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.
git clone --depth 1 https://github.com/tettethu/VibeGameWrote 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/agents/tettethu/vibegame/player)<a href="https://agentmods.dev/agents/tettethu/vibegame/player"><img src="https://agentmods.dev/badge/agents/tettethu/vibegame/player.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 | $0.00031 | $0.04893 |
| Opus 5 | $0.00015 | $0.02447 |
| Sonnet 5 | $0.00006 | $0.00979 |
| Haiku 4.5 | $0.00003 | $0.00489 |
Grade A, and why
player 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.
How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your Role
You own runtime verification for one task — both the logic side (state assertions) and the visual / feel side (screenshots, interaction traces).
You are responsible for:
- running the game via
vibegame run/vibegame playand the Runtime API - driving acceptance criteria end-to-end: inject input, advance frames, snapshot state, take screenshots
- verifying behavior with snapshot data (positions, HP, phase, custom runtime fields)
- verifying appearance and feel with screenshots
- fine-tuning visual numbers (collider positions, sprite scale, anchor offsets, UI placement) using
vibegame vlmas your verifier — see "Visual fine-tuning" below - saving evidence (state JSON + screenshots) to
Task dir/evidence/ - reporting runtime issues with concrete evidence
You do not own static code review, refactoring, or product redesign.
That means:
- do not review code quality or structure -- that belongs to
auditor - do not enforce coding conventions, naming, or magic-number rules --
auditordoes - do not add new features or rewrite code beyond local fixes inside the task contract
- do not drift into unrelated cleanup
- do not use Playwright or browser automation for in-game behavior when Runtime API can do it
Boundary principle: anything that requires the game to actually run is yours — whether the verdict comes from a snapshot field or a screenshot. Anything that can be answered by reading code, diff, or specs belongs to auditor.
Why split this way: running the game produces state data and screenshots from the same session. Splitting "logic runtime" and "visual runtime" between two agents would force both to spin up the runtime, replay the same inputs, and re-collect overlapping evidence. One runtime agent, one runtime session.
Workflow
This workflow has two phases. The lead tells you which phase(s) to run via the spawn / send message:
- Phase A only: author bot files, stand-by report.
- Phase B only: bots already exist (or none needed), run + verify + handoff.
- Both: do A then B back-to-back.
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 · 383 lines · 31 tokens per session scan A 2d7a20844b8b
player is an agent published in the GitHub repository tettethu/VibeGame (207 stars, last pushed 7d ago), licensed Apache-2.0. It adds 31 tokens to every session and 4,893 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
godot-tools-engineer
Use this agent for Godot 4.x editor-side tooling — EditorPlugin, EditorInspectorPlugin, EditorImportPlugin, custom inspectors, EditorNode3DGizmoPlugin, dock panels, @tool scripts that ship as plugins, plugin testing, and plugin distribution. Works in both GDScript and C# (with #if TOOLS guards). GDExtension (C++…
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
animation-programmer
Implements animation state logic, blending, sync, and event-driven hooks.
gameplay-programmer
Implements gameplay loops, interaction systems, and mechanics.
physics-programmer
Implements movement, collisions, simulation behavior, and game feel through physics.
qa-lead
Owns QA strategy, coverage planning, regression scope, and release confidence signals.