A browser-based playtesting workflow for checking whether a canvas or WebGL game actually runs and can be played. It can open the game, interact with it, inspect diagnostics, take screenshots, and close the browser.

It helps run smoke checks, scripted playtests, input and objective checks, softlock detection, deterministic canvas or WebGL checks, screenshots, and visual comparisons.

A successful build or visible screen does not prove that controls work, objectives are reachable, or the game avoids errors and softlocks.

playtest — Skill for Claude Code by kyh/vibedgames

Install

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.

Any agent

npx skills add kyh/vibedgames --skill playtest

Clone the repo

git clone --depth 1 https://github.com/kyh/vibedgames

Made for: Claude Code.

Or install vibedgames, the plugin that ships this one along with the rest of its 34 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kyh/vibedgames/playtest/github.svg)](https://agentmods.dev/skills/kyh/vibedgames/playtest)

Your own site

<a href="https://agentmods.dev/skills/kyh/vibedgames/playtest"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/playtest/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kyh/vibedgames/playtest"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/playtest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,046 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

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 Agent Snooping · line 92
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00055	$0.04046
Opus 5.5	$0.00022	$0.01618
Sonnet 5.5	$0.00011	$0.00809
Haiku 4.5	$0.00006	$0.00405

Measured 29d ago against content hash 3fcfdea6cbbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

playtest 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/_lib/asset-tools.mjs, scripts/lib/harness.mjs, scripts/ref-sxs.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/vibedgames/skills/playtest/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playtest

A build that compiles proves nothing. A game that renders proves almost nothing. Playtesting proves it plays — that the loop runs, input moves the player, the objective is reachable, and nothing throws along the way.

The Tool: `vg playtest`

Everything here runs through one command. vg playtest is a passthrough to agent-browser, a native browser-automation CLI built for agents — vg installs it and its browser on first use, so there is nothing to add to the game's package.json to drive it. No test runner, no devDependencies, no MCP server to configure. (The one optional dependency is on the game's side: @vibedgames/playtest types and publishes the diagnostics contract below.)

vg playtest open http://localhost:5173   # launch + navigate (headless by default)
vg playtest snapshot -i                  # interactive elements, with @eN refs
vg playtest click @e2                    # act on a ref from that snapshot
vg playtest eval "window.__GAME_DIAGNOSTICS__" --json
vg playtest screenshot /tmp/frame.png
vg playtest close

A daemon persists between invocations, so one-call-per-step is cheap and the page stays open across commands.

Load the upstream skill for the general command surface

agent-browser ships its own skills and serves them from the installed binary, so the content always matches the version you actually have:

vg playtest skills get core       # the general browser-automation guide — read before driving anything
vg playtest skills get core --full  # + full command reference and templates
vg playtest skills get dogfood    # systematic exploratory testing / bug hunts
vg playtest skills list           # everything available on this version

skills get core is the source of truth for the generic surface — the snapshot-and-ref loop, sessions, waiting, forms, auth, troubleshooting. Don't re-derive it here, and don't trust a stale memory of it. An older agent-browser build with no skills subcommand falls back to vg playtest --help.

Read the full file on GitHub · 213 lines

Files

What ships with it

8 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.

Changes

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 3fcfdea6cbbb
1mo ago Changed · +9 lines ba1977c0f094
1mo ago Changed · +24 lines · +14 tokens per session 566c3d542817
1mo ago Changed · +7 lines · -74 tokens per session 8018a1258419
2mo ago Changed · +9 lines 60637b6ca6fc
2mo ago First seen · 164 lines · 115 tokens per session scan A 56526d441025

Subscribe to this mod's changes

playtest is a skill published in the GitHub repository kyh/vibedgames (61 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 4,046 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.

Browser automation React Testing game multiplayer nextjs realtime supabase

playtest next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
playtestkyh/vibedgames	Skill	61	2d ago	MIT	A	55	Claude Code
verifymeursyphus/ssgoi	Skill	1.0k	3d ago	MIT	A	26	Claude Code
quality-engineering-playwright-cliHoangNguyen0403/agent-skills-standard	Skill	583	yesterday	MIT	A	62	Claude Code, Codex
quality-engineering-playwright-pom-generationHoangNguyen0403/agent-skills-standard	Skill	583	yesterday	MIT	A	69	Claude Code, Codex
supabasemartineserios/thebrana	Skill	3	today	MIT	A	58	Claude Code
playwright-e2elroy-stack/ai-pod-store	Skill	1	11d ago	none	A	86	Claude Code
next-cache-components-optimizervercel/next.js	Skill	143k	yesterday	MIT	A	123	Claude Code