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 mintdotgg/mint-threejs-skills --skill threejs-qa-releasegit clone --depth 1 https://github.com/mintdotgg/mint-threejs-skillsWrote 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/mintdotgg/mint-threejs-skills/threejs-qa-release)<a href="https://agentmods.dev/skills/mintdotgg/mint-threejs-skills/threejs-qa-release"><img src="https://agentmods.dev/badge/skills/mintdotgg/mint-threejs-skills/threejs-qa-release/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/mintdotgg/mint-threejs-skills/threejs-qa-release"><img src="https://agentmods.dev/badge/skills/mintdotgg/mint-threejs-skills/threejs-qa-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 13 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00046 | $0.00731 |
| Opus 5.5 | $0.00018 | $0.00292 |
| Sonnet 5.5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
threejs-qa-release 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 2mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three.js QA Release
Prove the app or game works as its user encounters it and that the production build is shippable.
Read ../../references/verification-policy.md first. Do not start browser,
Playwright, canvas, screenshot, diagnostics, release-preview, or mobile work
without approval for that scope.
Read By Need
- Core QA, responsive behavior, performance, evidence, and release:
references/qa-release-checklists.md. - Screenshot baselines or visual regression:
references/visual-test-harness.md. - Game-only scripted play, difficulty, fairness, or softlocks:
references/game-playtest-bot.md.
Default Minimum
Without additional approval, run only the policy's automatic minimum: the smallest build/typecheck gate, focused existing non-browser tests, and local asset/import-path checks. Fix owned failures, then state that extended browser QA was not run and offer a concrete desktop QA pass.
Approved Desktop QA Workflow
- Confirm the approved scope, then start the intended dev or production preview.
- Capture console, page, and relevant network errors.
- Verify nonblank canvas pixels and the approved active desktop view.
- Exercise the primary user journey and changed risky paths.
- Test loading, empty, unsupported, and error states when applicable.
- Check desktop UI fit, input cancellation, and resize.
- If audio changed, verify gesture unlock, decode/load, triggers, loops, cleanup, mute, and volume.
- Add deterministic screenshot baselines only when separately approved; otherwise record that they were not run.
- Run canvas diagnostics, profiling, production-preview checks, or game bot playtests only when the user approved those checks.
- Record commands, artifacts, issues, and remaining risks.
After desktop QA, offer mobile as a separate second step. Do not infer mobile approval from desktop approval.
Canvas Inspector
After canvas-inspector approval, run from the target project so its
@playwright/test and pngjs dependencies are used:
What ships with it
4 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.
- 2mo ago First seen · 83 lines · 46 tokens per session scan A abcbbc60afd1
threejs-qa-release is a skill published in the GitHub repository mintdotgg/mint-threejs-skills (125 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 731 once invoked, about $0.0002 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 skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.