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/ai-ecoverse/slicc/playwright-cli-e2enpx skills add ai-ecoverse/slicc --skill playwright-cli-e2egit clone --depth 1 https://github.com/ai-ecoverse/sliccWrote 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/ai-ecoverse/slicc/playwright-cli-e2e)<a href="https://agentmods.dev/skills/ai-ecoverse/slicc/playwright-cli-e2e"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/playwright-cli-e2e.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 | $0.00138 | $0.01949 |
| Opus 5 | $0.00069 | $0.00975 |
| Sonnet 5 | $0.00028 | $0.00390 |
| Haiku 4.5 | $0.00014 | $0.00195 |
Grade A, and why
playwright-cli-e2e 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
playwright-cli E2E regression session
Re-run a consistent, 12-group end-to-end exercise of the playwright-cli shell command and diff the result against a known-good baseline to catch regressions and confirm bug fixes.
How to run it
- Automated, deterministic groups — run the companion runner:
It loadspcli-e2e # runs the checks, prints a PASS/FAIL table + JSON, cleans up its tab pcli-e2e --helptest-fixture.html(this directory) as adata:URL, exercises each programmatically-checkable group, and flags every result as matches baseline, REGRESSION (was PASS, now FAIL), or IMPROVEMENT (was a known bug, now PASS). The final line is a machine-comparable JSON object. - Manual / visual groups — work the checklist below by hand. These need human or visual judgment (mouse feel, overlay rendering, HAR file contents, live dialogs) and are deliberately not automated.
- Save the run next to the original report, dated:
/shared/playwright-cli-e2e-report-<YYYY-MM-DD>.md. Reference report:/shared/playwright-cli-e2e-report.md.
The 12 test groups
| # | Group | Auto? | Key commands to exercise | PASS looks like |
|---|---|---|---|---|
| 1 | Core | manual | open/goto, snapshot, eval, frames, resize, reload |
snapshot lists refs; eval "document.title" returns the title; resize/reload ack |
| 2 | Interaction | partial | fill, type, press, click, hover, select, check, uncheck, dblclick, drag |
input value/#out attrs change; select/check/hover resolve the ref (auto: ref-resolution detector) |
| 3 | Network capture | auto | requests, request N, request-headers, response-headers, response-body |
requests lists entries on a real navigation; detail sub-commands return data |
| 4 | Console | auto | eval log/warn/error, console [min-level], console --clear |
logged messages appear; --clear empties the buffer |
| 5 | Route mocking | auto | route, route-list, page fetch, unroute |
mocked body is returned by the page fetch; unroute clears routes |
| 6 | Mouse | manual | mousemove, mousedown, mouseup, mousewheel |
each acks; #out data-scroll updates on wheel (note: mousewheel is flaky) |
| 7 | Visual / locator | auto (locator) | generate-locator, highlight [--hide] |
generated selector actually matches an element; highlight overlay appears/clears |
| 8 | Drop | manual | drop --data=mime/type=value, drop --path=<vfs> |
#dropout == dropped:<value>; #fileout == file:<name> |
| 9 | Storage | manual | cookie-*, localstorage-*, sessionstorage-* (use a real origin) |
full CRUD round-trips on a real origin (opaque data: origins won't store) |
| 10 | Screenshots | auto | screenshot, --filename, --fullPage, --max-width, element ref |
option variants produce different dimensions/bytes (auto: byte+IHDR detector) |
| 11 | HAR | manual | record <url>, stop-recording <id> |
commands succeed; HAR saved under /recordings/... (contents not VFS-visible) |
| 12 | fetch / discover | auto | fetch <url>, fetch <url> --discover |
JSON with status, links[], and a discovery object |
What ships with it
2 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.
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 · 83 lines · 138 tokens per session scan A 0a5405411c4a
playwright-cli-e2e is a skill published in the GitHub repository ai-ecoverse/slicc (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 138 tokens to every session and 1,949 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
browser-viz-verify
Verifies that a NetClaw-generated visualization HTML file (three.js, canvas, drawio, UML, markmap) actually renders correctly — screenshot, console-error check, and an optional Lighthouse audit. Use immediately after generating any browser-based visualization output, to close the QA gap that otherwise requires a human…
BrowserBash Browser Automation
BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream NDJSON results with CI exit codes — using free local Ollama…
Geb Testing
Browser automation testing with Geb framework for Groovy/JVM using jQuery-like content DSL, Page Object pattern, Spock integration, and WebDriver abstraction.
playwright-cli
Use when a task needs Playwright-backed browser automation from the shell: open or attach to browser sessions, inspect snapshots and element refs, click/type/fill forms, debug Playwright tests, inspect console/network/storage, run Playwright snippets, capture screenshots/traces/videos, or generate reliable test code.…
ui-automation
WHartTest UI 自动化管理工具。用于创建、编辑、删除 UI 测试模块、页面、元素、页面步骤和测试用例。支持执行记录查询和错误分析。当需要将浏览器技能获取到的页面元素保存到平台、创建 UI 自动化用例、执行测试或分析执行结果时使用。元素采集默认优先 browser-use，无法覆盖时再用 playwright-skill 兜底。.