What is AIBattery CLAUDE.md?

Project instructions for AIBattery, a macOS menu-bar app built with Swift and SwiftUI that shows Claude API usage. They define a spec-first workflow, build commands, app packaging, and testing.

Use them when changing the app, checking its specifications, building or launching it, packaging it as a macOS app, or running tests.

They keep the written specifications and the code aligned, so architecture, data, interface details, and fixed values do not drift apart.

How KyleNesium/AIBattery configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to KyleNesium/AIBattery. 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/KyleNesium/AIBattery/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/KyleNesium/AIBattery

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/kylenesium/aibattery/claude-md/github.svg)](https://agentmods.dev/instructions/kylenesium/aibattery/claude-md)

Your own site

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

Per session 2,604 This file is loaded in full into every session.

When invoked 2,604 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	$0.02604	$0.02604
Opus 5.5	$0.01042	$0.01042
Sonnet 5.5	$0.00521	$0.00521
Haiku 4.5	$0.00260	$0.00260

Measured 6d ago against content hash 9e879d01059f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AIBattery 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 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.

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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Battery — AI Agent Guide

macOS menu bar app showing Claude and Codex (OpenAI) usage at a glance — up to 3 accounts per provider. Built with Swift 6 / SwiftUI, SPM, macOS 13+.

Spec-Driven Workflow

The spec/ folder is the single source of truth.

Spec first — describe the desired state in the relevant spec file
Code second — update code to match the spec
Never diverge — if you find spec/code drift, fix the spec first
Before any push to main — ensure all spec files and README.md reflect the current state of the code. No merge goes out with stale docs.

File	Covers
`spec/ARCHITECTURE.md`	App structure, data flow, project tree, build config
`spec/DATA_LAYER.md`	Models, services, algorithms, ViewModel
`spec/UI_SPEC.md`	Views, layout, colors, typography, ASCII mockup
`spec/CONSTANTS.md`	Every hardcoded value: thresholds, URLs, timings

Build & Run

swift build -c release

# Local smoke-test bundle. The release binary links Sparkle.framework via
# @executable_path/../Frameworks, so a bare "copy the binary into an .app"
# bundle aborts at launch (dyld: Library not loaded). Always use the script:
./scripts/build-app.sh && open .build/AIBattery.app

# The same script is the full signed bundle CI/release ships: entitlements,
# Sparkle.framework, codesign, zip + dmg
./scripts/build-app.sh

Testing

# Run all tests (requires Xcode for the Swift Testing framework)
swift test

1577 tests across 120 files, using import Testing + @testable import AIBatteryCore.

The package has 3 SPM targets:

AIBatteryCore (.target, path AIBattery/) — all logic: models, services, views, utilities
AIBattery (.executableTarget, path AIBatteryApp/) — thin @main entry point, imports AIBatteryCore
AIBatteryCoreTests (.testTarget) — unit tests, @testable import AIBatteryCore

CI (macos-15): build → test → verify signed bundle. Runs on push to main, and once when a PR leaves draft — not on later pushes to that PR (force a re-run via workflow_dispatch). A separate Lint job (SwiftLint + SwiftFormat) runs on every PR push touching .swift/lint-config files; run swiftformat AIBattery/ AIBatteryApp/ Tests/ and swiftlint locally before pushing to avoid a red check.

Read the full file on GitHub · 97 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.

6d ago Changed · +2 lines · +149 tokens per session 9e879d01059f
13d ago Changed · +1 lines · +236 tokens per session c261afb15050
17d ago Changed · +6 lines · +831 tokens per session cc09b63db803
1mo ago Changed · +4 lines · +208 tokens per session 91d6ed0b0137
1mo ago First seen · 84 lines · 1,180 tokens per session scan A 612a6df8aec7

Subscribe to this mod's changes

AIBattery CLAUDE.md is an instructions file published in the GitHub repository KyleNesium/AIBattery (24 stars, last pushed 4d ago), licensed MIT. It adds 2,604 tokens to every session, about $0.0104 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 2026-08-30.

Claude Code ai anthropic developer-tools macos menu-bar

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).

microsoft/vscode · 9,715 tokens

AIBattery: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AI Battery — AI Agent Guide

Spec-Driven Workflow

Build & Run

Testing

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md