#token
RepoScope — AI Cost Intelligence & Security Scanner
nxgentech
See what your AI subscription actually costs you — per file, per prompt, per month. RepoScope shows which files burn the most tokens, audits your .cursorrules for bloat, and projects when your Cursor Pro or Claude Pro plan runs out. Free: 44-detector security scanner (secrets, XSS, SQL injection) +
H47 Token Optimizer
wcalmels
Compress LLM prompts locally — no API calls. Reduce tokens on selected text for Claude, GPT, and Cursor.
SecretGuard - Secret Detection
secretguard-cli
Real-time secret detection — catches API keys, tokens, and credentials as you type
AI Context Handoff Guard
AravindhanJ
A privacy-first handoff reminder for long AI coding sessions. Estimates when your local editor session may be getting context-heavy, applies idle decay, adapts to AI likelihood, and helps you start a fresh chat. No model calls, no data leaves the machine.
Context and Usage Monitor for Claude Code
viktor-moyseyenko
Status bar monitor for Claude Code: correct context-window %, cache hit rate, per-turn and monthly cost. Not affiliated with Anthropic.
Codex Multi-Account Usage
QG-devramyun
Show token usage & estimated cost for every OpenAI Codex account (auto-detected, multi-account) in the VS Code status bar.
Trae Use Token
firerl
在 TRAE 内本地观测模型 Token、缓存命中与实际/估算积分
CleanMyPrompt — AI Security & Token Intelligence
cleanmyprompt
Stop leaking secrets. Stop burning tokens. Intercepts API keys, PII & credentials before they reach Copilot, and compresses code with LSP-aware squeeze to cut token costs by 30–70%. 100% local.
Claude & Copilot Token Optimizer
ai-token-optimizer
Automatically reduces token consumption for Claude Code, GitHub Copilot, and Codex by injecting optimized instructions, installing compression tools, and configuring MCP servers.
QuotaWatch
VarunVasisth
Track your AI coding tool usage limits right in the VS Code status bar. Real-time Codex CLI usage monitoring with alerts, charts, and repo analysis.
ACIL — AI Credit Intelligence Layer
imKrisK
Pre-execution LLM cost governor for VS Code. Predicts cost before tokens are spent, compresses prompts, routes to cheaper models, enforces budgets, and learns your session patterns. Patent Pending.
Claude Code: How Much Is Your Prompt?
kuritaku
How much is your prompt? Claude Code のトークン使用量と料金(円換算)をステータスバーにリアルタイム表示