browser-controller

browser-controller is an agent for coding agents from ShaheerKhawaja/ProductionOS. It costs 32 tokens per session (1,493 once invoked), scanned A, original, MIT.

A headless-browser control agent for testing websites without manually using a browser. It can navigate pages, take screenshots, interact with forms, capture page structure, and inspect accessibility.

In plain words
What is it for?
It supports page and element screenshots, before-and-after checks for clicks and form flows, page snapshots, accessibility reviews, and recorded browser interactions.
Why use it?
It verifies what users actually see and what interactions actually do, helping find visual, functional, and accessibility problems.

Agent

Part of the productionos plugin — 4 skills, 41 commands, 11 agents shipped together

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 agents/shaheerkhawaja/productionos/browser-controller
Clone the repo
git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOS

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.

agentmods badge for browser-controller

README.md
[![agentmods](https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/browser-controller.svg)](https://agentmods.dev/agents/shaheerkhawaja/productionos/browser-controller)
Your own site
<a href="https://agentmods.dev/agents/shaheerkhawaja/productionos/browser-controller"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/browser-controller.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00032 $0.01493
Opus 5 $0.00016 $0.00746
Sonnet 5 $0.00006 $0.00299
Haiku 4.5 $0.00003 $0.00149

Measured 3d ago against content hash e323d294b125, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-controller scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

# Last resort: curl for basic page fetch
agents/browser-controller.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProductionOS Browser Controller

Capabilities

Navigate

# Prefer Playwright MCP tools if available (mcp__plugin_playwright_playwright__*)
# Fallback: Playwright CLI
npx playwright open "$URL" --browser chromium 2>/dev/null
# Last resort: curl for basic page fetch
curl -s "$URL" | head -200

Screenshot Workflow

  1. Navigate to the target URL
  2. Wait for network idle (no pending requests for 500ms)
  3. Take full-page screenshot
  4. Take viewport-only screenshot for above-the-fold analysis
  5. Take element-level screenshots for specific components if requested
npx playwright screenshot "$URL" --full-page screenshot-full.png 2>/dev/null
npx playwright screenshot "$URL" screenshot-viewport.png 2>/dev/null

Interaction Protocol

For form fills, clicks, navigation sequences:

  1. Take a "before" snapshot/screenshot
  2. Perform the interaction
  3. Wait for the page to settle (network idle + animation complete)
  4. Take an "after" snapshot/screenshot
  5. Diff the before/after to verify the interaction had the expected effect
# Use Playwright codegen for complex interaction recording
npx playwright codegen "$URL" 2>/dev/null

Accessibility Snapshot

Capture the full accessibility tree:

  1. Navigate to the page
  2. Capture the accessibility snapshot (ARIA tree)
  3. Cross-reference with visual rendering
  4. Identify mismatches (visible but not accessible, or accessible but hidden)

Page Health Check

Run a systematic health check on any page:

  1. HTTP status — verify 200, flag any non-200 responses
  2. Console errors — capture and categorize JS errors
  3. Network failures — identify failed resource loads (images, fonts, scripts)
  4. Performance — measure DOMContentLoaded, LCP, CLS, INP
  5. Responsive — check viewport meta tag, test at 375px/768px/1440px widths
  6. Links — verify internal links resolve (no 404s)
  7. Forms — verify all inputs have labels, submit actions exist
  8. Images — verify alt text on meaningful images
  9. Contrast — flag text with insufficient color contrast

Read the full file on GitHub · 167 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. 3d ago First seen · 167 lines · 32 tokens per session scan A e323d294b125

Subscribe to this mod's changes

browser-controller is an agent published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,493 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

qa-tester

The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…

a-lottes/aSPARK · 79 tokens

balrog

Adversarial validation agent. Spawned by quest between Implement and Review phases. Analyzes the quest diff for failure modes, writes targeted test cases, runs them, and delivers a severity-ranked findings report. Critical/High findings must be addressed before the Review gate opens.

justinjdev/fellowship · 58 tokens

palantir

Background monitor during fellowship execution. Watches quest progress via task metadata, detects stuck quests, scope drift, and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.

justinjdev/fellowship · 46 tokens

_protocol

Canonical spec for how fellowship agents deliver reports and respond to lifecycle events via SendMessage.

justinjdev/fellowship · 0 tokens

quest-runner

Quest executor that uses the fellowship CLI for gate management. Runs the full quest lifecycle (Onboard through Research, Plan, Implement, Review, Complete) with structural gate enforcement via the fellowship binary.

justinjdev/fellowship · 43 tokens

scout

Research & analysis agent. Investigates questions and analyzes codebases without modifying source code. Can write research notes to docs/research/ or .fellowship/. No git operations, no commits, no PRs.

justinjdev/fellowship · 46 tokens