agentmods.dev

browseruse-agent-bench AGENTS.md

Repository instructions for a Python benchmark framework that tests browser-using agents and connections to different service providers.

In plain words
What is it for?
Use them when modifying browser benchmarks, provider integrations, tests or scripts. They also specify how to run a real benchmark and complete the required review.
Why use it?
They give coding agents the project's required Python setup, code boundaries, logging and error-handling rules, plus checks needed before changes are committed or proposed.

Instructions file for CodexOpenCode

19 1mo ago A scan 386 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/agents-md
Clone the repo
git clone --depth 1 https://github.com/lexmount/browseruse-agent-bench

Made for: Codex, OpenCode.

Per session 386 This file is loaded in full into every session.
When invoked 386 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 $0.00386 $0.00386
Opus 5 $0.00193 $0.00193
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00039 $0.00039

Measured 2d ago against content hash 8ff32523d95d, 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 AGENTS.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.

AGENTS.md · 26 lines

What it actually says

browseruse_bench Agent Instructions

Python benchmark framework for browser agents and provider integrations.

Essentials

  • Python version: >=3.11 (use uv, not system Python).
  • Install dev tools: uv sync --extra dev.
  • Run tests: uv run pytest tests/.
  • Run scripts: uv run python ....
  • Make the smallest correct change with clear control flow.
  • Keep optional dependency isolation in registry/router lazy-load factories.
  • Keep provider modules direct and fail-fast when selected.
  • Use logger for logs; do not use print().
  • Catch specific exceptions only; do not use bare except: or except Exception:.
  • Before committing agent-touching changes, run a real bubench run --agent <agent> --data LexBench-Browser --mode single (not --dry-run, not pytest-only). See Smoke Testing Before Commit.
  • Before opening or updating a PR, complete the Mandatory Self-Review and tick the self-review checklist in the PR template. This applies to humans and coding agents alike.

Detailed Instructions

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. 2d ago First seen · 26 lines · 386 tokens per session scan A 8ff32523d95d

Subscribe to this mod's changes

browseruse-agent-bench AGENTS.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 386 tokens to every session, about $0.0019 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 automationCode reviewTestingagentagent-evaluationai-agentsbenchmarkbrowser-agentbrowseruse
Related

Other instructions, from other repositories

nanobrowser CLAUDE.md

Instructions for nanobrowser/nanobrowser, covering claude.md, project overview, development commands, workspace tips and architecture.

nanobrowser/nanobrowser · 2,693 tokens

browser-harness CLAUDE.md

Instructions for browser-use/browser-harness, a project described as: Browser Harness | Self-healing harness that enables LLMs to complete any task.

browser-use/browser-harness · 39 tokens

browser-control AGENTS.md

Instructions for keon/browser-control: Use this project as a tiny browser pipe, not an agent framework.

keon/browser-control · 484 tokens

Browser4 CLAUDE.md

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

nuwax AGENTS.md

Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.

nuwax-ai/nuwax · 5,807 tokens

serve-sim AGENTS.md

Instructions for EvanBacon/serve-sim, covering native build notes, e2e testing with agent-browser and e2e testing via the serve-sim cli.

EvanBacon/serve-sim · 919 tokens