Enters and exits the MX Maintenance Hangar to perform governance repairs.
Install
mkdir -p .claude/skills/gz-mx && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19262" && unzip -o skill.zip -d .claude/skills/gz-mx && rm skill.zipInstalls to .claude/skills/gz-mx
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Enter and exit the MX Maintenance Hangar — operator's interface to gz mx. Use when entering the hangar to perform governance repair, checking hangar status mid-session, or cleanly exiting when repair is complete. Operator operates the skill; the skill invokes gz mx; nobody shells out.Key capabilities
- →Enter the MX Maintenance Hangar to begin governance repair
- →Check the current status of the maintenance hangar mid-session
- →Cleanly exit the hangar when repair is complete
- →Temporarily lower non-critical governance guards to advisory
- →Re-enforce all guards at full strength upon exit
How it works
It manages a governance repair session by allowing entry into a maintenance hangar, temporarily lowering non-critical guards. It ensures that critical invariants remain active and all guards are re-enforced upon exit.
Inputs & outputs
When to use gz-mx
- →Enter the maintenance hangar to begin a repair
- →Check the current status of the maintenance hangar
- →Close the hangar and re-enforce all security guards
About this skill
gz mx
Overview
The MX Maintenance Hangar lets the operator repair governance surfaces that
the guards themselves protect. While the hangar is open, most governance
guards drop to advisory so repair work can proceed without the checked-in
surfaces blocking the repair itself. Two guards NEVER drop: gate5_invariants
and the PRIME DIRECTIVE (ownership — "fix what you know AND what you find").
The operator operates this skill; the skill invokes gz mx; nobody shells
out to gz mx enter or gz mx exit directly.
When to Use
- Entering the hangar — governance repair session needs to begin; guards need to go advisory so you can fix the surfaces they protect
- Checking hangar status — confirming whether the hangar is currently open mid-session
- Clean exit — repair is complete; re-enforce all guards at full strength
Workflow
-
Open the hangar
uv run gz mx enterCreates
.gzkit/mx.jsonmarker. Most governance guards drop to advisory. -
Perform the repair Work on the governance surfaces that needed fixing. Gate 5 invariants and the PRIME DIRECTIVE still bind — guards drop to advisory so you can repair governance itself, not so defects can be deferred.
-
Close the hangar
uv run gz mx exitRemoves
.gzkit/mx.jsonmarker. Every guard re-runs at full strength; exit is a hard gate (all guards must pass before exit succeeds).
Example
# Enter the hangar to repair a drifted OBPI brief
uv run gz mx enter
# Perform repair work (briefs, rules, docs)
# ...
# Exit — guards re-enforce; exit fails if any guard is still red
uv run gz mx exit
Constraints
- Operator operates the skill; the skill invokes
gz mx; nobody shells out gate5_invariantsand the PRIME DIRECTIVE bind throughout the session- Exit is a hard gate — do not attempt exit until all detectable defects are fixed
- See
.gzkit/rules/mx-mode.mdfor the binding agent rule for hangar sessions
When not to use it
- →When the task does not involve governance repair
- →When `gate5_invariants` or the PRIME DIRECTIVE need to be dropped
- →When defects can be deferred instead of fixed
Limitations
- →`gate5_invariants` and the PRIME DIRECTIVE bind throughout the session
- →Exit is a hard gate , do not attempt exit until all detectable defects are fixed
- →Operator operates the skill; the skill invokes `gz mx`; nobody shells out
How it compares
This skill provides a controlled environment for governance repair by selectively adjusting guard enforcement, which is more structured than manually disabling or re-enabling security checks.
Compared to similar skills
gz-mx side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gz-mx (this skill) | 0 | 1mo | Review | Intermediate |
| azure-role-selector | 0 | 5mo | No flags | Intermediate |
| secrets-management | 5 | 3mo | Review | Advanced |
| healthcheck | 10 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by tvproductions
View all by tvproductions →You might also like
azure-role-selector
Tyler-R-Kendrick
|
secrets-management
wshobson
Implement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.
healthcheck
openclaw
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
linkerd-patterns
wshobson
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
linux-production-shell-scripts
davila7
This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration.
secops-setup-antigravity
Helps the user configure the Google SecOps Remote MCP Server for Antigravity. Use this when the user asks to "set up" or "configure" the security tools for Antigravity.