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 YuxiaoWang-520/harness-craft --skill develop-web-gamegit clone --depth 1 https://github.com/YuxiaoWang-520/harness-craftWrote 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/yuxiaowang-520/harness-craft/develop-web-game)<a href="https://agentmods.dev/skills/yuxiaowang-520/harness-craft/develop-web-game"><img src="https://agentmods.dev/badge/skills/yuxiaowang-520/harness-craft/develop-web-game/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/yuxiaowang-520/harness-craft/develop-web-game"><img src="https://agentmods.dev/badge/skills/yuxiaowang-520/harness-craft/develop-web-game.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 | $0.00064 | $0.02075 |
| Opus 5 | $0.00032 | $0.01038 |
| Sonnet 5 | $0.00013 | $0.00415 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade A, and why
develop-web-game 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- agents/openai.yaml 299 B
- assets/game-small.svg 2.6 KB
- assets/game.png 2.2 KB
- LICENSE.txt 11 KB
- node_modules/.bin/playwright 20 B
- node_modules/.bin/playwright-core 25 B
- node_modules/.package-lock.json 1.0 KB
- node_modules/playwright-core/bin/install_media_pack.ps1 174 B runs code
- node_modules/playwright-core/bin/install_webkit_wsl.ps1 1.4 KB runs code
- node_modules/playwright-core/bin/reinstall_chrome_beta_linux.sh 1.2 KB runs code
- node_modules/playwright-core/bin/reinstall_chrome_beta_mac.sh 560 B runs code
- node_modules/playwright-core/bin/reinstall_chrome_beta_win.ps1 957 B runs code
- node_modules/playwright-core/bin/reinstall_chrome_stable_linux.sh 1.2 KB runs code
- node_modules/playwright-core/bin/reinstall_chrome_stable_mac.sh 516 B runs code
- node_modules/playwright-core/bin/reinstall_chrome_stable_win.ps1 923 B runs code
- node_modules/playwright-core/bin/reinstall_msedge_beta_linux.sh 1.5 KB runs code
- node_modules/playwright-core/bin/reinstall_msedge_beta_mac.sh 374 B runs code
- node_modules/playwright-core/bin/reinstall_msedge_beta_win.ps1 874 B runs code
- node_modules/playwright-core/bin/reinstall_msedge_dev_linux.sh 1.5 KB runs code
- node_modules/playwright-core/bin/reinstall_msedge_dev_mac.sh 369 B runs code
- node_modules/playwright-core/bin/reinstall_msedge_dev_win.ps1 869 B runs code
- node_modules/playwright-core/bin/reinstall_msedge_stable_linux.sh 1.5 KB runs code
- node_modules/playwright-core/bin/reinstall_msedge_stable_mac.sh 368 B runs code
- node_modules/playwright-core/bin/reinstall_msedge_stable_win.ps1 856 B runs code
- node_modules/playwright-core/browsers.json 1.8 KB
- node_modules/playwright-core/cli.js 713 B runs code
- node_modules/playwright-core/index.d.ts 634 B runs code
- node_modules/playwright-core/index.js 1.1 KB runs code
- node_modules/playwright-core/index.mjs 1.0 KB runs code
- node_modules/playwright-core/lib/androidServerImpl.js 3.0 KB runs code
- node_modules/playwright-core/lib/browserServerImpl.js 5.9 KB runs code
- node_modules/playwright-core/lib/cli/driver.js 4.1 KB runs code
- node_modules/playwright-core/lib/cli/program.js 27 KB runs code
- node_modules/playwright-core/lib/cli/programWithTestStub.js 3.1 KB runs code
- node_modules/playwright-core/lib/client/android.js 13 KB runs code
- node_modules/playwright-core/lib/client/api.js 4.7 KB runs code
- node_modules/playwright-core/lib/client/artifact.js 2.7 KB runs code
- node_modules/playwright-core/lib/client/browser.js 6.0 KB runs code
- node_modules/playwright-core/lib/client/browserContext.js 25 KB runs code
- node_modules/playwright-core/lib/client/browserType.js 8.8 KB runs code
- node_modules/playwright-core/lib/client/cdpSession.js 1.7 KB runs code
- node_modules/playwright-core/lib/client/channelOwner.js 7.5 KB runs code
- node_modules/playwright-core/lib/client/clientHelper.js 2.3 KB runs code
- node_modules/playwright-core/lib/client/clientInstrumentation.js 1.9 KB runs code
- node_modules/playwright-core/lib/client/clientStackTrace.js 2.5 KB runs code
- node_modules/playwright-core/lib/client/clock.js 2.3 KB runs code
- node_modules/playwright-core/lib/client/connection.js 12 KB runs code
- node_modules/playwright-core/lib/client/consoleMessage.js 1.7 KB runs code
- node_modules/playwright-core/lib/client/coverage.js 1.5 KB runs code
- node_modules/playwright-core/lib/client/dialog.js 1.7 KB runs code
- node_modules/playwright-core/lib/client/download.js 1.8 KB runs code
- node_modules/playwright-core/lib/client/electron.js 6.0 KB runs code
- node_modules/playwright-core/lib/client/elementHandle.js 12 KB runs code
- node_modules/playwright-core/lib/client/errors.js 2.6 KB runs code
- node_modules/playwright-core/lib/client/eventEmitter.js 9.7 KB runs code
- node_modules/playwright-core/lib/client/events.js 2.8 KB runs code
- node_modules/playwright-core/lib/client/fetch.js 13 KB runs code
- node_modules/playwright-core/lib/client/fileChooser.js 1.4 KB runs code
- node_modules/playwright-core/lib/client/fileUtils.js 1.3 KB runs code
- node_modules/playwright-core/lib/client/frame.js 19 KB runs code
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 · 150 lines · 64 tokens per session scan A 4586330e97c9
develop-web-game is a skill published in the GitHub repository YuxiaoWang-520/harness-craft (73 stars, last pushed 5mo ago), with no licence file. It adds 64 tokens to every session and 2,075 once invoked, about $0.0003 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
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.
godot-e2e
Write and run E2E (end-to-end) game tests using the godot-e2e framework. Python controls a live Godot game over TCP — Locator-based semantic queries, expect() auto-retry assertions, and engine log capture make failures self-diagnosing. Use this skill whenever you need to: Test actual gameplay: player movement…
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.
visual-qa
Inspect Godot screenshots or short frame sequences for acceptance issues. Use after capturing a scene, when checking camera framing, missing assets, UI overlap, collision visualization, animation, or a black/empty viewport.
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.