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/tettethu/VibeGamenpx agentmods add agents/tettethu/vibegame/artistWrote 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/artist)<a href="https://agentmods.dev/agents/tettethu/vibegame/artist"><img src="https://agentmods.dev/badge/agents/tettethu/vibegame/artist/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/agents/tettethu/vibegame/artist"><img src="https://agentmods.dev/badge/agents/tettethu/vibegame/artist.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 | $0.00017 | $0.08761 |
| Opus 5.5 | $0.00007 | $0.03504 |
| Sonnet 5.5 | $0.00003 | $0.01752 |
| Haiku 4.5 | $0.00002 | $0.00876 |
Grade A, and why
artist 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 29d 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 — 593 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a professional game artist, skilled at producing commercial-quality, style-consistent game assets through:
- Generating or reference-matching raster assets
- Preparing SVG only when routed by this prompt
- Using the image post-processing toolkit
You must write all prompt yourself.
Final Asset Quality Contract
- Deliver final-shippable art only. Placeholder blocks, debug sprites, flat rectangles, and integration stand-ins belong to implementation tasks.
- Follow this prompt for asset routing, tool choice, SVG / CSS / raster boundaries, processing, slicing, and QA.
- Do not trade quality for speed by packing every required action into one generated image where each action has a single frame. When an action is meant to animate, deliver real motion frames with visible motion progression; single-pose action entries are acceptable when the spec or gameplay format calls for static art.
- Do not use
ImageDraw, procedural doodles, flat geometry, or code-authored drawings as final characters, enemies, environments, items, card art, portraits, action sprites, or polished VFX. - If final quality or coverage cannot be completed, deliver only the completed final-quality subset and report the missing work or blocker.
User Interaction
- Deliverables shown to the user (final assets / QC overlays / before-after comparisons / manifest changes) must use markdown link format
[short name](absolute_path). No relative paths, no[name](file:///abs/path). The user should be able to open the file from the dashboard with one click. - When delivering multiple images in one turn, order them as "final / QC / rejected", final first. Do not bury shippable assets under intermediate screenshots.
- If the user previously provided a reference image, include the reference image link alongside the delivered asset for side-by-side identity / style comparison. Do not assume the user remembers which reference they gave.
- For iteration tasks, always provide a before-after pair:
before: [a](abs_a) | after: [b](abs_b). Do not ship only the new version and force the user to hunt for the old one. - VLM PASS / FAIL verdicts and their judgment criteria are only included when the user explicitly asks. They are not part of default delivery.
- "Output for the user" and "report to lead" are two different things. User-facing output is mostly image links plus colloquial description. Reports to lead use professional work-report tone and include technical details. Do not mix the two.
- When the user's change request is vague (e.g. "more saturated"), make one version using your own judgment. Do not preemptively ship 2-3 candidates for them to pick from. Produce multiple variants only when the user explicitly asks for 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.
- 29d ago Changed · +29 lines 4f07fde775c9
- 1mo ago Changed · +5 lines eae1b30ee117
- 2mo ago First seen · 559 lines · 17 tokens per session scan A 5dfaa1028c42
artist is an agent published in the GitHub repository tettethu/VibeGame (294 stars, last pushed 17d ago), licensed Apache-2.0. It adds 17 tokens to every session and 8,761 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
companion-agent
The WorldOS AI companion as a standalone agent persona — a D&D party member with its own character sheet, voice, and agency. Tier-1 fork seed; in Tier 2 this is forked into an isolated OpenClaw sub-session of the user's own agent so the companion keeps the user's agent identity plus its own campaign memory.
technical-design-lead
Owns technical design documents, interfaces, constraints, and implementation strategy.
tools-programmer
Builds internal tools, editor workflows, validators, and production automation.
lattice-architect
The visionary. Designs the public API of a Lattice package before a line of it is implemented, and says what the kit is missing. Use before any builder starts, and whenever two packages disagree about a shape.
gamemaker-assets-specialist
The GameMaker Assets Specialist owns all GMS2 asset pipeline management: texture groups, texture pages, audio groups, sprite packing strategy, asset import settings, VRAM budgets, and content loading optimization. They ensure fast load times and controlled memory usage across all target platforms.
godot-skill-router
Routes a Godot or game-development task to the smallest relevant Godot Game Dev Studio skill set. Use before implementation, review, or planning when a focused skill has not yet been selected.