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/dwsy/agent/web-browsernpx skills add Dwsy/agent --skill web-browsergit clone --depth 1 https://github.com/Dwsy/agentWrote 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/dwsy/agent/web-browser)<a href="https://agentmods.dev/skills/dwsy/agent/web-browser"><img src="https://agentmods.dev/badge/skills/dwsy/agent/web-browser.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 | $0.00062 | $0.02958 |
| Opus 5 | $0.00031 | $0.01479 |
| Sonnet 5 | $0.00012 | $0.00592 |
| Haiku 4.5 | $0.00006 | $0.00296 |
Grade A, and why
web-browser 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- .gitignore 34 B
- COMPLETE_GUIDE.md 7.3 KB
- COMPLETION_REPORT.md 9.3 KB
- cursor_pi_cli_rpc.md 21 KB
- demo.js 1.7 KB runs code
- docs/issues/20260112-shittycodingagent.ai 真实网站测试.md 4.7 KB
- docs/issues/20260112-web-browser 技能全面测试.md 9.5 KB
- docs/pr/20260112-web-browser 技能测试与修复.md 10.0 KB
- examples.js 3.2 KB runs code
- EXAMPLES.md 7.3 KB
- FIX_NOTE.md 6.1 KB
- kwm-full.html 176 KB
- LICENSE 1.0 KB
- package-lock.json 34 KB
- package.json 457 B
- pnpm-lock.yaml 22 KB
- README.md 10 KB
- resources.json 10 B
- scripts/browser.sh 1.7 KB runs code
- scripts/check-console.js 1.6 KB runs code
- scripts/check-visible.js 1.4 KB runs code
- scripts/checkbox.js 2.4 KB runs code
- scripts/clear-data.js 2.1 KB runs code
- scripts/click.js 1.2 KB runs code
- scripts/console-logs.js 1.7 KB runs code
- scripts/cookies.js 4.3 KB runs code
- scripts/debug.js 2.4 KB runs code
- scripts/download.js 3.1 KB runs code
- scripts/eval.js 2.5 KB runs code
- scripts/find-text.js 3.1 KB runs code
- scripts/get-element.js 2.6 KB runs code
- scripts/get-meta.js 4.0 KB runs code
- scripts/get-port.js 438 B runs code
- scripts/hover.js 1.2 KB runs code
- scripts/inspect.js 3.2 KB runs code
- scripts/intercept.js 3.7 KB runs code
- scripts/nav.js 1.2 KB runs code
- scripts/network.js 4.0 KB runs code
- scripts/pdf.js 1.7 KB runs code
- scripts/performance.js 2.5 KB runs code
- scripts/pick.js 5.5 KB runs code
- scripts/reload.js 1.7 KB runs code
- scripts/screenshot.js 961 B runs code
- scripts/scroll.js 3.0 KB runs code
- scripts/select.js 1.3 KB runs code
- scripts/start.js 5.1 KB runs code
- scripts/stop.js 1.6 KB runs code
- scripts/storage.js 4.3 KB runs code
- scripts/submit.js 1.2 KB runs code
- scripts/tabs.js 3.4 KB runs code
- scripts/test.js 2.1 KB runs code
- scripts/type.js 1.6 KB runs code
- scripts/upload.js 1.5 KB runs code
- scripts/visit-insecure.js 1.3 KB runs code
- scripts/wait-for-url.js 1.6 KB runs code
- scripts/wait-for.js 2.4 KB runs code
- SUBAGENT_CREATED.md 6.4 KB
- test-all-scripts.js 2.6 KB runs code
- test-complete.js 3.9 KB runs code
- test-integration.js 2.0 KB runs code
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 · 486 lines · 62 tokens per session scan A 0e33cf955cac
web-browser is a skill published in the GitHub repository Dwsy/agent (22 stars, last pushed 18d ago), with no licence file. It adds 62 tokens to every session and 2,958 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
remediate
Auto-fixes runtime issues found during visual verification (Stage 6V) using a categorized fix-verify cycle. This skill should be used when the user asks to "run runtime remediation", "fix 6V failures", "run Stage 6R", "auto-fix verification issues", "remediate runtime issues", "fix the verification report failures"…
verify
Verifies the running application against PRD screen specs and acceptance criteria in a browser. This skill should be used when the user asks to "run visual verification", "verify the app against the PRD", "run Stage 6V", "check the running app", "verify screens match specs", "run live app verification", "test the…
web-test
Этот скилл MUST быть вызван когда пользователь просит проверить или протестировать 1С через браузер в интерактивном режиме (быстрые ручные проверки). SHOULD также вызывать для одноразовой верификации поведения веб-интерфейса 1С. Do NOT использовать для создания файлов автотестов — используй playwright-test; для…
1c-web-session
Этот скилл MUST быть вызван для управления 1С:Предприятие в веб-клиенте через Playwright MCP: запуск/перезапуск/завершение сеанса, навигация, создание и редактирование справочников и документов. SHOULD также вызывать для генерации тестовых данных через UI и сценарного тестирования в браузере. Do NOT использовать для…
playwright-test
Этот скилл MUST быть вызван когда пользователь говорит "напиши UI-тест", "создай playwright тест", "scaffold playwright", "протестируй фичу в браузере". SHOULD также вызывать после деплоя фичи 1С для создания автоматизированного регрессионного теста. Do NOT использовать для интерактивной автоматизации браузера …
amazon-bestseller-listing
Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…