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 agentmods add commands/alphabravo-oss/guild/initgit clone --depth 1 https://github.com/alphabravo-oss/guildWhat 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 | $0.00016 | $0.00921 |
| Opus 5 | $0.00008 | $0.00461 |
| Sonnet 5 | $0.00003 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
init 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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants to initialize Playwright E2E testing in the current project.
Preflight (read before doing anything)
- Run
pwd— confirm you are in the project the user wants to set up. If this is the guild repo itself (cwd ends inguild), STOP and ask the user which app to set up — this plugin is not meant to test itself. - Check for
package.jsonat the cwd root. If missing, ask whether tonpm init -yor whether they want a different workspace root. - Check for existing
playwright.config.ts/playwright.config.js. If present, STOP and ask: append-to-existing, or abort? Never overwrite without explicit ack. - Check for existing
.mcp.json. If present and already has aplaywrightserver entry, skip the MCP step — don't clobber their config.
Steps
1. Install Playwright
npm install --save-dev @playwright/test
npx playwright install
Both must succeed. playwright install downloads Chromium/Firefox/WebKit — it's a multi-hundred-MB step; tell the user it may take a minute.
2. Write playwright.config.ts
Use this generic template — works for any framework. Do NOT bake in Next.js/Vite assumptions unless the user has confirmed the stack.
import { defineConfig, devices } from '@playwright/test';
export default defineConfig({
testDir: './tests',
fullyParallel: true,
forbidOnly: !!process.env.CI,
retries: process.env.CI ? 2 : 0,
workers: process.env.CI ? 1 : undefined,
reporter: [['html', { open: 'never' }], ['list']],
use: {
baseURL: process.env.BASE_URL ?? 'http://localhost:3000',
trace: 'on-first-retry',
screenshot: 'only-on-failure',
video: 'retain-on-failure',
},
projects: [
{ name: 'chromium', use: { ...devices['Desktop Chrome'] } },
],
});
Single browser project by default — add Firefox/WebKit only when the user asks. Multi-browser is a 3x cost multiplier for diminishing return.
3. Register Playwright MCP
If .mcp.json does not exist, create it with:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["@playwright/mcp@latest", "--caps", "vision,devtools"]
}
}
}
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.
- yesterday First seen · 114 lines · 16 tokens per session scan A 8e49ef08103d
init is a command published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 921 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 2026-08-31.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试(支持视频录制、Trace 录制、控制台/网络日志捕获).
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.