# FAQ

The questions engineers ask first - about agents, rules, privacy, platforms and price.

## Do I give up Claude Code or Codex?

No. Same agent, same subscription, same sign-in. You sign in once in its own CLI, as today, then work with it in Warden's window, beside an editor, instead of the terminal. See [Connect your models](models).

## Is an AI deciding what's safe?

No. A policy engine applies your rules. The same action under the same rules always gets the same verdict, and every verdict names the rule behind it. Models do the work; rules decide what the work may do.

## Why not just use Claude Code's own settings?

Its allow and deny lists match command text. Warden reads what a command does: it unwraps `sudo`, `sh -c` and `../` paths before it checks, so `cat .env` is caught through all of them, and commands it can't read in advance are asked about on Guarded. One rule file covers every agent you run in Warden. See [How Warden decides](how-it-decides).

## Can I make it deny-by-default?

Yes. Set `default: deny` and your file becomes a strict allow-list: a tool call runs only if a rule allows it. The rule sets use `default: allow` with a deny list instead, because a strict allow-list blocks even reading a README until you add a rule for it. See [A strict allow-list](rule-recipes#a-strict-allow-list).

## Can the agent use my MCP servers and skills?

Yes, once you connect them in Warden; they are handed to the agent. Your skills and workflows run from the chat as slash commands. See [Integrations](integrations) and [Agents and skills](agents-and-skills).

## Does it check Claude Code in my terminal too?

No, only agents you run in Warden. See [Known limitations](limitations).

## What if it can't tell what a command does?

On Open it runs; on Guarded it asks you; on Hardened it blocks it. `eval`, `$(...)`, backticks and inline `python -c` count as unreadable.

## What happens if the policy engine isn't running?

Warden fails closed. Actions in a chat need your manual approval, and automated runs are held.

## Where does my code go?

Only to the model you choose. Never to us on the Developer edition. On Team, it passes through Pluto only if your company uses our hosted AI gateway; point the gateway at your own proxy and it never does.

## On Team, what does Pluto hold?

Your rules, skills, plans and specs, and anything written in them. Never your repository. See [Warden Team](team).

## Can I use the free edition at work?

Yes. It is licensed for commercial work: for your employer, your clients or your own company. Your employer's own rules on new tools still apply.

## What does it cost?

Developer is free, including at work. Team is priced per seat plus a one-time setup fee, under a commercial licence and MSA.

## Windows, Linux or Intel Macs?

Not yet. Apple Silicon Macs (M1 or later) only, for now.

## How do I update?

Warden updates itself when a new version ships.

## How does Warden relate to goose?

Warden is built on the open-source [goose](https://github.com/block/goose) agent (Apache 2.0), with Pluto's policy engine and the Warden app around it.

## Where do I report a bug or a way past a rule?

Bugs and feature requests: the [Warden issue tracker](https://github.com/plutocoach/warden/issues). A way past a rule: please report it **privately** through [security advisories](https://github.com/plutocoach/warden/security/advisories/new).