agentmods.dev

usage-widget CLAUDE.md

usage-widget CLAUDE.md is an instructions file for coding agents from emm3ttarmstrong/usage-widget. It costs 944 tokens per session, scanned A, original, MIT.

Repository instructions for a macOS SwiftUI desktop widget that displays Claude Code usage as a contribution-style grid and rate-limit bars. They describe how to build it, where its code lives, and how it reads and combines usage data.

In plain words
What is it for?
Use them when changing the widget's SwiftUI views, usage calculations, cache handling, API polling, keychain authentication, or build setup.
Why use it?
They provide the app context and build commands an agent needs to make changes without breaking its data flow, authentication, or project structure.

Instructions file

not rated 5 4mo ago A scan 944 tokens original MIT
View the source file emm3ttarmstrong/usage-widget
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 instructions/emm3ttarmstrong/usage-widget/claude-md
Clone the repo
git clone --depth 1 https://github.com/emm3ttarmstrong/usage-widget

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 usage-widget CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/emm3ttarmstrong/usage-widget/claude-md.svg)](https://agentmods.dev/instructions/emm3ttarmstrong/usage-widget/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/emm3ttarmstrong/usage-widget/claude-md"><img src="https://agentmods.dev/badge/instructions/emm3ttarmstrong/usage-widget/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 944 This file is loaded in full into every session.
When invoked 944 The same file — it is already loaded in full.
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 $0.00944 $0.00944
Opus 5 $0.00472 $0.00472
Sonnet 5 $0.00189 $0.00189
Haiku 4.5 $0.00094 $0.00094

Measured 4d ago against content hash 601e8c9f6ed8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

usage-widget 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 4d 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 · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Usage Widget

macOS SwiftUI desktop widget showing Claude Code usage as a contribution grid + rate limit bars.

Build

make build      # Release build → build/Build/Products/Release/UsageWidget.app
make install    # Build + copy to /Applications
make clean      # Remove build/
make setup BUNDLE_ID=com.you.UsageWidget  # Change bundle ID in all 3 places

Or open UsageWidget/UsageWidget.xcodeproj in Xcode and hit Cmd+R.

Project Structure

UsageWidget/UsageWidget/
├── App/
│   ├── AppDelegate.swift          # NSPanel setup, menu bar, position persistence, App Nap prevention
│   └── UsageWidgetApp.swift       # @main entry point
├── Models/
│   ├── ContributionDay.swift      # Day model + IntensityLevel enum (message count thresholds)
│   └── StatsCache.swift           # Decodable for ~/.claude/stats-cache.json
├── ViewModels/
│   └── StatsViewModel.swift       # Loads cache, merges live JSONL data, polls API, builds grid
├── Views/
│   ├── ContentView.swift          # Root layout — grid + bars + hover stats row
│   ├── ContributionGraphView.swift # 16-week Mon-Fri grid with month labels
│   ├── ContributionCellView.swift  # Single cell with hover tooltip
│   └── UsageLimitBarView.swift     # Vertical fill bar for rate limits
├── Utilities/
│   ├── FileWatcher.swift          # DispatchSource file monitor on stats-cache.json
│   ├── LiveStatsComputer.swift    # Scans ~/.claude/projects/*/*.jsonl for recent activity
│   └── UsageAPIClient.swift       # Fetches /api/oauth/usage from Anthropic API
├── Info.plist                     # LSUIElement=YES (no dock icon)
├── UsageWidget.entitlements       # Keychain access group + network client
└── Assets.xcassets

Data Flow

  1. Cached history: ~/.claude/stats-cache.json — daily message/session counts from claude-code-stats CLI
  2. Live today: Scans ~/.claude/projects/*/ JSONL transcript files for today's messages (30s refresh)
  3. API rate limits: GET https://api.anthropic.com/api/oauth/usage with OAuth token (60s refresh)
  4. Plan tier: Reads ~/.claude/.credentials.json → claudeAiOauth.rateLimitTier

Read the full file on GitHub · 77 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.

  1. 4d ago First seen · 77 lines · 944 tokens per session scan A 601e8c9f6ed8

Subscribe to this mod's changes

usage-widget CLAUDE.md is an instructions file published in the GitHub repository emm3ttarmstrong/usage-widget (5 stars, last pushed 4mo ago), licensed MIT. It adds 944 tokens to every session, about $0.0047 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.

claude-codecontribution-graphmacosmenu-barswiftswiftui
Related

Other instructions, from other repositories

DeepSeekMeter AGENTS.md

Instructions for CWNU-Open-Source-Community/DeepSeekMeter, covering agents.md — deepseekmeter 仓库操作规范, 1. 项目是什么, 2. 常用命令（改动后必须本地验证）, ios 版验证（核心包自测 + 工程结构静态校验必跑；有 xcode 时还会构建 app 冒烟） and android 核心单测（需 jdk 17 + android sdk；jvm 直跑无需设备）.

CWNU-Open-Source-Community/DeepSeekMeter · 3,490 tokens

Applite CLAUDE.md

Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.

milanvarady/Applite · 2,572 tokens

skills-manager CLAUDE.md

Instructions for yibie/skills-manager, covering skills manager - development guide, tui engine: blessed, 核心原则, 参考文档 and 正确的 list 用法.

yibie/skills-manager · 642 tokens

swift-tui AGENTS.md

AGENTS.md instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.

SwiftTUI/swift-tui · 2,410 tokens

barkeep AGENTS.md

AGENTS.md instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.

iannuttall/barkeep · 1,600 tokens

skills-manager AGENTS.md

Instructions for yibie/skills-manager, covering repository agent instructions and ui and interaction work.

yibie/skills-manager · 179 tokens