Borrowing it
Nothing to install: this file belongs to GoldenTangerine/Claude-Relay-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/GoldenTangerine/Claude-Relay-Meter/main/CLAUDE.mdgit clone --depth 1 https://github.com/GoldenTangerine/Claude-Relay-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/goldentangerine/claude-relay-meter/claude-md)<a href="https://agentmods.dev/instructions/goldentangerine/claude-relay-meter/claude-md"><img src="https://agentmods.dev/badge/instructions/goldentangerine/claude-relay-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/goldentangerine/claude-relay-meter/claude-md"><img src="https://agentmods.dev/badge/instructions/goldentangerine/claude-relay-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 | $0.05165 | $0.05165 |
| Opus 5 | $0.02583 | $0.02583 |
| Sonnet 5 | $0.01033 | $0.01033 |
| Haiku 4.5 | $0.00517 | $0.00517 |
Grade B, and why
Claude-Relay-Meter CLAUDE.md scanned grade B 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `reloadClaudeConfig`: Manually reloads configuration from `~/.claude/settings.json` and updates VSCode settings How it starts
The opening of the file, as written. The whole thing — 457 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.
Project Overview
Claude Relay Meter is a multilingual VSCode extension that monitors Claude Relay Service usage statistics and displays them in the VSCode status bar. The extension fetches usage data from a relay service API and provides real-time monitoring with color-coded visual feedback based on usage thresholds.
Supported Languages: Chinese (中文) and English, with full i18n support.
Development Commands
Build and Development
npm install # Install dependencies
npm run compile # Compile TypeScript + copy locale files to out/
# This command runs both tsc compilation and copy-locales script
# Locale files from src/locales/*.json are copied to out/locales/
npm run copy-locales # Copy locale JSON files to out/locales/ (standalone)
npm run watch # Watch mode for development (TypeScript only)
npm run lint # Run ESLint on TypeScript files
npm run package # Package extension as .vsix file
Publishing
The extension is published as a .vsix file. After making changes:
- Update version in
package.json - Run
npm run compileto build - Run
npm run packageto create the.vsix - The packaged file appears in
builds/directory
Debugging
To debug the extension in VSCode:
- Open the project in VSCode
- Press
F5to launch a new Extension Development Host window - The extension will be loaded in the new window with debugging enabled
- Set breakpoints in TypeScript files under
src/ - View debug output in the "Claude Relay Meter" output channel
Architecture
Core Components
Extension Lifecycle (src/extension.ts)
- Entry point managing activation/deactivation
- Critical initialization order (see Important Implementation Details #1):
- First:
initializeLogging()- Must be called before any log statements - Second:
initializeI18n()- Required before any translation calls
- First:
- Registers commands:
refreshStats,openSettings,selectLanguage,openWebDashboard,reloadClaudeConfig, andmanualReloadConfigopenWebDashboard: Opens the web dashboard in browser at{apiUrl}/admin-next/api-stats?apiId={apiId}reloadClaudeConfig: Manually reloads configuration from~/.claude/settings.jsonand updates VSCode settingsmanualReloadConfig: Triggered from tooltip button, prompts user to choose between new and current config
- Manages timer-based auto-refresh with window focus awareness
- Handles configuration changes (including language switching) and re-initialization
- Auto-initializes config from Claude Settings if VSCode settings are empty
- Configuration namespace:
relayMeter.*
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.
- 10d ago First seen · 457 lines · 5,165 tokens per session scan B c1cbea52f155
Claude-Relay-Meter CLAUDE.md is an instructions file published in the GitHub repository GoldenTangerine/Claude-Relay-Meter (11 stars, last pushed 8mo ago), licensed MIT. It adds 5,165 tokens to every session, about $0.0258 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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 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.
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.