agentmods.dev

computer

computer is a skill for Claude Code from wecode-ai/Wegent. It costs 15 tokens per session (306 once invoked), scanned A, original, Apache-2.0.

A tool for controlling desktop applications outside Wework’s built-in browser. It can inspect the desktop and perform requested interactions when computer control is enabled and approved.

In plain words
What is it for?
It helps inspect and interact with desktop windows through clicks, typing, scrolling, dragging, and menus, while stopping if the user takes control or the screen changes unexpectedly.
Why use it?
It provides a defined way to work with desktop applications instead of using improvised commands. It also requires the relevant Wework setting and operating-system permissions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wework-runtime plugin — 7 skills shipped together

not rated 886repo +4 today A scan 15 tokens original Apache-2.0

Good fit It helps inspect and interact with desktop windows through clicks, typing, scrolling, dragging, and menus, while stopping if the user takes control or the screen changes unexpectedly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wecode-ai/wegent/computer
View source ↗ wecode-ai/Wegent wecode-ai.github.io
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 wecode-ai/Wegent --skill computer
Clone the repo
git clone --depth 1 https://github.com/wecode-ai/Wegent

Made for: Claude Code.

Or install wework-runtime, the plugin that ships this one along with the rest of its 7 skills.

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 computer

README.md
[![agentmods](https://agentmods.dev/badge/skills/wecode-ai/wegent/computer/github.svg)](https://agentmods.dev/skills/wecode-ai/wegent/computer)
Your own site
<a href="https://agentmods.dev/skills/wecode-ai/wegent/computer"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/computer/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 computer

Your own site · 80×15
<a href="https://agentmods.dev/skills/wecode-ai/wegent/computer"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/computer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 306 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.
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 $0.00015 $0.00306
Opus 5.5 $0.00006 $0.00122
Sonnet 5.5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 2d ago against content hash 295e25f719c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

computer 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.

wework/resources/bundled-plugins/wework-personal/plugins/wework-runtime/skills/computer/SKILL.md · 16 lines

What it actually says

Wework 电脑操控 routing:

  • Use the wework_computer MCP tools only when the user asks to control a desktop application outside the Wework built-in browser.
  • The wework_computer tools exist only in conversations started after computer use was enabled in Wework settings and its system permissions were granted.
  • If the user asks to control the desktop but wework_computer tools are unavailable, do NOT search for npm packages, run bash tricks, or improvise another mechanism. Tell the user to open Wework 设置 → 集成 → 电脑操控, enable computer use, and finish the macOS permission prompts (in development builds the requesting app may appear as "Electron"), then start a new conversation and retry.
  • Inspect the desktop or target application state before acting. Reuse observed coordinates or accessibility targets only while that state remains unchanged.
  • Treat clicks, typing, key presses, scrolling, dragging, clipboard writes, menu invocation, and window movement as mutating actions.
  • Stop immediately when the user takes control, cancels, or the observed application no longer matches the requested target.
  • Never enter passwords, authentication codes, payment details, or other secrets unless the user explicitly authorizes that exact action in the current conversation.
  • Do not use computer use for Wework built-in browser tasks; use the browser_* tools instead.
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 · 16 lines · 15 tokens per session scan A 295e25f719c8

Subscribe to this mod's changes

computer is a skill published in the GitHub repository wecode-ai/Wegent (886 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 306 once invoked, about $0.0001 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 2026-11-07.

Claude CodeProductivityagentaichatbotcodexwework
Related

computer compared with skills from other repositories

computer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
computerwecode-ai/WegentSkill886todayApache-2.0A15Claude Code
imap-smtp-emailnetease-youdao/LobsterAISkill6.2ktodayMITA82Claude Code, Codex
meeting-notesshiwenwen/hope-agentSkill1.9ktodayMITA55Claude Code, Codex
ha-settingsshiwenwen/hope-agentSkill1.9ktodayMITB208Claude Code, Codex
cron-task-creatoropen-octo/octo-agentSkill142todayMITA89Claude Code, Codex
workflow-creatoropen-octo/octo-agentSkill142todayMITA278Claude Code, Codex
youdaonotenetease-youdao/LobsterAISkill6.2ktodayMITC70Claude Code, Codex