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.
npx skills add rondorkerin/gamestack --skill art-direction-and-readabilitygit clone --depth 1 https://github.com/rondorkerin/gamestackWrote 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/skills/rondorkerin/gamestack/art-direction-and-readability)<a href="https://agentmods.dev/skills/rondorkerin/gamestack/art-direction-and-readability"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/art-direction-and-readability/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/skills/rondorkerin/gamestack/art-direction-and-readability"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/art-direction-and-readability.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 | $0.00111 | $0.00648 |
| Opus 5 | $0.00056 | $0.00324 |
| Sonnet 5 | $0.00022 | $0.00130 |
| Haiku 4.5 | $0.00011 | $0.00065 |
Grade A, and why
art-direction-and-readability 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 11d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Art Direction & Readability
How to make a game read — so the player can instantly answer the gameplay questions the scene poses (friend or foe? safe to touch? where do I go?) — and how an AI content engine holds one coherent visual language across thousands of generated pieces. This is the design discipline of visual communication, not asset production.
When to use this
- Setting a project's visual direction (stylization vs. fidelity, reference set, palette)
- Auditing a scene, character, or generated asset for readability
- Designing or policing a signal-color language
- Giving an AI generator a checkable "house style" and per-asset read contract
Scope
This skill owns visual communication at the design level. Adjacent concerns live in siblings:
- Where landmarks/signal-color sit in space →
open-world-design - What gets generated and its sameness problem →
procedural-generation,procgen-review - Coherence of generated text/lore (the non-visual analogue) →
ai-authored-content-coherence - General feedback/clarity theory →
game-design-fundamentals
How the pieces fit
GUIDE.md— the why, with exemplars and citations. Sections 1–6 are verification-confirmed (Team Fortress 2 primary sources, adversarially checked 3-0). Sections 7+ are sourced but unverified — see the verification banner in the guide.CHECKLIST.md— the what to do: Do/Don't plus "Test for" criteria you can run against a scene, a character, or a generated asset.
The one idea to anchor on
Readability is an engineerable requirement, not a taste call. Every visual element should be able to name the gameplay question it answers; one that answers none is decoration competing with the ones that do. Order of priority: readability first, personality second, fidelity never.
⚠️ Verification note: This skill was built from a deep-research pass whose adversarial-verification phase was cut short by a session limit. The TF2-grounded core (GUIDE §1–6) is confirmed; the signal-color case studies (BotW, Mirror's Edge, Naughty Dog/yellow-paint) are sourced but not verification-confirmed. Treat the latter as strong defaults to re-verify, not settled fact.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 37 lines · 111 tokens per session scan A e3ea8a3915f0
art-direction-and-readability is a skill published in the GitHub repository rondorkerin/gamestack (28 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 648 once invoked, about $0.0006 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 skills, from other repositories
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
architecture-review
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL…
localize
Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.
vertical-slice
Pre-Production validation — build a production-quality end-to-end build to confirm the full game loop is achievable before committing to Production. Run after GDDs, architecture, and UX specs are complete. Produces a PROCEED/PIVOT/KILL verdict that gates the Pre-Production → Production transition.
quick-design
Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full GDD authoring when a system GDD already exists or the change is too small to warrant one. Produces a Quick Design Spec that embeds directly into story files.
day-one-patch
Prepare a day-one patch for a game launch. Scopes, prioritises, implements, and QA-gates a focused patch addressing known issues discovered after gold master but before or immediately after public launch. Treats the patch as a mini-sprint with its own QA gate and rollback plan.