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 frabcd/codex-ai-game-studio --skill visual-qagit clone --depth 1 https://github.com/frabcd/codex-ai-game-studioWrote 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/frabcd/codex-ai-game-studio/visual-qa)<a href="https://agentmods.dev/skills/frabcd/codex-ai-game-studio/visual-qa"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/visual-qa/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/frabcd/codex-ai-game-studio/visual-qa"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/visual-qa.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 | $0.00025 | $0.00464 |
| Opus 5 | $0.00013 | $0.00232 |
| Sonnet 5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
visual-qa 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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Qa
Outcome
Find visible and technical failures that single-view or file-only validation misses.
Required inputs
- asset, scene, or build under review
- reference target and acceptance criteria
- representative cameras, states, platforms, and budgets
Ask for missing information only when it changes the route materially. Otherwise state conservative assumptions and proceed with read-only analysis.
Workflow
- Confirm the comparison baseline, capture settings, color pipeline, cameras, states, and tolerances.
- Capture consistent front, side, rear, three-quarter, close-up, silhouette, wireframe, and motion views as applicable.
- Compare against references and prior approved artifacts without hiding uncertainty behind a single similarity score.
- Inspect temporal stability, animation contacts, particles, lighting, UI states, and transition frames.
- Run engine import and representative runtime captures, then classify findings by severity and reproducibility.
Expected artifacts
- capture manifest
- annotated contact sheet
- temporal review
- runtime metrics
- reproducible findings
Workflow-specific gates
- Control resolution, camera, lighting, exposure, pose, animation time, and platform before comparing images.
- Review transparent assets over light, dark, and checkerboard backgrounds.
- A visual pass never overrides license, format, performance, playability, or human-approval gates.
Production completion gate
Before recommending production use, complete and report all seven gates:
- Rights, consent, code/model/dataset/output license, and generation-provenance checks.
- Technical format, naming, scale, color, metadata, and target-import validation.
- Visual and temporal consistency review across representative views and states.
- Runtime memory, frame-time, draw-call, streaming, and asset-budget checks.
- Playability and interaction smoke tests in the target runtime.
- Screenshot, capture, diff, or artifact-regression evidence with reproducible settings.
- Human approval before replacing source assets or promoting generated output.
What ships with it
1 file 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.
- 5d ago First seen · 58 lines · 25 tokens per session scan A e498da527486
visual-qa is a skill published in the GitHub repository frabcd/codex-ai-game-studio (9 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 464 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 2026-09-03.
Other skills, from other repositories
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
threejs-qa-release
Verify and release Three.js browser games: playtest QA, automated bot playtests, mobile and responsive checks, production builds, static-hosting base paths, debug gating, bundle review, screenshots, visual regression baselines, canvas-pixel inspection with measured metrics, and release risk reports.
test-playable-web-games
Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
pie-testing
Start, stop, and query Play-In-Editor (PIE) sessions for runtime testing of Blueprints, gameplay logic, widgets, AI, and any in-game behavior. Use when the user asks you to "play", "test", "run", "PIE", "start/stop the game", or otherwise needs a live game world to validate changes.