A headless browser tool, meaning a web browser controlled without a visible window, for checking websites and testing interactions.

It is for loading pages, taking screenshots, listing interactive elements, clicking and filling forms, and capturing accessibility snapshots.

It lets you inspect pages and verify browser behavior without performing each check manually in a graphical browser.

browse — Command for Claude Code by ShaheerKhawaja

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.

Clone the repo

git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOS

Made for: Claude Code.

Or install productionos, the plugin that ships this one along with the rest of its 4 skills, 41 commands, 11 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/browse/github.svg)](https://agentmods.dev/commands/shaheerkhawaja/productionos/browse)

Your own site

<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/browse"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/browse/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/shaheerkhawaja/productionos/browse"><img src="https://agentmods.dev/badge/commands/shaheerkhawaja/productionos/browse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 307 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00307
Opus 5	$0.00014	$0.00153
Sonnet 5	$0.00006	$0.00061
Haiku 4.5	$0.00003	$0.00031

Measured 10d ago against content hash 9650a7be64f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

browse 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 10d 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.

.claude/commands/browse.md · 47 lines

What it actually says

/browse — Headless Browser Interaction

Control a headless browser for testing, QA, and site inspection.

Step 0: Preamble

Run templates/PREAMBLE.md.

Execution

Dispatch browser-controller agent:

Read agents/browser-controller.md
Dispatch with:
  URL: $ARGUMENTS.url
  Action: $ARGUMENTS.action
  Output: .productionos/browse/

Actions

navigate — Load page, report status

Navigate to URL, report HTTP status, page title, key elements found.

screenshot — Full-page capture

Navigate + capture full-page screenshot. Save to .productionos/browse/screenshot-{timestamp}.png.

interact — Interactive session

Navigate + describe all interactive elements (buttons, forms, links). Execute user-directed interactions.

snapshot — Accessibility tree

Navigate + capture full accessibility snapshot. Report missing labels, roles, ARIA attributes.

Self-Eval

After browsing, run templates/SELF-EVAL-PROTOCOL.md on findings quality.

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.

10d ago First seen · 47 lines · 28 tokens per session scan A 9650a7be64f5

Subscribe to this mod's changes

browse is a command published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 307 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.

Browser automation Claude Code E2E testing Multi-Agent Testing agentic-development claude-code-plugin llm-judge prompt-engineering

browse