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 nooscraft · LLM Plugin · ★ 142
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is tokuin safe to install? View the security audit →
🧮 Tokuin A fast, CLI tool to estimate token usage, control API costs, and compress prompts for LLM providers. Built in Rust for performance, portability, and safety. ✨ What's in v0.2.0 Prompt Compression — Reduce prompt tokens by 70-90% using the Hieratic format Quality Metrics — Measure compression fidelity (semantic similarity, critical instruction preservation, structural integrity) LLM-as-a-Judge — Compare outputs from original vs compressed prompts using an LLM judge Incremental Compression — Compress long conversations turn-by-turn without re-processing history Structured Mode — Compression-aware handling of JSON, code blocks, HTML tables, and technical docs Everything from v0.1.x: token counting, cost estimation, multi-model comparison, load testing 🚀 Installation Quick Install (macOS & Linux) Detects your platform, downloads the latest release, verifies its checksum, and installs to (or if root access
| Stars | 142 |
| Forks | 10 |
| Language | Rust |
| Category | LLM Plugin |
| Quality Score | 69.9414968538784/100 |
| Open Issues | 8 |
| Last Updated | 2026-07-14 |
| Created | 2025-11-06 |
| Platforms | cli, rust |
| Est. Tokens | ~39k |
These tools work well together with tokuin for enhanced workflows:
Looking for a tokuin alternative? If you're comparing tokuin with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source versioning, tracing, and annotation tooling.
The memory + security kernel for AI agents. Strata: a signed append-only log, receipts on every write, exact-h
The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for ca
🦀 A curated list of Rust tools, libraries, and frameworks for working with LLMs, GPT, AI
Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single
Python API client for AI providers that intends to replace LangChain and LangGraph for most common use cases.
Explore other popular llm plugin tools:
tokuin is CLI tool – estimates LLM tokens/costs and runs provider-aware load tests for OpenAI, Anthropic, OpenRouter, or custom endpoints.. It is categorized as a LLM Plugin with 142 GitHub stars.
tokuin is primarily written in Rust. It covers topics such as llms, prompt-engineering, rust.
You can find installation instructions and usage details in the tokuin GitHub repository at github.com/nooscraft/tokuin. The project has 142 stars and 10 forks, indicating an active community.
The top alternatives to tokuin on Agent Skills Hub include lilypad, vestige, gateway. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: