āāā repos/ ā software projects (git clones)
ā āāā <project-a>/ ā separate git repo
ā ā āāā CLAUDE.md ā project-specific coding rules
ā ā āāā ...source code...
ā āāā <project-b>/data/repos/ contains separate git repos ā each project has its own .git, branches, remotes.gitignore excludes data/ ā repo contents stay in their own git, not the workspace commit.md files, .gitignore, and cronjobs/| Endpoint | What |
|----------|------|
| GET /api/sessions | List all sessions (status: running/idle/done/error) |
| GET /api/create?type=T&dir=D | Spawn session |
| GET /api/session-monitor?session=S | Last 20 lines + status + duration |
| GET /api/capture?session=S | Full terminal output |
| GET /api/send?session=S&text=T | Send keystrokes |
| GET /api/forward?session=S&task=T | Ctrl+C then send task |
| GET /api/kill?session=S | Kill session |
| GET /api/workspaces | List workspaces (with repos) |
| GET /api/workspace-repos?workspace=W | List repos in workspace |
| GET /api/repo-tree?path=P | Repo file tree with git status |
| GET/POST /api/workspace/W/file/PATH | Read/write workspace files |
| POST /api/auto-commit?workspace=W | Commit workspace changes |
POST /api/create accepts JSON body with notify_url ā gets called when session finishes.
Generated Mar 1, 2026
A development team uses Sandboxer to spawn Claude Code sessions in project repos to automatically review pull requests, run tests, and apply fixes. The agent monitors sessions via the API, captures output, and commits changes to workspace files, streamlining CI/CD pipelines.
In a DevOps environment, Sandboxer dispatches bash sessions to manage server configurations, deploy updates, and monitor cronjobs. Agents automate routine tasks by sending commands, checking progress, and killing sessions post-completion, reducing manual intervention.
A research lab employs multiple AI agents (e.g., Claude, Gemini) via Sandboxer to work concurrently on different parts of a codebase. Each agent runs in its own tmux session, with the system coordinating tasks, merging outputs, and tracking changes in workspace git for collaborative projects.
Teams use Sandboxer to spawn lazygit sessions for automated branch management, conflict resolution, and repository synchronization. Agents monitor session status, forward tasks, and commit workspace changes, ensuring version control is handled efficiently without human oversight.
In a production AI system, Sandboxer creates sessions for tasks like data processing or model training, with agents using the session-monitor and capture APIs to track progress. Notify_url in POST /api/create triggers alerts upon completion, enabling proactive management.
Offer Sandboxer as a cloud service where teams subscribe to automate coding, testing, and deployment tasks. Revenue comes from tiered pricing based on session limits, workspace size, and API usage, targeting enterprises seeking to reduce development costs.
Provide expert services to integrate Sandboxer into existing workflows, customizing sessions and APIs for specific industries like finance or healthcare. Revenue is generated through project-based fees and ongoing support contracts, leveraging the skill's advanced capabilities.
Distribute Sandboxer as open-source software with a free community edition, while offering enterprise licenses for enhanced features like advanced security, priority support, and SLA guarantees. Revenue streams include licensing fees and premium add-ons.
š¬ Integration Tip
Ensure the server running Sandboxer is secured and isolated, as it requires root access and operates without authentication on localhost, making it suitable only for trusted, dedicated environments.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.