claudette — security grade CAUTION, quality 71/100

Security audit verdict: CAUTION · quality 71/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by utensils · MCP Server · ★ 76

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

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

About claudette

Claudette Claude's missing better half — a companion tool for Claude Code usage. Highlights Parallel agents in isolated git worktrees — run multiple Claude Code agents simultaneously, each on its own branch with no merge conflicts. Plan mode and AskUserQuestion handling — let the agent draft a plan or pause for input, then approve, deny with feedback, or answer from the GUI or the CLI. Checkpoints and workspace forking — roll any session back to an earlier turn, or fork a workspace from a checkpoint to exp

agent-orchestrationai-agentsai-coding-assistantanthropicclaudeclaude-codedesktop-appmcpremote-workspacetauri

Quick Facts

Stars76
Forks17
LanguageRust
CategoryMCP Server
LicenseMIT
Quality Score70.5985921613402/100
Open Issues21
Last Updated2026-09-11
Created2026-03-21
Platformsclaude-code, mcp, rust
Est. Tokens~26k

Compatible Skills

These tools work well together with claudette for enhanced workflows:

  • worktrunk — semantic(0.17)+complementary+rare_topics+same_lang+shared_platform (51%)
  • openusage — semantic(0.34)+complementary+similar_pop+shared_platform (47%)

claudette alternative? Top 6 similar tools

Looking for a claudette alternative? If you're comparing claudette 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.

  • genie by automagik-dev · ⭐ 338

    Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated work

  • Claude-Agent-Team-Manager by DatafyingTech · ⭐ 140

    Visual org-chart desktop app for managing Claude Code agent teams, skills, and configurations

  • agent-skills by simota · ⭐ 80

    90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anth

  • gsd-skill-creator by Tibsfox · ⭐ 68

    Introduces a comprehensive agent-based framework for guided software development (GSD)

  • orchestkit by yonatangross · ⭐ 278

    The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl

  • shep by shep-ai · ⭐ 255

    Ship features 10x faster. Built In Auto: Memory, K8S Agent & Security (SDD+SDLC) . 😇

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is claudette?

claudette is Claude's missing better half — a companion tool for Claude Code usage.. It is categorized as a MCP Server with 76 GitHub stars.

What programming language is claudette written in?

claudette is primarily written in Rust. It covers topics such as agent-orchestration, ai-agents, ai-coding-assistant.

How do I install or use claudette?

You can find installation instructions and usage details in the claudette GitHub repository at github.com/utensils/claudette. The project has 76 stars and 17 forks, indicating an active community.

What license does claudette use?

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

What are the best alternatives to claudette?

The top alternatives to claudette on Agent Skills Hub include genie, Claude-Agent-Team-Manager, agent-skills. 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