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 The747Lab/747-terminal-games/plugin install 747-terminal-gamesWrote 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/the747lab/747-terminal-games/breakin)<a href="https://agentmods.dev/commands/the747lab/747-terminal-games/breakin"><img src="https://agentmods.dev/badge/commands/the747lab/747-terminal-games/breakin/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/the747lab/747-terminal-games/breakin"><img src="https://agentmods.dev/badge/commands/the747lab/747-terminal-games/breakin.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 | $0.00016 | $0.00194 |
| Opus 5 | $0.00008 | $0.00097 |
| Sonnet 5 | $0.00003 | $0.00039 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
breakin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run this exactly, then report the one-line result to the user:
bash "${CLAUDE_PLUGIN_ROOT}/hooks/breakout-hook.sh" toggle breakout
This opens BREAK-IN — the endless ascent: crack the ceiling, thread the ball up through the hole, and climb into the chamber above, forever — in a tmux pane split in the current window (free-play, so it ignores Claude's thinking state), or closes it if it's already open. It requires the session to be running inside tmux. If it isn't, tell the user the game needs a tmux session and that the auto-launch-while-thinking still works without the manual toggle.
The title key stays breakout on purpose: it is the file name and the pane title, and renaming it would orphan any game already running in the background.
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.
- 8d ago First seen · 15 lines · 16 tokens per session scan A 981c0ffdafd7
breakin is a command published in the GitHub repository The747Lab/747-terminal-games (2 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 194 once invoked, about $0.0001 per session on Opus 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
companion-customize
Choose your own companion pet (species, rarity, eyes, hat).
status
Show game progress (no spoilers).
buddy
Manage BuddyBar pet status, statusline, mode, evolution, prestige, and self-check.
uw-cmd-implement-feature
Build a feature complete: interrogation -> TDD implementation -> game feel -> documentation — all in one pass.
uw-cmd-brainstorm
Transform a rough game idea into structured design document sections.
companion-review-log
Read the companion review log and show it to the user.