Borrowing it
Nothing to install: this file belongs to JackBhanded/claude-meter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JackBhanded/claude-meter/main/CLAUDE.mdgit clone --depth 1 https://github.com/JackBhanded/claude-meterWrote 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/jackbhanded/claude-meter/claude-md)<a href="https://agentmods.dev/instructions/jackbhanded/claude-meter/claude-md"><img src="https://agentmods.dev/badge/instructions/jackbhanded/claude-meter/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.
<a href="https://agentmods.dev/instructions/jackbhanded/claude-meter/claude-md"><img src="https://agentmods.dev/badge/instructions/jackbhanded/claude-meter/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00651 | $0.00651 |
| Opus 5.5 | $0.00260 | $0.00260 |
| Sonnet 5.5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
claude-meter 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Claude Meter
Context for any Claude (or human) picking up this repo. Keep it current.
What this is
A live Windows taskbar widget showing your Claude usage — per-model breakdown,
percentages, and reset countdowns — so you can see how much quota is left without
leaving the editor. Python + PySide6, shipped as a single .exe.
How it gets the data
GET https://api.anthropic.com/api/oauth/usage with Authorization: Bearer <token>
and header anthropic-beta: oauth-2025-04-20. The token is the
claudeAiOauth.accessToken from ~/.claude/.credentials.json. The JSON returns
per-quota rows (five_hour, seven_day, seven_day_sonnet, seven_day_opus,
seven_day_omelette = the Claude Design codename). The endpoint rate-limits hard,
so polling is adaptive with backoff.
UI
PySide6 widget, light "Claude brew" theme, the real Claude logo rendered programmatically, progress bars coloured blue → orange (>50%) → red (>80%), reset countdowns, refresh control, system tray icon + settings, threshold toast notifications. Runs windowless via a silent launcher; packaged with PyInstaller.
Hard-won gotchas
- PyInstaller relative-import crash — use absolute imports
(
from claude_usage_widget.main import main), notfrom .main import main. - QThread parenting —
moveToThreadneeds a QThread with no parent. - Tooltip overlap — reposition beside the widget when it can't fit above.
- Fullscreen detection — hide the widget when another app is fullscreen.
wsl.exe/subprocess console flash — launch withCREATE_NO_WINDOW.- Morning stale data — the widget showed yesterday's data and refresh hung; handled by re-probing and a visible "auth expired / not refreshed" icon state.
Build & ship
PyInstaller → single .exe; GitHub Actions builds it on a version tag. SmartScreen
warns on the unsigned exe (More info → Run anyway); documented in the README.
Roadmap
v0.2: browser cookie auth (sessionKey from Chrome/Edge), Codex usage support. Later: multi-account cycling, Linux tray build, CSV export of the 14-day history. v0.3 idea: log usage over time and add a rich history dashboard (trends per model, burn rate, time-of-day heatmaps, projections).
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 · 57 lines · 651 tokens per session scan A cace07dd12e1
claude-meter CLAUDE.md is an instructions file published in the GitHub repository JackBhanded/claude-meter (13 stars, last pushed 5mo ago), licensed MIT. It adds 651 tokens to every session, about $0.0026 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.