sandboxer
Manage Claude Code terminal sessions via Sandboxer web dashboard. Use when: (1) listing running Claude Code sessions, (2) checking what a Claude session is doing, (3) sending commands to a Claude session, (4) creating or killing sessions, (5) user mentions 'sandboxer' or 'session'.
Best use case
sandboxer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Manage Claude Code terminal sessions via Sandboxer web dashboard. Use when: (1) listing running Claude Code sessions, (2) checking what a Claude session is doing, (3) sending commands to a Claude session, (4) creating or killing sessions, (5) user mentions 'sandboxer' or 'session'.
Teams using sandboxer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/sandboxer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How sandboxer Compares
| Feature / Agent | sandboxer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Manage Claude Code terminal sessions via Sandboxer web dashboard. Use when: (1) listing running Claude Code sessions, (2) checking what a Claude session is doing, (3) sending commands to a Claude session, (4) creating or killing sessions, (5) user mentions 'sandboxer' or 'session'.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Sandboxer
Manage Claude Code sessions running in tmux via HTTP API.
**All commands run locally - no SSH needed.**
## Health Check (Run First!)
Before using any commands, verify Sandboxer is running:
```bash
curl -sf http://localhost:8081/api/sessions >/dev/null && echo "✓ Sandboxer is running" || echo "✗ Sandboxer not reachable"
```
**If Sandboxer is not reachable:**
```
✗ Sandboxer is not installed or not running on this machine.
To install Sandboxer, run:
claude --dangerously-skip-permissions "clone github.com/chriopter/sandboxer to /home/sandboxer/git/sandboxer, read README.md for install instructions, then install sandboxer"
To start if already installed:
sudo systemctl start sandboxer
See: https://github.com/chriopter/sandboxer
```
## List Sessions
```bash
curl -s http://localhost:8081/api/sessions | jq
```
Filter by project:
```bash
curl -s http://localhost:8081/api/sessions | jq '.[] | select(.name | contains("PROJECT"))'
```
## Read Session Output
See what Claude is doing:
```bash
tmux capture-pane -t "SESSION_NAME" -p | tail -80
```
## Send Command to Session
Forward user requests to Claude Code:
```bash
tmux send-keys -t "SESSION_NAME" "implement feature X" Enter
```
Then wait 10-30s and read output to check result.
## Create Session
```bash
curl -s "http://localhost:8081/create?type=claude&dir=/path/to/project"
```
Types: `claude`, `bash`, `lazygit`
## Kill Session
```bash
curl -s "http://localhost:8081/kill?session=SESSION_NAME"
```
## Workflow: Forward Tasks to Claude
When user says "do X" or "implement Y":
1. Find the right session: `curl -s http://localhost:8081/api/sessions | jq`
2. Send command: `tmux send-keys -t "SESSION" "do X" Enter`
3. Wait 10-30 seconds
4. Read result: `tmux capture-pane -t "SESSION" -p | tail -80`
5. Report back to user
## Web Dashboard
URL: `https://YOUR_SERVER:8080`
Shows live terminal previews. May require password.
## Installation
See [GitHub README](https://github.com/chriopter/sandboxer#install) for setup instructions.Related Skills
sandboxer-tmux
Dispatch coding tasks to tmux sessions via Sandboxer.
paylock
Non-custodial SOL escrow for AI agent deals.
agent-reputation
summary: Cross-platform AI agent reputation checker with trust scoring and PayLock escrow recommendations.
Telecom Agent Skill
Turn your AI Agent into a Telecom Operator. Bulk calling, ChatOps, and Field Monitoring.
OpenClaw-Finnhub
OpenClaw skill for real-time stock quote, and financials via Finnhub API.
```markdown
# OpenClaw-Last.fm
security-operator
Runtime security guardrails for OpenClaw agents.
operator-humanizer
Transform AI-generated text into authentic human writing.
kit-email-operator
**AI-powered email marketing for Kit (ConvertKit)**.
agora
Trade prediction markets on Agora — the prediction market exclusively for AI agents. Register, browse markets, trade YES/NO, create markets, earn reputation via Brier scores.
surf-check
Surf forecast decision engine.
jinko-flight-search
Search flights and discover travel destinations using the Jinko MCP server. Provides two core capabilities: (1) Destination discovery — find where to travel based on criteria like budget, climate, or activities when the user has no specific destination in mind, and (2) Specific flight search — compare flights between two known cities/airports with flexible dates, cabin classes, and budget filters. Use this skill when the user wants to: search for flights, find cheap flights, discover travel destinations, compare flight prices, plan a trip, find deals from a specific city, or explore where to go. Triggers on any flight-booking, travel-planning, or destination-discovery request. Requires the Jinko MCP server connected at https://mcp.gojinko.com.