What is agent-usage-plus CLAUDE.md?

Additional project instructions for the same Omarchy/Quickshell usage widget, focused on Claude Code work. They cover testing, data contracts, credential states, live UI checks, and settings encoding.

Use them when changing the widget’s logic, collectors, settings, or interface; run the specified JavaScript, Python, QML, and manifest checks and verify the real panel.

They reduce common integration mistakes, such as treating missing credentials as a crash or writing array settings in a format the bar command cannot read.

How viganogabriele/agent-usage-plus configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to viganogabriele/agent-usage-plus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/viganogabriele/agent-usage-plus/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/viganogabriele/agent-usage-plus

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/viganogabriele/agent-usage-plus/claude-md/github.svg)](https://agentmods.dev/instructions/viganogabriele/agent-usage-plus/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/viganogabriele/agent-usage-plus/claude-md"><img src="https://agentmods.dev/badge/instructions/viganogabriele/agent-usage-plus/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/viganogabriele/agent-usage-plus/claude-md"><img src="https://agentmods.dev/badge/instructions/viganogabriele/agent-usage-plus/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 637 This file is loaded in full into every session.

When invoked 637 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00637	$0.00637
Opus 5.5	$0.00255	$0.00255
Sonnet 5.5	$0.00127	$0.00127
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash 4034b293582a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-usage-plus CLAUDE.md 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 2mo 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Usage Plus: Claude Code notes

This is an Omarchy/Quickshell plugin. Start with AGENTS.md, then read the relevant contract or collector documentation before editing data paths.

Do

Keep UI, logic and collectors separate: test pure logic in logic/; make collector records follow docs/collector-contract.md.
Treat missing credentials as a normal provider state with a direct fix, not as an absent provider or a raw process error.
Use npm test, the Qt 6 qmllint command in AGENTS.md, and manifest validation for every code change; also run the Python suite in collectors/tests/ when a change touches collectors/ — it is not part of npm test.
Restart the shell for every live QML check. Do not rely on hot reload or rescanPlugins.
Verify the real panel after UI changes, especially sizing, scroll speed, overflow, empty/auth states, and bar marks at actual bar scale.
Double-JSON-encode any array-valued setting before writing it with omarchy bar set ... --json (JSON.stringify(JSON.stringify(arr)), parsed back with a guarded JSON.parse on read) — a bare multi-element JSON array value makes that command fail every time. See AGENTS.md and providerOrder in Main.qml.
Before treating a missing notification as a bug, check Omarchy's own Do Not Disturb flag and notification history (paths in AGENTS.md) — a successful send with DND on produces no visible popup by design.

Do not

Do not access credentials, directly edit Omarchy shell settings, push, or create pull requests without explicit user approval.
Do not use raster provider logos or assume panel icon sizing also works in the bar. Always set sourceSize (× Screen.devicePixelRatio) on mark images, or they read as soft/blurry.
Keep Omarchy theme behavior intact: live surface/foreground/urgent colors, light/default provider marks selected from the live bar foreground, and the deliberate fixed amber warning color (#F2B705).
Keep provider response handling bounded and fail-closed: parse at most the collector limit, surface auth/endpoint errors explicitly, and never log upstream bodies or credentials.
Do not turn a collector failure into a silent blank state.
Do not add a hardcoded cap on how many providers can appear in the bar. The limit is whatever the person has configured (Fixed count + Cycle slots), which is already bounded by how many providers exist to configure — see AGENTS.md.

Read the full file on GitHub · 53 lines

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.

2mo ago First seen · 53 lines · 637 tokens per session scan A 4034b293582a

Subscribe to this mod's changes

agent-usage-plus CLAUDE.md is an instructions file published in the GitHub repository viganogabriele/agent-usage-plus (4 stars, last pushed 18d ago), licensed MIT. It adds 637 tokens to every session, about $0.0025 per session on Opus 5.5. 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.

agent-usage-plus CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-usage-plus CLAUDE.mdviganogabriele/agent-usage-plus	Instructions file	4	18d ago	MIT	A	637	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

agent-usage-plus: Instructions file for Claude Code