agentmods.dev

browseruse-agent-bench CLAUDE.md

browseruse-agent-bench CLAUDE.md is an instructions file for coding agents from lexmount/browseruse-agent-bench. It costs 1,419 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Claude Code sessions in a Python browser-agent benchmarking project. They link to the team's shared rules and list commands for running and evaluating benchmarks.

In plain words
What is it for?
Use them when working on benchmark agents, datasets, evaluation scripts or architecture-related changes in this repository.
Why use it?
They provide the project orientation and exact commands needed to start work and verify benchmark changes consistently.

Instructions file

not rated 19 1mo ago A scan 1,419 tokens original Apache-2.0
View the source file lexmount/browseruse-agent-bench
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/lexmount/browseruse-agent-bench/claude-md
Clone the repo
git clone --depth 1 https://github.com/lexmount/browseruse-agent-bench

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 browseruse-agent-bench CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lexmount/browseruse-agent-bench/claude-md.svg)](https://agentmods.dev/instructions/lexmount/browseruse-agent-bench/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lexmount/browseruse-agent-bench/claude-md"><img src="https://agentmods.dev/badge/instructions/lexmount/browseruse-agent-bench/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,419 This file is loaded in full into every session.
When invoked 1,419 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.

ModelPer sessionOnce invoked
Fable 5 $0.01419 $0.01419
Opus 5 $0.00709 $0.00709
Sonnet 5 $0.00284 $0.00284
Haiku 4.5 $0.00142 $0.00142

Measured 4d ago against content hash 14671f8d42a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browseruse-agent-bench 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 4d 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Team-wide agent rules

These are the single source of truth for coding conventions, layer boundaries, import/runtime rules, error handling, and testing in this repo. They apply to every coding agent. Read them first.

@AGENTS.md @docs_4_codeagent/coding-style.md @docs_4_codeagent/architecture-boundaries.md @docs_4_codeagent/imports-runtime-config.md @docs_4_codeagent/error-handling-testing.md

The sections below are bootstrap context specific to Claude Code sessions — architecture orientation and command cheatsheet. They do not override the imports above.

Commands

  • Run a benchmark: uv run scripts/run.py --agent <agent> --data <bench> --split <split> --mode first_n --count <n> (equivalent: bubench run ...).
  • Evaluate results: uv run scripts/eval.py --agent <agent> --data <bench> --split <split> --model-id <id> (equivalent: bubench eval ...).
  • Run then evaluate in one call: uv run scripts/run_and_eval.py --agent <agent> --data <bench> --mode <mode> (equivalent: bubench run-eval ...). Forwards run flags to the run stage, then derives the run's model_id and chains eval with an explicit --model-id (so passthrough models line up). --skip-eval stops after the run; eval is skipped if the run hard-fails.
  • Submit a LexBench job (not local run): bubench submit ....
  • Leaderboard / viz: bubench leaderboard, bubench server, bubench viz --watch.
  • Discover available benchmarks/splits, agents, and browser backends: bubench list (--json for machine-readable output).
  • All tests: uv run pytest tests/.
  • Single test: uv run pytest tests/browseruse_bench/test_task.py -v or ... -k <pattern>.
  • Integration tests (marked integration, require external tools / API keys) live under tests/integration/.

Install gotcha

Agent SDKs ship as mutually exclusive extras (declared in pyproject.toml under [tool.uv] conflicts): browser-use, skyvern, openai-cua pin incompatible Playwright versions. Install each into a separate venv when running multiple agents.

Read the full file on GitHub · 54 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. 4d ago First seen · 54 lines · 1,419 tokens per session scan A 14671f8d42a6

Subscribe to this mod's changes

browseruse-agent-bench CLAUDE.md is an instructions file published in the GitHub repository lexmount/browseruse-agent-bench (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,419 tokens to every session, about $0.0071 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.

agentagent-evaluationai-agentsbenchmarkbrowser-agentbrowseruse
Related

Other instructions, from other repositories

DM-Code-Agent AGENTS.md

Instructions for hwfengcs/DM-Code-Agent, covering agents.md, project intent, development rules, verification and important modules.

hwfengcs/DM-Code-Agent · 1,264 tokens

WorldCupArena CLAUDE.md

Instructions for wzk1015/WorldCupArena, covering project goal, key files, development process, coding style and running the website locally.

wzk1015/WorldCupArena · 604 tokens

hermes-skilleval AGENTS.md

AGENTS.md instructions for Raidriar7170/hermes-skilleval, a project described as: Verification-gated skill routing and self-improvement harness for Hermes-style agent skills.

Raidriar7170/hermes-skilleval · 363 tokens

intelligent-terminal rust.instructions.md

Concise Rust coding conventions for this repository.

microsoft/intelligent-terminal · 435 tokens

Browser4 CLAUDE.md

Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

InvestSkill GEMINI.md

Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).

yennanliu/InvestSkill · 3,074 tokens