tokentop — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by tokentopapp · Agent Tool · ★ 70

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is tokentop safe to install? View the security audit →

About tokentop

Early release — tokentop is functional and actively developed. Please report issues! tokentop htop for your AI costs Real-time terminal monitoring of LLM token usage and spending across providers and coding agents. Features · Install · Quick Start · Agents · Plugins · Docs tokentop.app

aianthropicbunclicost-trackingdeveloper-toolsllmmonitoringopenaiterminal

Quick Facts

Stars70
Forks6
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score74.4607435975091/100
Open Issues17
Last Updated2026-09-12
Created2026-01-23
Platformscli, node
Est. Tokens~17k

Compatible Skills

These tools work well together with tokentop for enhanced workflows:

  • toktrack — semantic(0.54)+complementary+rare_topics+similar_pop+shared_platform (67%)
  • codex-viz — semantic(0.31)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • sidekick-agent-hub — semantic(0.16)+complementary+rare_topics+same_lang+similar_pop+shared_platform (55%)
  • claude-view — semantic(0.25)+complementary+rare_topics+similar_pop+shared_platform (53%)

tokentop alternative? Top 6 similar tools

Looking for a tokentop alternative? If you're comparing tokentop with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • toktrack by mag123c · ⭐ 190

    Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

  • gptree by travisvn · ⭐ 290

    A CLI tool to provide LLM context for coding projects by combining project files into a single text file (or c

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

  • ccboard by FlorianBruniaux · ⭐ 94

    Monitor Claude Code sessions, costs, config, hooks, agents & MCP servers from a single Rust binary — TUI (9 ta

  • AICodeBot by TechNickAI · ⭐ 62

    CLI tool that generates commit messages from git changes, reviews code for quality issues, and provides debugg

  • claudetop by liorwn · ⭐ 213

    htop for your Claude Code sessions — real-time cost, cache efficiency, model comparison, and smart alerts

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is tokentop?

tokentop is htop for your AI costs — real-time terminal monitoring of LLM token usage and spending across providers and coding agents. It is categorized as a Agent Tool with 70 GitHub stars.

What programming language is tokentop written in?

tokentop is primarily written in TypeScript. It covers topics such as ai, anthropic, bun.

How do I install or use tokentop?

You can find installation instructions and usage details in the tokentop GitHub repository at github.com/tokentopapp/tokentop. The project has 70 stars and 6 forks, indicating an active community.

What license does tokentop use?

tokentop is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to tokentop?

The top alternatives to tokentop on Agent Skills Hub include toktrack, gptree, claude-code-open. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools