bazzite-operator

bazzite-operator is a skill for Codex from rolandreads/bazzite-mcp. It costs 77 tokens per session (660 once invoked), scanned A, original, MIT.

A Bazzite OS operations guide. Bazzite is a Linux operating system designed for gaming and desktop use, with workflows involving the host system, containers, and virtual machines.

In plain words
What is it for?
Use it to inspect system health, manage packages and services, configure networking and firewalls, operate containers or virtual machines, and troubleshoot development or gaming setups.
Why use it?
It helps you diagnose and change Bazzite systems using the appropriate platform-specific tools and safeguards instead of treating them like a generic Linux installation.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to inspect system health, manage packages and services, configure networking and firewalls, operate containers or virtual machines, and troubleshoot development or gaming setups.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rolandreads/bazzite-mcp/bazzite-operator
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 rolandreads/bazzite-mcp --skill bazzite-operator
Clone the repo
git clone --depth 1 https://github.com/rolandreads/bazzite-mcp

Made for: Codex.

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 bazzite-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/rolandreads/bazzite-mcp/bazzite-operator/github.svg)](https://agentmods.dev/skills/rolandreads/bazzite-mcp/bazzite-operator)
Your own site
<a href="https://agentmods.dev/skills/rolandreads/bazzite-mcp/bazzite-operator"><img src="https://agentmods.dev/badge/skills/rolandreads/bazzite-mcp/bazzite-operator/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 bazzite-operator

Your own site · 80×15
<a href="https://agentmods.dev/skills/rolandreads/bazzite-mcp/bazzite-operator"><img src="https://agentmods.dev/badge/skills/rolandreads/bazzite-mcp/bazzite-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 660 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00077 $0.00660
Opus 5 $0.00039 $0.00330
Sonnet 5 $0.00015 $0.00132
Haiku 4.5 $0.00008 $0.00066

Measured 10d ago against content hash 878b21bdbb57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bazzite-operator scanned grade A with 0 findings 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 10d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/bazzite-operator/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bazzite Operator

Overview

Use this skill as the workflow and policy layer for Bazzite tasks. Treat bazzite-mcp as the capability layer for live system state, guarded mutations, built-in knowledge resources, screenshots, and audit-aware changes.

Prefer MCP tools over ad hoc shell commands when an equivalent MCP tool exists. Use shell access mainly for targeted logs or for capabilities the MCP server does not expose yet.

Tool Routing

Route tasks this way:

  • Use ujust for Bazzite-provided setup and maintenance flows.
  • Use packages for package discovery, installation, removal, and inventory across install methods.
  • Use docs for lightweight Bazzite knowledge lookup and official source pointers.
  • Use system_info, system_doctor, and storage_diagnostics to inspect the host before recommending changes.
  • Use manage_service, manage_network, and manage_firewall for service and network operations.
  • Use manage_distrobox, manage_quadlet, and manage_podman for development environments and containerized services.
  • Use manage_vm when the workload needs stronger isolation than a container should provide.
  • Use gaming for Steam lookup, community reports, and game-specific settings changes.
  • Use screenshot, manage_windows, interact, set_text, and send_input only when desktop automation is required.

Read these references when needed:

  • references/install-policy.md
  • references/tool-routing.md
  • references/troubleshooting.md
  • references/dev-environments.md
  • references/game-optimization.md

Operating Rules

Use this default order of operations:

  1. Inspect current state first.
  2. Choose the least invasive Bazzite-native path.
  3. Explain the chosen path and why it fits Bazzite.
  4. Mutate the system only after the path is justified.
  5. Check audit history or rollback options after risky changes.

Keep these defaults:

  • Prefer ujust before composing custom host commands.
  • Prefer Flatpak for GUI apps and Homebrew for CLI/TUI tools.
  • Prefer Distrobox for development environments and other package ecosystems that do not belong on the immutable host.
  • Treat rpm-ostree as a last resort.
  • Prefer VMs over containers for untrusted executables or high-isolation workflows.

Read the full file on GitHub · 63 lines

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. 10d ago First seen · 63 lines · 77 tokens per session scan A 878b21bdbb57

Subscribe to this mod's changes

bazzite-operator is a skill published in the GitHub repository rolandreads/bazzite-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 77 tokens to every session and 660 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

ask-user-questions

Ask clarifying questions to users via interactive TUI. Use when you need user input on preferences, implementation choices, or ambiguous instructions.

paulp-o/ask-user-questions-mcp · 32 tokens

search-mesh

This skill should be used when searching a codebase for one or more keywords across many files, validating whether a match sits inside a specific syntax node (function, class, struct, interface, enum), extracting the smallest syntax-bounded code block around a match instead of reading a whole file, or making a precise…

jamestkelly/search-mesh · 107 tokens

skill-dispatcher

Universal MCP skill dispatcher for AI coding agents. Loads Claude Code, OpenCode, Cursor, Gemini-style, command, plain markdown, and GitHub-hosted skills on demand. Includes agent routing, active skill lifecycle tracking, external repo import, nested skill discovery, origin filtering, and hardened parsing for secure…

farhanic017/dynamic-skill-loader · 68 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

southwest

Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.

borski/travel-hacking-toolkit · 40 tokens