Borrowing it
Nothing to install: this file belongs to lexmount/browseruse-agent-bench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lexmount/browseruse-agent-bench/main/CLAUDE.mdgit clone --depth 1 https://github.com/lexmount/browseruse-agent-benchWrote 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.
[](https://agentmods.dev/instructions/lexmount/browseruse-agent-bench/claude-md)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01419 | $0.01419 |
| Opus 5.5 | $0.00568 | $0.00568 |
| Sonnet 5.5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
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 2mo 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.
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 chainsevalwith an explicit--model-id(so passthrough models line up).--skip-evalstops 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(--jsonfor machine-readable output). - All tests:
uv run pytest tests/. - Single test:
uv run pytest tests/browseruse_bench/test_task.py -vor... -k <pattern>. - Integration tests (marked
integration, require external tools / API keys) live undertests/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.
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.
- 2mo ago First seen · 54 lines · 1,419 tokens per session scan A 14671f8d42a6
browseruse-agent-bench CLAUDE.md is an instructions file published in the GitHub repository lexmount/browseruse-agent-bench (21 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,419 tokens to every session, about $0.0057 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.