distill — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 samuelfaj · Codex Skill · ★ 677

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

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

About distill

distill Agent command outputs are one of the biggest sources of token waste. Logs, test results, stack traces… thousands of tokens sent to an LLM just to answer a simple question. 🔥 compresses command outputs into only what the LLM actually needs. Save up to 99% of tokens without losing the signal. How to use You can also point at OpenAI-compatible providers such as LM Studio, Jan, LocalAI, vLLM, SGLang, llama.cpp-compatible servers, MLX-based servers, and Docker Model Runner. Add in your global agent instructions file: md CRITICAL: Pipe every non-interactive shell command through unless raw output is explicitly required. CRITICAL: Your prompt to must be fully explicit. State exactly what you want to know and exactly what the output must contain. If you want only filenames, say If you want JSON, say Do not ask vague questions. Bad: Good: Examples: npm audit 2&1 | d

claude-codecodexgrokjevllmtokens

Quick Facts

Stars677
Forks43
LanguageRust
CategoryCodex Skill
LicenseApache-2.0
Quality Score69.8137805718542/100
Open Issues5
Last Updated2026-09-20
Created2026-03-06
Platformsclaude-code, codex, rust
Est. Tokens~23k

distill alternative? Top 6 similar tools

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

  • agtx by fynnfluegge · ⭐ 1.5k

    🏄🏼‍♂️ The blackboard for coding agents - agentic development environment for claude code, codex, cursor, ope

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • phi by pulseaiclub · ⭐ 465

    a coding agent, rpc plugin, sub-agents, hashline edits, and mcp

  • agentrove by Mng-dev-ai · ⭐ 327

    Self-hosted AI coding workspace to run and orchestrate Claude Code, Codex, Copilot, Cursor, Grok and OpenCode

  • aivo by yuanchuan · ⭐ 193

    Use your favorite coding agent with any model.

  • jev-review by NiazMorshed2007 · ⭐ 177

    Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is distill?

distill is Distill is a lightweight coding agent harness and TUI built to get more done with FAR FEWER tokens 🔥. It is categorized as a Codex Skill with 677 GitHub stars.

What programming language is distill written in?

distill is primarily written in Rust. It covers topics such as claude-code, codex, grok.

How do I install or use distill?

You can find installation instructions and usage details in the distill GitHub repository at github.com/samuelfaj/distill. The project has 677 stars and 43 forks, indicating an active community.

What license does distill use?

distill is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to distill?

The top alternatives to distill on Agent Skills Hub include agtx, Overture, phi. 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 Codex Skill tools