ClaudeBar is a macOS menu bar application that displays remaining quotas, credits, balances, and reset times for AI coding services. It is for developers who use services such as Claude, Codex, Gemini, Copilot, or Cursor and want to monitor their usage from one place.
Borrowing it
Nothing to install: this file belongs to tddworks/ClaudeBar. 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/tddworks/ClaudeBar/main/AGENTS.mdgit clone --depth 1 https://github.com/tddworks/ClaudeBarWrote 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/tddworks/claudebar/agents-md)<a href="https://agentmods.dev/instructions/tddworks/claudebar/agents-md"><img src="https://agentmods.dev/badge/instructions/tddworks/claudebar/agents-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/tddworks/claudebar/agents-md"><img src="https://agentmods.dev/badge/instructions/tddworks/claudebar/agents-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 | $0.02718 | $0.02718 |
| Opus 5.5 | $0.01087 | $0.01087 |
| Sonnet 5.5 | $0.00544 | $0.00544 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
ClaudeBar AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Rules for AI coding agents (Claude Code, Codex, Cursor, …) in this repo. This is the only agent-instructions file; there is no CLAUDE.md. Everything else is one link away: docs index · architecture · contributing · docs design.
ClaudeBar is a macOS menu bar app that shows AI coding quotas. It reads them from CLIs, APIs and local files for 28 built-in providers, plus user extensions from ~/.claudebar/extensions/. The code is moving from three layers to modules (MODULAR_DESIGN.md). Every built-in provider is a JSON definition in Modules/Providers/Resources/Providers/, found by ProviderCatalog.detect() (no Swift lists one) and run by one generic Provider on one shared Engine; what one needs that the engine can't say yet becomes a general rule in DataSources.
Build & test
tuist install && tuist generate # generated *.xcodeproj / *.xcworkspace are git-ignored
tuist test # every target: module tests, DomainTests, InfrastructureTests, AppTests, AcceptanceTests
tuist test Providers # one scheme (Providers, DataSources, Domain, Infrastructure, AppTests, AcceptanceTests)
xcodebuild test -workspace ClaudeBar.xcworkspace -scheme ClaudeBar-Workspace \
-destination 'platform=macOS,arch=arm64' -only-testing:DomainTests # bypasses Tuist's result cache
swift test # the modules alone, from the root Package.swift
tuist testcaches results; usexcodebuild testwhen you need a test to really run.- SourceKit "No such module" errors in the editor are expected; modules resolve at build time.
- The modules are
ClaudeBarKit, the rootPackage.swift, which takes every file in a module'sSources/. The app and its layers are targets inApp/Project.swift, with**globs; the schemes are inWorkspace.swift. New subfolders are picked up without edits. - Tuist 4.209 or later: the modules' tests reach
tuist testthroughincludeLocalPackageTestTargetsinTuist/Package.swift, and 4.209 is the first release that lets them use products from other packages (Mockable). swift testbuilds SwiftTerm's Metal shader, which needs Xcode's Metal Toolchain once (xcodebuild -downloadComponent MetalToolchain); the Tuist build leaves the shader out.
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.
- 4d ago Changed · +47 tokens per session 23891b549443
- 8d ago Changed · +2 lines · +157 tokens per session 5c821f6b38dd
- 15d ago Changed · +77 tokens per session 0cd80c7fc2ce
- 18d ago Changed · +3 lines · +155 tokens per session 9dcddeb2ab1c
- 21d ago Changed · +7 tokens per session e2f274d3b358
- 22d ago Changed · +15 lines · +608 tokens per session 228680119c10
- 23d ago Changed · +1 lines · +61 tokens per session 1f44fb82fb81
- 24d ago Changed · +3 tokens per session f00334cd4ac6
- 25d ago Changed · +6 lines · +319 tokens per session 68ebacf2ec7e
- 1mo ago First seen · 69 lines · 1,284 tokens per session scan A 244c9097ccc0
ClaudeBar AGENTS.md is an instructions file published in the GitHub repository tddworks/ClaudeBar (1,557 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,718 tokens to every session, about $0.0109 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 2026-09-25.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.