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 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/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/ai-ecoverse/slicc/playwright-cli-e2e"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/playwright-cli-e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Prompt Injection · line 32 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.01960 |
| Opus 5.5 | $0.00055 | $0.00784 |
| Sonnet 5.5 | $0.00028 | $0.00392 |
| Haiku 4.5 | $0.00014 | $0.00196 |
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 17d 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 — 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.
- 17d ago Changed 5d2208e6c266
- 1mo ago 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 (34 stars, last pushed 2d ago), licensed Apache-2.0. It adds 138 tokens to every session and 1,960 once invoked, about $0.0006 per session on Opus 5.5. 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.
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
muggle-test
Change-driven E2E acceptance testing: detects the user's recent changes (local diff, branch, or PR), maps them to the user flows they affect, and runs real-browser tests on localhost or a preview/staging URL. Use whenever the user wants their own work validated before it ships — "make sure I didn't break anything"…