playground

playground is a command for Claude Code from TheLobbi/claude. It costs 14 tokens per session (5,176 once invoked), scanned A, original, MIT.

An interactive environment for debugging and developing AI agents through a WebSocket server. It supports execution control, breakpoints, variable inspection, and recording or replaying sessions.

In plain words
What is it for?
Use it to start a debugging server, run an agent, step through its code, inspect variables, and replay a recorded session.
Why use it?
It lets you pause an agent and inspect what it is doing instead of debugging only from final output or logs. Recorded sessions can be replayed to reproduce behavior.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the claude-orchestration plugin — 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins shipped together

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 commands/thelobbi/claude/playground
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins.

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 playground

README.md
[![agentmods](https://agentmods.dev/badge/commands/thelobbi/claude/playground.svg)](https://agentmods.dev/commands/thelobbi/claude/playground)
Your own site
<a href="https://agentmods.dev/commands/thelobbi/claude/playground"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/playground.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,176 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00014 $0.05176
Opus 5 $0.00007 $0.02588
Sonnet 5 $0.00003 $0.01035
Haiku 4.5 $0.00001 $0.00518

Measured today against content hash 560c543c06cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

playground scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

params: { command: 'curl http://localhost:8080' },
.claude/commands/playground.md · 770 lines

How it starts

The opening of the file, as written. The whole thing — 770 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Playground Commands

Interactive debugging environment for testing Claude agents with real-time execution control, breakpoints, variable inspection, and session recording/replay.

Quick Reference

/playground start [--port 8765]           # Start server
/playground stop                          # Stop server
/playground status                        # Check status
/playground execute <file> [options]      # Execute agent
/playground step [--session-id <id>]      # Step through code
/playground inspect <session> <var>       # Inspect variable
/playground replay <recording-id>         # Replay session

Core Commands

Server Management

/playground start [options]

Start the playground WebSocket server for interactive debugging.

Options:

  • --port <number> - Server port (default: 8765)
  • --host <string> - Server host (default: 0.0.0.0)
  • --max-connections <number> - Maximum concurrent connections (default: 100)
  • --heartbeat-interval <number> - Heartbeat interval in ms (default: 30000)
  • --no-cors - Disable CORS
  • --daemon - Run as background daemon
  • --db-path <string> - Database path for recordings (default: .playground/recordings.db)

Examples:

# Start playground on default port
/playground start

# Start on custom port
/playground start --port 9000

# Start with external access
/playground start --host 0.0.0.0 --port 8765

# Run as daemon with custom database
/playground start --daemon --db-path ./data/playground.db

Endpoints:

  • WebSocket: ws://localhost:8765/ws
  • Health: http://localhost:8765/health
  • Status: http://localhost:8765/status
/playground stop

Stop the running playground server.

/playground status [options]

Check the status of the playground server.

Options:

  • --port <number> - Server port (default: 8765)
  • --host <string> - Server host (default: localhost)
  • --verbose - Show detailed statistics

Agent Execution

/playground execute <agent-file> [options]

Read the full file on GitHub · 770 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. today First seen · 770 lines · 14 tokens per session scan A 560c543c06cf

Subscribe to this mod's changes

playground is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 5,176 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.