
Brigade Host Hardening
Audits and hardens the machine running Brigade, with explicit approval before changes
- Repository
- spinabot/brigade
- Stars
- 11,367
- Licence
- MIT
- Files
- 1 file
What it does
When installed, the agent checks the security posture of the computer or server running the Brigade assistant: open ports, firewall, SSH access, disk encryption, backups, and update status. It runs Brigade's own security audit and version check, then proposes a numbered remediation plan matched to a risk level you choose. The skill says it will show every command and rollback step and wait for your approval before changing anything.
Great for
- Someone who runs Brigade on a personal laptop, workstation, Raspberry Pi or VPS and wants a security review
- Users who want a step-by-step plan rather than making firewall or SSH changes themselves
- Admins setting up an always-on Brigade gateway on a remote server
Skip it if
- Users who expect Brigade to manage their firewall, SSH or OS updates: the skill states Brigade does not change these, so the agent must make those changes with separate commands, and a mistake can lock you out of remote access
- Shared or corporate machines where another administrator owns the security policy, since the agent may suggest changes that conflict with it
- Anyone who wants fully automatic hardening without reviewing commands: the workflow is designed around confirmations
Try asking
- “Audit my Brigade setup and this machine's security, then give me a numbered plan”
- “Check whether my Brigade version is up to date and whether an update is available”
- “Review what ports are open on this server and whether my firewall is on”
- “Set up a periodic Brigade security check on a schedule”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
healthcheck.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip healthcheck.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip healthcheck.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Answer the context questions honestly (how you connect, whether the machine is public) so the agent does not change remote access settings you depend on.
- Keep a console or out-of-band way to reach the machine before applying firewall or SSH changes, and ask for the rollback plan first.
- Pick 'Show plan only' first to review the commands before asking for execution.
What's inside
- SKILL.md
Redistributed unmodified from spinabot/brigade under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.