omarchy-plugin

A guide for developing and checking Omarchy Quattro plugins, including their manifests, plugin types, QML entry points, lifecycle, and marketplace requirements. Omarchy Quattro is the plugin system this guide targets.

In plain words
What is it for?
Use it to choose a plugin type, build or troubleshoot its QML entry point, validate a plugin repository, check namespacing and lifecycle behaviour, and prepare marketplace submission files.
Why use it?
It helps ensure a plugin follows the expected runtime contract and is organized well enough to review or publish.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/firstp1ck/pi-coding-agent-forge/omarchy-plugin
Any agent
npx skills add Firstp1ck/pi-coding-agent-forge --skill omarchy-plugin
Clone the repo
git clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forge

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,059 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00072 $0.02059
Opus 5 $0.00036 $0.01030
Sonnet 5 $0.00014 $0.00412
Haiku 4.5 $0.00007 $0.00206

Measured 2d ago against content hash f44e61f3c55d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

omarchy-plugin 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 2d 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.

pi-skill-omarchy-plugin/skills/omarchy-plugin/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Omarchy Plugin

Guide an Omarchy Quattro plugin from a clearly chosen shell contract to a validated, reviewable repository and Marketplace-ready submission. The official development and publishing guides are the primary product sources. Re-check the official Omarchy shell/plugin reference before relying on a runtime detail because Quattro contracts can evolve.

When to Use

Use for requests to:

  • design or implement an Omarchy Quattro plugin;
  • select a plugin kind and matching QML entry point;
  • review or troubleshoot a plugin manifest, QML lifecycle, or repository;
  • validate a plugin folder or assess Marketplace readiness;
  • prepare publication files or submission content without submitting it.

Do not route here for unrelated Hyprland plugins, generic QML work with no Omarchy plugin contract, or a request that only installs an existing plugin.

Inputs

Establish the intended behavior, plugin kind, interaction pattern, working folder, current manifest and QML files, dependencies or commands, target namespace, and whether the user has authorized runtime or external side effects. Ask for missing code or diagnostics rather than inventing them.

Ordered Decision Workflow

Follow these decisions in order. Do not skip ahead from an uncertain contract to implementation or publication.

  1. Set the safety and authorization boundary
    • Treat inspection, source review, manifest parsing, path checks, and static validation as the default.
    • Omarchy plugins execute unsandboxed with the user's permissions inside the shared, long-running shell process. Review every dependency, executable, installer, network call, and shell command before use; avoid unnecessary privileges.
    • A plugin must use the existing shell. Never start a second Quickshell process for a plugin.
    • Obtain the user's explicit confirmation before cloning when it will enable or replace an active component, enabling, disabling, restarting, rescanning when it changes runtime state, removing, installing, pushing a repository, opening or submitting an issue, publishing, or causing any other external side effect not already authorized.
    • Completion: the proposed next action is read-only, already authorized, or paused for confirmation.

Read the full file on GitHub · 122 lines

Files

What ships with it

2 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. 2d ago First seen · 122 lines · 72 tokens per session scan A f44e61f3c55d

Subscribe to this mod's changes

omarchy-plugin is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (74 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 2,059 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 2026-08-30.