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 skills/fu-jie/openwebui-extensions/playwright-openwebuinpx skills add Fu-Jie/openwebui-extensions --skill playwright-openwebuigit clone --depth 1 https://github.com/Fu-Jie/openwebui-extensionsWrote 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/fu-jie/openwebui-extensions/playwright-openwebui)<a href="https://agentmods.dev/skills/fu-jie/openwebui-extensions/playwright-openwebui"><img src="https://agentmods.dev/badge/skills/fu-jie/openwebui-extensions/playwright-openwebui.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.02552 |
| Opus 5 | $0.00040 | $0.01276 |
| Sonnet 5 | $0.00016 | $0.00510 |
| Haiku 4.5 | $0.00008 | $0.00255 |
Grade A, and why
playwright-openwebui 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 6d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
重要说明 (Living Document)
这是一个持续演进的技能文件 (Living Skill)
每次测试会话结束后,必须将新发现的 selector、时序问题、已知坑点追加到.agent/learnings/playwright-tests.md。
每次新会话开始前,必须先读取该文件,避免重复踩坑。
本文件本身也应在发现重大 UI 变化时更新(例如 OWUI 版本升级导致 selector 失效)。
配套 Agent: plugin-tester.agent.md — 完整的部署+测试+学习闭环。
Env 文件: .github/agents/.env.openwebui (OPENWEBUI_URL / USERNAME / PASSWORD)
Scripts Env: scripts/.env (api_key + url,用于 Python 部署脚本)
Instructions
Use Playwright browser tools to test and debug OpenWebUI plugins. Start every session with the login flow. Credentials and URL are read from .github/agents/.env.openwebui.
第一步:登录(每次会话必须先执行)
const fs = require('fs');
const path = require('path');
// 读取 .env.openwebui
function loadEnv() {
const envPath = path.join(process.cwd(), '.github/agents/.env.openwebui');
const raw = fs.readFileSync(envPath, 'utf-8');
const env = {};
for (const line of raw.split('\n')) {
const trimmed = line.trim();
if (!trimmed || trimmed.startsWith('#')) continue;
const [key, ...rest] = trimmed.split('=');
env[key.trim()] = rest.join('=').trim();
}
return env;
}
const env = loadEnv();
const BASE_URL = env.OPENWEBUI_URL || 'http://localhost:3000';
// 导航到登录页
await page.goto(`${BASE_URL}/auth`, { waitUntil: 'networkidle' });
// 检查是否已登录(已登录则跳过)
const isLoggedIn = await page.locator('[id="chat-textarea"], [placeholder*="message" i], div[contenteditable]').count();
if (!isLoggedIn) {
// 填写 email
await page.locator('input[name="email"], input[autocomplete="username"], input[type="email"]').first().fill(env.OPENWEBUI_USERNAME);
// 填写密码
await page.locator('input[type="password"]').first().fill(env.OPENWEBUI_PASSWORD);
// 点击登录
await page.locator('button[type="submit"]').first().click();
// 等待登录完成
await page.waitForURL(`${BASE_URL}/**`, { timeout: 10000 });
await page.waitForTimeout(1500);
}
console.log('✅ 已登录 OpenWebUI:', await page.title());
常用操作模式
截图存档
await page.screenshot({ path: '/tmp/owui-before-fix.png' });
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.
- 6d ago First seen · 287 lines · 80 tokens per session scan A 16f0c767637c
playwright-openwebui is a skill published in the GitHub repository Fu-Jie/openwebui-extensions (304 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 2,552 once invoked, about $0.0004 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
11-browser-qa
Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.
06-test
Write and iterate tests until they pass, or validate a user journey end to end in the browser. Use when the user wants to add coverage, find what's untested, or walk a flow. Not for auditing test health or debugging a failure.
web-browser-automation
Comprehensive macOS browser automation using PyXA, Playwright, Selenium, and Puppeteer for desktop web testing, scraping, and workflow automation. Use when asked to "automate web browsers", "Selenium Chrome automation", "Playwright testing", "Puppeteer scraping", or "cross-browser automation". Supports Chrome, Edge…
e2e-setup
Set up Playwright e2e automation tailored to this team and app. Probes the running app (auth mechanism, API surface, spec availability), interviews with recommendations instead of open questions, scaffolds the playwright/ folder, and records every decision in playwright/AUTOMATION.md for the other e2e skills to read.…
verify-fix
Re-test a bug fix after a developer resolves it. Pulls the original bug from Jira, re-executes the repro steps in the browser, checks for regressions, and updates the bug status. The final step in the SDT workflow before a ticket moves to Done. Use when: "verify fix", "retest", "is this fixed?", "check BUG-123"…
playwright-standard
Comprehensive, opinionated guidance for Playwright test development. Use ONLY when writing E2E, browser tests, UI tests, API, component, or visual tests, debugging failures, implementing Page Object Model, or configuring CI/CD. For unit tests, use vitest-standard. Use Playwright solely for E2E, API, and component…