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 adbertram/cli-tools --skill playwright-cligit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/playwright-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/playwright-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/playwright-cli/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/adbertram/cli-tools/playwright-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/playwright-cli.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 | $0.00153 | $0.04630 |
| Opus 5.5 | $0.00061 | $0.01852 |
| Sonnet 5.5 | $0.00031 | $0.00926 |
| Haiku 4.5 | $0.00015 | $0.00463 |
Grade A, and why
playwright-cli 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 today.
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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start>
playwright-cli [-s=<session>] <command> [arguments] [options]
Commands are flat — there are no grouped subcommands. Write playwright-cli snapshot, not playwright-cli page snapshot.
| Task | Command |
|---|---|
| Open browser to URL | playwright-cli open https://example.com |
| Navigate to URL | playwright-cli goto https://example.com |
| Take page snapshot | playwright-cli snapshot |
| Click element | playwright-cli click REF |
| Fill form field | playwright-cli fill REF "text" |
| Take screenshot | playwright-cli screenshot |
| List sessions | playwright-cli list |
| Press key | playwright-cli press Enter |
| Save auth state | playwright-cli state-save auth.json |
| List network requests | playwright-cli requests |
| </quick_start> |
<essential_principles>
MANDATORY: Consult the adjacent usage.json at <cli-tools-root>/_repo/skills/<tool>-cli/usage.json before executing ANY playwright-cli command.
It contains every command, argument, and option with descriptions sourced directly from --help. Never guess at syntax. When in doubt, also run playwright-cli --help <command>.
There are no grouped forms like browser open, page snapshot, interact click, tab list, cookie get, network requests, devtools console, or data delete. Those will fail at parse time.
The following commands require a REF from a prior snapshot: click, dblclick, fill, hover, drag (two refs), select, check, uncheck, and optionally screenshot/eval. Always snapshot before interacting, and re-snapshot after any DOM-changing action — stale refs are invalid. After any submit or navigation, inspect the new snapshot and continue from the live page state; do not assume the next page or step.
Interaction commands can report a markdown ### Error block after the browser has already completed part of the action, such as a submit click that times out while the page still navigates. Treat ### Error in stdout as an action error, then verify the final page state with snapshot, URL, or title before deciding whether the workflow can continue from the new page.
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.
- today First seen · 282 lines · 153 tokens per session scan A 36079253fec0
playwright-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 4,630 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 2026-11-07.
playwright-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| playwright-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 153 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| surfnicobailon/surf-cli | Skill | 684 | yesterday | MIT | A | 53 | Claude Code, Codex |
| acrawl-mcpMingye-Lu/AgenticCrawler | Skill | 15 | yesterday | MIT | A | 200 | Claude Code, Codex |
| debug-failed-actionfrane/vibesurfer | Skill | 17 | 1mo ago | Apache-2.0 | A | 54 | Claude Code |
| x402browser-use/browser-use | Skill | 120k | yesterday | MIT | A | 175 | Claude Code |
| browser-usebrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 57 | Claude Code, Codex |