tokless — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 HoangP8 · MCP Server · ★ 280

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

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

About tokless

tokless Save tokens on AI coding agents — no performance loss. One tool, no config — works the moment it lands. Introduction A unified CLI to install and update every token-saving plugin — RTK, Caveman, CodeGraph, and Context-Mode — for your AI coding agents, fast, efficient, and without hurting how the agent performs. Supported agents Claude Code OpenCode Codex Antigravity Supported tools — each installed from its official source and wired per its own docs: Each tool targets a different source of token waste, so they complement each other with no overlap or conflict. Install <img src="assets/install.svg" alt="tokless install: run one curl command, then pi

ai-coding-agentsantigravityclaude-codeclicodexcontext-compressioncontext-window-optimizationfactory-droidgithub-copilotllm-cost-reduction

Quick Facts

Stars280
Forks30
LanguageGo
CategoryMCP Server
LicenseMIT
Quality Score69.2699716675761/100
Open Issues8
Last Updated2026-09-29
Created2026-05-30
Platformsclaude-code, cli, codex, go, mcp
Est. Tokens~16k

Compatible Skills

These tools work well together with tokless for enhanced workflows:

  • claw-compactor — semantic(0.63)+complementary+rare_topics (62%)
  • claw-compactor — semantic(0.46)+complementary+rare_topics (56%)
  • lazyagent — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (53%)

tokless alternative? Top 6 similar tools

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

  • entroly by juyterman1000 · ⭐ 471

    Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an

  • hcom by aannoo · ⭐ 530

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • omni by fajarhide · ⭐ 373

    Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twi

  • ccmanager by kbwo · ⭐ 1.3k

    Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI

  • OpenContext by 0xranx · ⭐ 1.2k

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • agent-sessions by jazzyalex · ⭐ 889

    Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Go Agent Tools

Frequently Asked Questions

What is tokless?

tokless is An effective and efficient coding-agent setup in under 30 seconds: best tools, unified instructions, any OS.. It is categorized as a MCP Server with 280 GitHub stars.

What programming language is tokless written in?

tokless is primarily written in Go. It covers topics such as ai-coding-agents, antigravity, claude-code.

How do I install or use tokless?

You can find installation instructions and usage details in the tokless GitHub repository at github.com/HoangP8/tokless. The project has 280 stars and 30 forks, indicating an active community.

What license does tokless use?

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

What are the best alternatives to tokless?

The top alternatives to tokless on Agent Skills Hub include entroly, hcom, omni. 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 MCP Server tools