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 AllenS0104/skill-browser --skill universal-web-adaptationgit clone --depth 1 https://github.com/AllenS0104/skill-browserWrote 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/allens0104/skill-browser/universal-web-adaptation)<a href="https://agentmods.dev/skills/allens0104/skill-browser/universal-web-adaptation"><img src="https://agentmods.dev/badge/skills/allens0104/skill-browser/universal-web-adaptation/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/allens0104/skill-browser/universal-web-adaptation"><img src="https://agentmods.dev/badge/skills/allens0104/skill-browser/universal-web-adaptation.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 | $0.00072 | $0.01669 |
| Opus 5 | $0.00036 | $0.00834 |
| Sonnet 5 | $0.00014 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
universal-web-adaptation 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 8d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal web adaptation skill
Use this skill when the user wants a general solution across many websites, not a one-by-one manual integration first.
This skill is especially suitable for:
- unfamiliar public websites
- search-oriented workflows
- result-page collection and lightweight summaries
- deciding whether a site needs a dedicated profile or can stay generic
For the 99idea Playwright project, this skill should work together with:
src\run-demo.jssrc\planner.jssrc\llm-planner.jssrc\site-profiles.jsscenarios\site-profiles.json
Core principle
Always try this order:
- Capability discovery — check if opencli already supports the site (
opencli list) - Auth cascade — classify: PUBLIC → COOKIE/SESSION → HEADER → LOGIN-GATED
- Generic adaptation — probe UI controls and try heuristic strategies
- Temporary scenario tuning — adjust runtime before assuming selectors are wrong
- Popup / opener / alternate-submit handling
- Site profile only if generic adaptation still fails
The goal is to minimize per-site handwork.
Execution path decision (inspired by opencli)
Before touching the DOM, first determine which execution layer to use:
if opencli has an adapter for this site:
use opencli (zero LLM cost, deterministic)
elif the site has a public API:
use fetch (structured data, no rendering)
elif the site renders server-side (SSR):
use web_fetch or Playwright (metadata extraction)
else:
use Browser Agent with login-state or mark blocked
This avoids wasting time on SPA shells that will never yield results via scraping.
What “generic adaptation” means
When facing a new site, do not immediately create a profile. First try to discover:
- likely search inputs
- likely opener buttons or icons
- likely submit controls
- whether Enter works
- whether a click opens a popup or new tab
- whether the site verifies best by URL, title, or visible text
Standard workflow
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.
- 8d ago First seen · 263 lines · 72 tokens per session scan A 87b4f7191835
universal-web-adaptation is a skill published in the GitHub repository AllenS0104/skill-browser (5 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 1,669 once invoked, about $0.0004 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 skills, from other repositories
e2e-testing
End-to-end testing workflow with Playwright for browser automation, visual regression, cross-browser testing, and CI/CD integration.
moab-browser-automation
MOAB — build a dedicated browser-automation agent for a website the user already logs in to. Use when the user mentions MOAB, asks to automate a portal, dashboard, intranet site, or SaaS tool, wants an AI agent for a site behind SSO or single sign-on, or asks to add a new tool or feature to an existing MOAB agent.…
browseros
Control the BrowserOS agentic browser (open-source Chromium fork) from a coding agent via its built-in MCP server. Use when the user asks to browse, click, fill forms, scrape/extract data, take screenshots, manage tabs/bookmarks/history, automate a website, do research + write files (Cowork), schedule a recurring…
browseros
Control the BrowserOS agentic browser (open-source Chromium fork) from coding agents via its native shell CLI (browseros-cli) or built-in HTTP MCP server (http://127.0.0.1:9200/mcp). Use when the user asks to browse, click, fill forms, scrape/extract data, take screenshots, manage tabs/bookmarks/history, automate a…
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.