Borrowing it
Nothing to install: this file belongs to sybrew/troy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sybrew/troy/main/.cursor/skills/playground/SKILL.mdgit clone --depth 1 https://github.com/sybrew/troyWrote 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/sybrew/troy/playground)<a href="https://agentmods.dev/skills/sybrew/troy/playground"><img src="https://agentmods.dev/badge/skills/sybrew/troy/playground/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/sybrew/troy/playground"><img src="https://agentmods.dev/badge/skills/sybrew/troy/playground.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 | $0.00085 | $0.03267 |
| Opus 5.5 | $0.00034 | $0.01307 |
| Sonnet 5.5 | $0.00017 | $0.00653 |
| Haiku 4.5 | $0.00009 | $0.00327 |
Grade A, and why
playground scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Playground WASM unhooks WordPress.org update cron and disables curl/streams. That does not make the faux optional. Site Health, `plugins_api`, Daemon ZIP, and anything that sets `update_plugins` still call `wp_remote_*`. How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playground regression
Do not write PHPUnit. Do not use Local WP, Docker, or MySQL. The engine is wp-plugin-regression.
If launch, harness, permalinks, official intercept, or Playwright login looks wrong, decide whether the cause is a Troy package or the regression plumbing (Playground, engine, mounts, cookies, rewrites, mu-plugins, the harness). When the plumbing is at fault, say so in the chat. Fix or report that system. Do not work around it in plugin code. Never change Troy Server, Client, Daemon, or Installer so they fit a broken harness.
When not to boot: wrap, trailing-comma, minify-only, docs-only.
When to run:
- Admin UI, update API, endpoints, headers, install, Site Health
- Support reproduction
- Before calling that work done
PHP edits on the working-tree mount apply on the next request. Launch takes the next free port in 9001–9099 (shared with other consumers of this engine). Read the URL from launch output or ~/.wordpress-playground/tests/runs.json. Do not assume port 9410. Restart after --wp / --php, a different --site, or a different --package set. Do not reuse persist across majors or latest vs trunk.
Captures are logged-out. Launch does not pass --login.
Do not flush_rewrite_rules() in a blueprint runPHP step. That writes incomplete rules and post permalinks fall through to the homepage. Set permalink_structure and delete_option( 'rewrite_rules' ) so Playground can flush on a later init.
Playground 301s /sitemap.xml via a VFS mu-plugin (sitemap-redirect.php). The engine overwrites that file with a no-op until https://github.com/WordPress/wordpress-playground/issues/4325 is patched. Drop the overwrite when that issue lands. If every request 500s with a parse error in that file, the no-op was invalid PHP. Fix lib/launch.js in wp-plugin-regression; do not change a Troy package.
If ~/.wordpress-playground/tests/runs.json lists a live pid for that port, reuse it.
waitReady waits for the Playground CLI line Ready! WordPress is running (blueprint finished) plus HTTP, not the first mid-install 200. A blueprint error in server.log fails launch even if the pid is still up.
Do not pass --plugin=wporg. Troy packages are not on wordpress.org. Do not use launch --pair.
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.
- mu-plugin/0-troy-playground-official.php 15 KB
- mu-plugin/1-troy-playground-daemon.php 1.9 KB
- mu-plugin/2-troy-playground-server-sqlite.php 2.3 KB
- mu-plugin/3-troy-playground-frames.php 1.9 KB
- mu-plugin/troy-playwright-admin.php 4.0 KB
- packages.json 998 B
- playwright.mcp.json 221 B
- scripts/playground.js 9.0 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.
- 2d ago First seen · 164 lines · 85 tokens per session scan A c906f35a6211
playground is a skill published in the GitHub repository sybrew/troy (55 stars, last pushed 14d ago), licensed MIT. It adds 85 tokens to every session and 3,267 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.