weavebench-cua-reproduce

weavebench-cua-reproduce is a skill for Codex from AMAP-ML/LongHorizon-Harness. It costs 81 tokens per session (1,568 once invoked), scanned A, original, MIT.

A reproduction guide for WeaveBench CUA-Harness experiments. WeaveBench is a benchmark for evaluating computer-using agents, and CUA-Harness is the system that runs those evaluations.

In plain words
What is it for?
It helps download official benchmark assets, prepare a 120GB Ubuntu virtual machine, configure supported model APIs, run smoke tests or evaluations, inspect logs, and summarize scores.
Why use it?
It provides a defined path for preparing the required repositories, virtual-machine assets, APIs, and local evaluation environment.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; built for openclaw.

Good fit It helps download official benchmark assets, prepare a 120GB Ubuntu virtual machine, configure supported model APIs, run smoke tests or evaluations, inspect logs, and summarize scores.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amap-ml/longhorizon-harness/weavebench-cua-reproduce
About the project

LongHorizon-Harness is a computer-use harness that lets AI agents continue work across desktop applications and the command line for extended periods by planning, acting, verifying, checkpointing, and recovering. It is for users who need Claude Code, Codex, OpenCode, or DeepSeek Harness to make reliable progress on complex long-running workflows without training a new model. The catalogue entries provide skills for operating this execution loop.

AMAP-ML/LongHorizon-Harness · 1,497 stars · on GitHub · lh-harness.pages.dev

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.

Any agent
npx skills add AMAP-ML/LongHorizon-Harness --skill weavebench-cua-reproduce
Clone the repo
git clone --depth 1 https://github.com/AMAP-ML/LongHorizon-Harness

Made for: Codex.

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 weavebench-cua-reproduce

README.md
[![agentmods](https://agentmods.dev/badge/skills/amap-ml/longhorizon-harness/weavebench-cua-reproduce/github.svg)](https://agentmods.dev/skills/amap-ml/longhorizon-harness/weavebench-cua-reproduce)
Your own site
<a href="https://agentmods.dev/skills/amap-ml/longhorizon-harness/weavebench-cua-reproduce"><img src="https://agentmods.dev/badge/skills/amap-ml/longhorizon-harness/weavebench-cua-reproduce/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.

agentmods 80×15 button for weavebench-cua-reproduce

Your own site · 80×15
<a href="https://agentmods.dev/skills/amap-ml/longhorizon-harness/weavebench-cua-reproduce"><img src="https://agentmods.dev/badge/skills/amap-ml/longhorizon-harness/weavebench-cua-reproduce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00081 $0.01568
Opus 5 $0.00041 $0.00784
Sonnet 5 $0.00016 $0.00314
Haiku 4.5 $0.00008 $0.00157

Measured 13d ago against content hash 3ad149599e4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

weavebench-cua-reproduce 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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/reproduce.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

eval/WeaveBench-harness/skills/weavebench-cua-reproduce/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WeaveBench CUA-Harness Reproduction

Use this skill to guide an agent through a complete, reproducible WeaveBench CUA-Harness run. The expected repository layout is:

WeaveBench-harness/
  WeaveBench/
  cua-harness/
  skills/weavebench-cua-reproduce/

Do not invent alternate launch commands. Prefer the bundled helper script and the project scripts under WeaveBench/scripts/.

Supported Scope

Supported automation:

  • Local Docker/KVM WeaveBench evaluation.
  • Qwen 3.7-Plus through an Anthropic-compatible endpoint.
  • Claude Code execution backend through cua_harness_claudecode.
  • OpenClaw judge setup and verification.
  • Official WeaveBench assets downloaded from the HuggingFace dataset.
  • A 120G copy of the official Ubuntu qcow2 plus per-task rootfs growth.

Not automated:

  • Cloud VM provisioning.
  • Public image-hosting service deployment.
  • New model-provider adapters beyond the existing Anthropic-compatible path.
  • Non-Claude-Code execution backend reproduction.
  • Deleting or pruning existing results.

If the user requests unsupported automation, explain the boundary and provide the closest supported local Docker/KVM path.

Start With Intake

Before doing setup work on a new machine, run or mentally follow:

./skills/weavebench-cua-reproduce/scripts/reproduce.sh intake

Confirm:

  • Linux Docker/KVM is available or installable.
  • The user accepts large downloads and creation of Ubuntu_120G.qcow2.
  • The model endpoint and API key are available.
  • Image proxy should be enabled with public upload/show URLs, or disabled because the endpoint accepts large base64 screenshots.
  • The desired scope is doctor, smoke, subset, or full 114-task evaluation.
  • Long-running/full evaluation is allowed, especially if other experiments may already be active.

Workflow

  1. Locate the project root. It must contain both WeaveBench/ and cua-harness/.
  2. Read references/configuration.md when you need exact defaults, environment variables, or paths.
  3. Read references/assets.md before downloading or validating WeaveBench tasks, runtime assets, judge templates, or VM files.
  4. Read references/verify.md before reporting whether setup or a run is actually verified.
  5. Read references/troubleshooting.md when setup, VM, API, image proxy, warmup, or judge errors occur.
  6. Ask the user for missing API details only when they are required and not discoverable from the environment.
  7. Run commands from the project root unless a command explicitly changes into WeaveBench/.

Read the full file on GitHub · 178 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 178 lines · 81 tokens per session scan A 3ad149599e4f

Subscribe to this mod's changes

weavebench-cua-reproduce is a skill published in the GitHub repository AMAP-ML/LongHorizon-Harness (1,497 stars, last pushed 23d ago), licensed MIT. It adds 81 tokens to every session and 1,568 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

remote-claude-code

Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…

Prism-Shadow/penguin-harness · 107 tokens

web-design

Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.

Prism-Shadow/penguin-harness · 51 tokens

agent-optimization

Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.

Prism-Shadow/penguin-harness · 22 tokens

agent-evaluation

Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.

Prism-Shadow/penguin-harness · 28 tokens