claude-code-stats: Instructions file for Claude Code

CLAUDE.md

claude-code-stats CLAUDE.md is an instructions file for Claude Code from dmelo/claude-code-stats. It costs 1,959 tokens per session, scanned C, original, MIT.

Project instructions for ClaudeCodeStats, a macOS menu bar app that displays Claude Code usage limits, service health, and command-line updates. They describe how to build, install, and relaunch the app safely.

In plain words
What is it for?
They help build the SwiftUI app with Xcode, identify the exact output application, copy it to Applications, and restart it.
Why use it?
They prevent developers from copying an old build by mistake when Xcode stores several versions in its build folders.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is dmelo/claude-code-stats's own configuration. It tells Claude Code how to work on claude-code-stats itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-stats configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dmelo/claude-code-stats. 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/dmelo/claude-code-stats/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dmelo/claude-code-stats

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.

agentmods badge for claude-code-stats CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dmelo/claude-code-stats/claude-md/github.svg)](https://agentmods.dev/instructions/dmelo/claude-code-stats/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dmelo/claude-code-stats/claude-md"><img src="https://agentmods.dev/badge/instructions/dmelo/claude-code-stats/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.

agentmods 80×15 button for claude-code-stats CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dmelo/claude-code-stats/claude-md"><img src="https://agentmods.dev/badge/instructions/dmelo/claude-code-stats/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,959 This file is loaded in full into every session.
When invoked 1,959 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01959 $0.01959
Opus 5.5 $0.00784 $0.00784
Sonnet 5.5 $0.00392 $0.00392
Haiku 4.5 $0.00196 $0.00196

Measured 19d ago against content hash 74d7d629b4a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

claude-code-stats CLAUDE.md scanned grade C 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 19d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /Applications/ClaudeCodeStats.app
CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

ClaudeCodeStats is a native macOS menu bar app (SwiftUI) that shows Claude Code usage limits, Claude service health status, and CLI version update notifications.

Build

cd ClaudeCodeStats
xcodebuild -scheme ClaudeCodeStats -configuration Release build

The built .app is in ~/Library/Developer/Xcode/DerivedData/ClaudeCodeStats-<hash>/Build/Products/Release/.

Resolve that path explicitly — never with a ClaudeCodeStats-* glob. Xcode keeps a separate DerivedData directory per project location, and stale ones are not cleaned up. When more than one exists the glob expands to all of them, so cp -R src1 src2 /Applications/ copies the fresh build and then overwrites it with the stale one, exit 0 and no warning — you end up debugging a binary that is weeks old. ls -dt does not save you either: it sorts by directory mtime, which a previous cp will have touched. The last line xcodebuild prints (lsregister -f -R -trusted <path>) names the directory it actually built into.

To install locally:

# Take the path from xcodebuild's own output, or pick by the *binary's* mtime:
APP=$(ls -dt ~/Library/Developer/Xcode/DerivedData/ClaudeCodeStats-*/Build/Products/Release/ClaudeCodeStats.app/Contents/MacOS/ClaudeCodeStats \
      | head -1 | sed 's#/Contents/MacOS/ClaudeCodeStats##')
echo "installing from: $APP"   # sanity-check this before continuing

# Kill running instance, copy to /Applications, relaunch
pkill -x ClaudeCodeStats; sleep 0.5
rm -rf /Applications/ClaudeCodeStats.app
cp -R "$APP" /Applications/ClaudeCodeStats.app
open /Applications/ClaudeCodeStats.app

If a change you just made doesn't show up, check this first: a rendered colour or string that exists nowhere in the source tree means you are not running the tree.

There are no tests or linters configured, so verifying a change means running the app and looking at it. Three non-obvious traps when doing that from a shell:

  • Launch with open, never &. A .app started as "$BINARY" & from a Bash tool dies when that shell returns, often mid-work — open /Applications/ClaudeCodeStats.app hands it to LaunchServices so it survives. To time a scan or wait on a side effect, poll the artifact (until [ -f "$cost_cache" ]; do sleep 2; done), don't hold the process open.
  • Instrument to a file, not stderr. A menu bar app has no attached terminal, and one you'll pkill loses buffered stdout/stderr — write debug lines to a file (/tmp/…) and cat it after.
  • AppleScript can't open the MenuBarExtra popover (click menu bar item … does nothing). To inspect a view in a specific state or appearance without the running app, compile the real views into a standalone ImageRenderer harness and render at a chosen \.colorScheme + sample data (swiftc main.swift Theme.swift Models.swift Views/*.swift — top-level code needs the file named main.swift). It renders everything except ScrollView content, which comes back blank.

Read the full file on GitHub · 98 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. 19d ago Changed · +72 tokens per session 74d7d629b4a0
  2. 20d ago Changed · +1 lines · +218 tokens per session bc5d489493ad
  3. 1mo ago First seen · 97 lines · 1,669 tokens per session scan C 142dded34170

Subscribe to this mod's changes

claude-code-stats CLAUDE.md is an instructions file published in the GitHub repository dmelo/claude-code-stats (26 stars, last pushed 2d ago), licensed MIT. It adds 1,959 tokens to every session, about $0.0078 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens