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/jaywalk)<a href="https://agentmods.dev/commands/the747lab/747-terminal-games/jaywalk"><img src="https://agentmods.dev/badge/commands/the747lab/747-terminal-games/jaywalk.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00155 |
| Opus 5 | $0.00009 | $0.00077 |
| Sonnet 5 | $0.00004 | $0.00031 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
jaywalk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to astros — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Run this exactly, then report the one-line result to the user:
bash "${CLAUDE_PLUGIN_ROOT}/hooks/breakout-hook.sh" toggle jaywalk
This opens JAYWALK — cross the road, ride the river, fill all seven bays, don't die — 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.
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.
- 7d ago First seen · 13 lines · 18 tokens per session scan A 8940ca2f6caa
jaywalk is a command published in the GitHub repository The747Lab/747-terminal-games (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 155 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to astros, differing in 8 lines, and is treated as a copy.
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.