Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TheLobbi/claudenpx agentmods add commands/thelobbi/claude/playgroundWrote 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.
[](https://agentmods.dev/commands/thelobbi/claude/playground)<a href="https://agentmods.dev/commands/thelobbi/claude/playground"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/playground/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/thelobbi/claude/playground"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/playground.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.05176 |
| Opus 5.5 | $0.00006 | $0.02070 |
| Sonnet 5.5 | $0.00003 | $0.01035 |
| Haiku 4.5 | $0.00001 | $0.00518 |
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 1mo 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.
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' }, 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]
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.
- 1mo ago First seen · 770 lines · 14 tokens per session scan A 560c543c06cf
playground is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 5,176 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.
debug
Deep-dive artifact analysis for diagnosing E2E test failures.
aqe-chaos
Run chaos testing scenarios to validate system resilience and fault tolerance.
fix
Correction automatisee des bugs identifies par la QA Recette.
tdd
Correction de Bug en Mode TDD/BDD.
verify-loop
A command that repeatedly checks recent code changes and tries to fix failures, with a configurable retry limit. It can run code review, builds, tests, linting, and type checks according to the project language.