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.
npx agentmods add instructions/nihildigit/waybar-ai-usage/claude-mdgit clone --depth 1 https://github.com/NihilDigit/waybar-ai-usageWrote 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.
[](https://agentmods.dev/instructions/nihildigit/waybar-ai-usage/claude-md)<a href="https://agentmods.dev/instructions/nihildigit/waybar-ai-usage/claude-md"><img src="https://agentmods.dev/badge/instructions/nihildigit/waybar-ai-usage/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02388 | $0.02388 |
| Opus 5 | $0.01194 | $0.01194 |
| Sonnet 5 | $0.00478 | $0.00478 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
waybar-ai-usage CLAUDE.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `copilot.py` | ~280 | PAT-auth via `urllib` (no `curl_cffi`); PR #13 adds Chrome-cookie HTML-scrape fallback for org-managed accounts | How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Waybar widgets that show usage/balance for Claude Code, OpenAI Codex CLI, GitHub Copilot, OpenCode Zen, and Z.ai. Each provider is one Python script that prints either a human-readable line (CLI) or a Waybar JSON blob (--waybar). Cron-style behavior comes from Waybar itself, not the scripts.
Mental model
This is a fan-in layout, not a framework:
- N small, mostly-independent provider scripts at the repo root (
claude.py,codex.py,copilot.py,zen.py,zai.py) - One shared utility module (
common.py) holding the cookie loader, file cache, output formatter, and reset-time formatter - One fat orchestrator (
waybar_ai_usage.py, ~900 lines) that knows about all providers and writes/restores the user's Waybar config + CSS
A provider script never imports another provider — it only depends on common.py. The orchestrator depends on knowledge of every provider (in five places — see "Adding a provider"), but not on imports of them.
Code shape
| File | Lines | Role |
|---|---|---|
common.py |
~340 | Contract layer: load_cookies, get_cached_or_fetch, format_eta, format_output, parse_window_*, open_login_url |
waybar_ai_usage.py |
~920 | Setup/cleanup/restore CLI. Reads/writes Waybar's JSON5 config and CSS, handles backups, drives the TUI module picker |
claude.py / codex.py |
~290 each | Cookie-auth providers (claude.ai, chatgpt.com) — most code is API request + parse_window_* glue |
zen.py |
~230 | Cookie-auth provider (opencode.ai), parses balance from rendered HTML/JS state |
copilot.py |
~280 | PAT-auth via urllib (no curl_cffi); PR #13 adds Chrome-cookie HTML-scrape fallback for org-managed accounts |
zai.py |
~320 | API-token-auth via urllib; JWT must be copied from DevTools (no browser auto-detect possible) |
waybar_ai_usage.py is the most complex file. It does JSON5 round-tripping, region-marker-based CSS edits, dry-run previews, and config restoration from .bak files. Most maintenance work touches the providers and common.py; waybar_ai_usage.py only changes when adding/removing a provider or tweaking the setup UX.
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.
- 6d ago First seen · 125 lines · 2,388 tokens per session scan A 0f8e70aa959a
waybar-ai-usage CLAUDE.md is an instructions file published in the GitHub repository NihilDigit/waybar-ai-usage (52 stars, last pushed 1mo ago), licensed MIT. It adds 2,388 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.