agentmods.dev

agent-os

agent-os is a skill for Claude Code, Codex from dinglebear-ai/dendrite. It costs 123 tokens per session (3,874 once invoked), scanned B, original, AGPL-3.0.

A set of instructions for controlling and testing the agent-os Windows 11 sandbox, a separate Windows virtual machine, through Windows-MCP.

In plain words
What is it for?
Use it to run commands, take screenshots, test desktop applications, install software, or inspect the Windows sandbox.
Why use it?
It provides guidance for working with Windows desktops, programs, files, settings, and installers from an agent.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the agent-os plugin — 1 skill, 1 command shipped together

not rated 1repo changed 2mo ago B scan 123 tokens AGPL-3.0

Good fit Use it to run commands, take screenshots, test desktop applications, install software, or inspect the Windows sandbox.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dinglebear-ai/dendrite/agent-os
View source ↗ dinglebear-ai/dendrite
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 dinglebear-ai/dendrite --skill agent-os
Clone the repo
git clone --depth 1 https://github.com/dinglebear-ai/dendrite

Made for: Claude Code, Codex.

Or install agent-os, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 agent-os

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dinglebear-ai/dendrite/agent-os"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/dendrite/agent-os.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,874 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00123 $0.03874
Opus 5.5 $0.00049 $0.01550
Sonnet 5.5 $0.00025 $0.00775
Haiku 4.5 $0.00012 $0.00387

Measured 2mo ago against content hash 383902084ae5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agent-os scanned grade B with 1 finding 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

3. **Client (this plugin).** The `agent-os` plugin's `.mcp.json` registers the `windows-mcp` server from your userConfig via `${user_config.*}` substitution. Set the URL + token in plugin settings; there's nothing to edi
plugins/agent-os/skills/agent-os/SKILL.md · 161 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 2mo ago Changed 383902084ae5
  2. 2mo ago First seen · 161 lines · 123 tokens per session scan B c5949f9fa468

Subscribe to this mod's changes

agent-os is a skill published in the GitHub repository dinglebear-ai/dendrite (1 stars, last pushed 1mo ago), licensed AGPL-3.0. It adds 123 tokens to every session and 3,874 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automationClaude Codeagent-skillsai-agentsclaudecodexgemini-cli
Related

agent-os compared with skills from other repositories

agent-os next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-osdinglebear-ai/dendriteSkill11mo agoAGPL-3.0B123Claude Code, Codex
chatcut-editor-handoffChatCut-Inc/agent-pluginSkill1.0k2d agoApache-2.0A77Claude Code, Codex
ui-regressionfcakyon/claude-codex-settingsSkill1.2ktodayApache-2.0A87Claude Code
run-qafcakyon/claude-codex-settingsSkill1.2ktodayApache-2.0A51Claude Code
tavily-usagefcakyon/claude-codex-settingsSkill1.2ktodayApache-2.0A57Claude Code
agent-browsercafe3310/public-agent-skillsSkill2569d agoApache-2.0A36Claude Code
lov-fill-web-formlovstudio/skillsSkill724d agoMITA146Claude Code