browser-computer-use

A collection of browser and computer-control actions for observing and interacting with web pages and desktop interfaces. It supports tasks such as navigation, clicking, typing, screenshots, and extracting page content.

In plain words
What is it for?
Use it for browser navigation, UI testing, form entry, page searches, content extraction, screenshots, and other observed computer interactions.
Why use it?
It lets an agent inspect and operate interfaces where reading source code or using a direct API is not enough.

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/browser-computer-use
Any agent
npx skills add CodeInfinity1/Stram --skill browser-computer-use
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 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 $0.00025 $0.00891
Opus 5 $0.00013 $0.00445
Sonnet 5 $0.00005 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured 2d ago against content hash b75732a25eac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-computer-use 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/browser-computer-use/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser And Computer Use

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_html
  • browser_live_page_search
  • browser_live_find_elements
  • browser_live_extract
  • 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_tabs
  • browser_live_new_tab
  • browser_live_switch_tab
  • browser_live_close_tab
  • browser_live_query_selector
  • browser_live_dropdown_options
  • browser_live_select_option
  • browser_live_upload_file
  • browser_live_download
  • browser_live_save_pdf
  • browser_live_evaluate_js
  • browser_live_screenshot
  • browser_live_wait
  • os_active_window
  • os_observe_ui
  • os_click_element
  • os_type_text
  • os_send_keys
  • screenshot_capture

Use this skill when a task requires web navigation, browser UI testing, desktop GUI observation, or Windows app control.

Workflow

  1. Observe current state before acting.
  2. Prefer browser tools for web pages and OS/UI tools for native desktop apps.
  3. Use element ids from the most recent observation instead of stale coordinates when possible.
  4. Take one state-changing action at a time, then observe again.
  5. Keep high-risk GUI actions approval-gated.
  6. Use Codex or Playwright guidance as evidence when it is available, but choose tools through model reasoning and schemas.
  7. For local browser sessions, use stored session_id plus observed element_id values.
  8. For live browser sessions, use live_session_id and re-observe after clicks, typing, uploads, downloads, JavaScript, screenshots, or PDF saves.
  9. For Windows UI, use os_active_window and os_observe_ui before os_click_element, os_type_text, or os_send_keys.
  10. Stop on login, captcha, payment, identity verification, destructive confirmation, or unclear UI state.

Read the full file on GitHub · 90 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 · 90 lines · 25 tokens per session scan A b75732a25eac

Subscribe to this mod's changes

browser-computer-use is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 25 tokens to every session and 891 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.