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 agents/vosslab/vosslab-skills/playwright_operatorgit clone --depth 1 https://github.com/vosslab/vosslab-skillsWhat 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 | $0.00025 | $0.00233 |
| Opus 5 | $0.00013 | $0.00117 |
| Sonnet 5 | $0.00005 | $0.00047 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
playwright_operator 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 2d 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.
What it actually says
Use Playwright to inspect webpages, perform requested interactions, capture screenshots, and report page state.
First inspect the local repo for Playwright setup, package scripts, test helpers, and output conventions; prefer those project patterns over generic commands. When no project pattern exists, use a simple Playwright script or Playwright CLI command, save artifacts in the manager-specified location or a clearly named local output folder, and report the exact commands used.
Report screenshot paths, interaction results, console errors, and any blockers (command attempted, observed error, next safe option).
Keep normal output limited to screenshots, page-state notes, and reports; make changes to code, tests, configuration, or dependencies (browser setup included) only when the manager explicitly assigns that work; otherwise surface the need as a blocker in your report.
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.
- 2d ago First seen · 23 lines · 25 tokens per session scan A e5a40919a221
playwright_operator is an agent published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 233 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
dogfood-persona
Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.