live-browser-testing

A way to test real web applications in a browser using observed pages, user actions, screenshots, downloads, and other visible evidence.

In plain words
What is it for?
Use it for frontend smoke tests, login-free user flows, responsive checks, forms, screenshots, console-visible behavior, downloads, PDF exports, and verifying UI changes.
Why use it?
It checks that an interface actually works and renders correctly instead of relying only on source code or assumptions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/codeinfinity1/stram/live-browser-testing
Any agent
npx skills add CodeInfinity1/Stram --skill live-browser-testing
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 720 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00720
Opus 5 $0.00017 $0.00360
Sonnet 5 $0.00007 $0.00144
Haiku 4.5 $0.00003 $0.00072

Measured 2d ago against content hash 3e0c2cf7c5c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

live-browser-testing 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.

skills/browser-web/live-browser-testing/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live Browser Testing

Purpose

Run real browser checks for local or remote web apps using Stram-owned Playwright-backed tools. This skill is inspired by webapp testing practices, but execution stays inside Stram's native browser tool surface.

When To Use

Use for frontend smoke tests, local app QA, login-free flows, responsive checks, forms, screenshots, console-visible behavior, downloads, PDF export, and verifying that a UI change actually renders.

Inputs And Evidence

  • Target URL, expected screen, viewport needs, and user flow.
  • browser_live_status readiness.
  • Live session ID, observed element IDs, page URL/title/text, screenshot or artifact paths.
  • Test result, blocker, or approval status for state-changing actions.

Tool Map

  • browser_live_status
  • browser_live_open
  • browser_live_navigate
  • browser_live_observe
  • browser_live_back
  • browser_live_forward
  • browser_live_reload
  • browser_live_query_selector
  • browser_live_html
  • browser_live_page_search
  • browser_live_find_elements
  • browser_live_extract
  • browser_live_dropdown_options
  • browser_live_select_option
  • browser_live_click
  • browser_live_hover
  • browser_live_click_coordinates
  • browser_live_drag
  • browser_live_drag_coordinates
  • browser_live_type
  • browser_live_fill_form
  • browser_live_scroll
  • browser_live_scroll_to_text
  • browser_live_resize
  • browser_live_press_key
  • browser_live_upload_file
  • browser_live_download
  • browser_live_save_pdf
  • browser_live_evaluate_js
  • browser_live_wait
  • browser_live_screenshot
  • browser_live_tabs
  • browser_live_new_tab
  • browser_live_switch_tab
  • browser_live_close_tab
  • browser_live_close

Workflow

  1. Check live browser readiness when setup is uncertain.
  2. Open the target URL and immediately observe the page.
  3. Use observed element IDs for clicks and typing; avoid stale coordinates.
  4. Take one state-changing action, then observe again.
  5. Capture screenshots for visual claims or regression evidence.
  6. Report verified behavior, blockers, and any untested assumptions.

Read the full file on GitHub · 98 lines

Changes

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.

  1. 2d ago First seen · 98 lines · 34 tokens per session scan A 3e0c2cf7c5c3

Subscribe to this mod's changes

live-browser-testing is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 34 tokens to every session and 720 once invoked, about $0.0002 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.