What is Browser4 CLAUDE.md?

Project instructions for Browser4, a browser automation system whose Rust command-line tool sends requests to a Kotlin web service and Chrome-based browser driver.

Understanding Browser4's command path, tool dispatch, batch commands, and end-to-end tests, which test the complete system from request to browser action.

They give an AI coding assistant the project's layout and request flow, so it can work in the right part of the codebase.

Browser4 CLAUDE.md — Instructions file by platonai

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 instructions/platonai/browser4/claude-md

Clone the repo

git clone --depth 1 https://github.com/platonai/Browser4

Per session 1,205 This file is loaded in full into every session.

When invoked 1,205 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01205	$0.01205
Opus 5	$0.00602	$0.00602
Sonnet 5	$0.00241	$0.00241
Haiku 4.5	$0.00120	$0.00120

Measured 2d ago against content hash e23151b01210, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Browser4 CLAUDE.md 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.

CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser4 — Project Context for Claude

Architecture

browser4-cli (Rust)  ──MCP over HTTP──▶  browser4-rest (Kotlin/Spring)  ──▶  PulsarWebDriver (Kotlin/CDP)
     ▲                                           │
     │                                           ▼
     └──── e2e tests ────▶  Fixture HTTP server (Rust test harness)

CLI: cli/browser4-cli/ — Rust binary, talks to backend via MCP tool calls
Backend: browser4-rest/ — Spring Boot, MCPToolController dispatches tools
Browser driver: browser4-core/browser4-browser/ — PulsarWebDriver wraps CDP (Chrome DevTools Protocol)
Agent tools: browser4-agentic/ — AgentToolManager maps MCP tool names → PulsarWebDriver methods

Key dispatch chain (CLI → browser)

CLI builds MCP tool call: {tool: "browser_type", arguments: {ref: "#el", text: "hi"}}
Backend MCPToolController.callTool() → dispatchToToolExecutor()
normalizeFrontendToolCall() applies FRONTEND_TOOL_NAME_ALIASES (e.g., browser_type → fill)
DefaultArgumentNormalizer maps ref → selector, strips sessionId, converts snake_case keys
resolveMcpToolCall() → ToolCall("tab", "fill", args)
AgentToolManager.execute() → executor.callFunctionOn(toolCall, driver) → PulsarWebDriver.fill()

Batch commands

Batch commands go through handleCommandBatch() → handleBatchTool() in MCPToolController. The CLI's compile_batch_request() builds step arrays with op: "tool" entries. preFocusSelector is only added for keydown/keyup steps (not fill/type/press).

E2E test structure

Tests live in cli/browser4-cli/tests/e2e/
scenarios/mod.rs — registry of all scenarios with requires_browser4, level, group
scenarios/browser.rs — tests against the real Browser4 backend
scenarios/batch.rs — batch-command tests against the real backend
scenarios/mock_server.rs — tests against MockBrowser4Server (no real backend needed)
Real-backend tests use HTML fixtures from browser4-tests/pulsar-tests-common/src/main/resources/static/b4/
State verification: wait_for_state_or_abort() polls read_interactive_state() which evals state-log.textContent

Read the full file on GitHub · 89 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.

2d ago First seen · 89 lines · 1,205 tokens per session scan A e23151b01210

Subscribe to this mod's changes

Browser4 CLAUDE.md is an instructions file published in the GitHub repository platonai/Browser4 (1,114 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,205 tokens to every session, about $0.0060 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 2026-08-30.

Browser automation Kotlin and Swift Languages Rust agentic-ai agentic-browser ai-browser browser-agent browser-infra browser-use-agent

Browser4 CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Browser4 — Project Context for Claude

Architecture

Key dispatch chain (CLI → browser)

Batch commands

E2E test structure

What this file has done since we first saw it

Other instructions, from other repositories

eric-task-master AGENTS.md

comet-mcp CLAUDE.md

browser-harness CLAUDE.md

intelligent-terminal rust-wta.instructions.md

intelligent-terminal rust.instructions.md

servo-fetch AGENTS.md