> ## Documentation Index
> Fetch the complete documentation index at: https://docs.guardway.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Skill Custody
> Stop a blocked skill in every AI tool on a machine, not only in Claude Code, and read what the console says about it.
## What this is for
When your organization blocks a skill in the AI Control skill catalog, Claude Code denies it on
every enrolled machine. Other AI tools (Antigravity, Gemini CLI, Codex, Copilot, Windsurf) load
skills from their own folders and have no such check. **Skill custody** closes that gap: on managed
machines, the agent moves the blocked skill's folder out of every tool's skill directory and leaves
a short notice in its place, so no AI tool on the machine can load it.
Custody never deletes anything. When the block is lifted, or custody is turned off, the skill goes
back exactly where it was, owned by the same person.
## Options
Custody acts on a machine only when **all four** of these are true:
| Condition | Where it is set |
| --------------------------------------- | ----------------------------------------------------------------------------------------- |
| **Block skills in every AI tool** is on | The Detection Policy that governs the machine, or the machine's own managed configuration |
| Skill lockdown is on enforce | The AI Control policy |
| The machine runs the **managed** agent | Installed by your MDM with the managed package. Per-user installs never move skills |
| Break-glass is off | On the machine |
**Block skills in every AI tool** can only turn custody **on**. It never turns it off on a machine
where an administrator turned it on locally. Changes reach machines at their next policy refresh,
with no restart.
## How to configure
Add the skill to the blocked list in the AI Control skill catalog, and set skill lockdown to
enforce.
Open the Detection Policy that covers the machines, go to **Live guard**, and turn on
**Block skills in every AI tool**. Publish the policy.
Open an endpoint and go to **Skills & findings**. The custody panel shows whether blocked skills
are held on that machine.
Roll out to a pilot group first. Before you turn custody on, the panel already counts blocked
skills it **would** hold, so you can see the blast radius without moving a file.
## What the console shows
The panel on **Skills & findings** says whether custody is enforcing on that machine and, when it
is not, the first thing to change:
| Status | What it means | What to do |
| -------------------------------- | -------------------------------------------------------------------- | ----------------------------------------------------------------- |
| **Enforcing** | Blocked skills are held on this machine, so no AI tool can load them | Nothing |
| **Break-glass is on** | Custody stands down while break-glass is active | Clear break-glass on the machine |
| **User-context install** | A per-user install never moves skills | Deploy the managed agent to the machine |
| **Custody is switched off** | The machine is not told to hold skills | Turn on **Block skills in every AI tool** in its Detection Policy |
| **Skill lockdown is on observe** | The AI Control policy does not enforce skill lockdown | Set skill lockdown to enforce |
| **Unknown** | The agent is too old to report custody | Upgrade the agent |
When custody is on, the panel also says who turned it on: **Turned on by policy** or **Turned on
locally on this machine**.
Each blocked skill carries a chip:
| Chip | Meaning |
| ------------------------ | ------------------------------------------------------------------------------------ |
| **Held** | Custody moved the skill out of every tool's folder |
| **Held, notice pending** | The skill is held and its notice is still being written |
| **Not moved** | A blocked skill inside a code repository. Custody reports these but never moves them |
| **Restore conflict** | Custody could not give this skill back: something now occupies its original path |
| **Custody failed** | Custody could not act on this skill. See the section below |
**Watching** means the machine reacts to a new blocked skill within seconds. **Watching, partial**
means some skill folders could not be watched and rely on the regular rescan every few minutes.
A **Partial coverage** box lists skill folders the agent could not read at all.
## When custody refuses to act
Custody never follows a folder shortcut (symlink) it did not create. If a developer's skill folder,
or any folder between their home and it, is a symlink, custody refuses to act there. The most common
case is `~/.claude` linked into a dotfiles repository. The skill stays usable in every tool, and the
console shows **Custody failed** for it instead of reporting it as held.
To cover that developer, have them use a real folder for the tool's skills, or remove the skill from
the dotfiles repository it comes from.
## Removing the agent
Uninstalling the agent gives every held skill back **before** anything is removed. If a skill cannot
go back, the uninstaller keeps the agent's data folder and prints where the skill is held. Do not
delete the agent's data folder by hand to clean up: that folder is where held skills live. See
[Uninstall & Recovery](/discovery/guardway-cli/uninstall).
A small notice file named `.guardway-tombstone` inside a skill folder is custody's notice. Do not
delete it by hand: the skill is held by the agent, and the notice is how it gets back.
## Limits
* Custody covers the skill folders of the AI tools the agent knows about. A tool that loads skills
from somewhere else is detected but not covered.
* Skills inside code repositories are reported as **Not moved** and never moved.
* Custody acts on managed machines only.
## Related
* [Uninstall & Recovery](/discovery/guardway-cli/uninstall)
* [Inventory](/discovery/guardway-cli/inventory)
* [Findings](/discovery/findings)