shell-use: Make the terminal / shell accessible for AI agents. Automate tasks with ease

by microsoft · Agent Tool · ★ 218

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

How to install shell-use

brew install shell-use

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 72/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

ai-toolsautomationbashclie2e-testingfishllmpowershellpwshshell-use

Quick Facts

Stars218
Forks20
LanguageRust
CategoryAgent Tool
LicenseMIT
Quality Score72/100
Open Issues9
Last Updated2026-08-07
Created2024-01-25
Platformscli, rust
Est. Tokens~24k

About shell-use

shell-use [!WARNING] Work in progress. is still being built out, so commands and behavior may change between releases & installation instructions may not yet work. is a rust powered cli for controlling, inspecting, testing, and recording shell sessions and terminal apps.

Compatible Skills

These tools work well together with shell-use for enhanced workflows:

  • computer-use-linux — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • unifly — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (55%)
  • ralph — semantic(0.26)+complementary+rare_topics+similar_pop+shared_platform (54%)

shell-use alternative? Top 6 similar tools

Looking for a shell-use alternative? If you're comparing shell-use 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 · ⭐ 196

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

  • hcom by aannoo · ⭐ 650

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

  • turbo-flow by marcuspat · ⭐ 186

    The rules layer for AI-written code — rig-lite: a fail-closed cross-model review gate, a written constitution,

  • claude-model-router-hook by tzachbon · ⭐ 111

    Claude Code hooks that auto-switch model tier based on task complexity

  • tokentop by tokentopapp · ⭐ 77

    htop for your AI costs — real-time terminal monitoring of LLM token usage and spending across providers and co

  • gob by juanibiapina · ⭐ 76

    Process manager for AI agents (and humans)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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