Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bitqs/Slime/plugin install slimeWrote 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/bitqs/slime/arena)<a href="https://agentmods.dev/commands/bitqs/slime/arena"><img src="https://agentmods.dev/badge/commands/bitqs/slime/arena/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/bitqs/slime/arena"><img src="https://agentmods.dev/badge/commands/bitqs/slime/arena.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 | $0.00011 | $0.00272 |
| Opus 5.5 | $0.00004 | $0.00109 |
| Sonnet 5.5 | $0.00002 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
Grade A, and why
arena scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Start the viewer server in the background if not already running (it also opens the browser), then relay the line it prints.
Run exactly this one line — it is the same on macOS, Linux and Windows (Git Bash, PowerShell or cmd); no lsof/nohup/Get-NetTCPConnection needed:
node "${CLAUDE_PLUGIN_ROOT}/scripts/arena-open.js"
(--no-open = don't open a browser; --calm = open the flash-free view.) It prints the live URL, or a clear failure if the server could not start — never claim the arena is live unless it printed the URL.
Show the user the printed line (e.g. "⚔️ Arena live — open http://127.0.0.1:4117").
- Stop it later — macOS/Linux:
kill $(lsof -ti :4117)· Windows:Stop-Process -Id (Get-NetTCPConnection -LocalPort 4117 -State Listen).OwningProcess
Flash-sensitive? Open http://127.0.0.1:4117/?calm=1 — flashes become fades, shake turns off.
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.
- 3d ago Changed · -6 lines 8e3fdaec0116
- 1mo ago First seen · 24 lines · 11 tokens per session scan A 1ab5cee06b92
arena is a command published in the GitHub repository bitqs/Slime (1 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 272 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
ia-test-browser
Run browser tests on pages affected by current PR or branch.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
restaurant-snipe
Schedule a future reservation to book at the exact release time (e.g. 10am sharp when Resy slots open).
adaptive-skills
Use the smallest relevant personal skill set for a game-dev task.
unity-agentic-workflow
Learn, audit, design, or bootstrap a professional Claude Code and Codex workflow for a Unity repository.
balance-check
Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.