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 maxritter · MCP Server · ★ 2.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pilot-shell safe to install? View the security audit →
The professional development environment for Claude Code Claude Code is powerful. Pilot Shell makes it reliable. Start a task, grab a coffee, come back to production-grade code. Tests enforced. Context preserved. Quality automated. ⭐ Star this repo · 🌐 Website · 🔔 Follow for updates · 📋 Changelog · 📄 License Works on macOS, Linux, and Windows (WSL2). Why I Built This Claude Code writes code fast. But without structure, it skips tests
| Stars | 2,072 |
| Forks | 177 |
| Language | JavaScript |
| Category | MCP Server |
| Quality Score | 69.3602380998718/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-18 |
| Created | 2025-10-18 |
| Platforms | claude-code, cli, codex, mcp, node |
| Est. Tokens | ~21k |
These tools work well together with pilot-shell for enhanced workflows:
Looking for a pilot-shell alternative? If you're comparing pilot-shell 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.
The control plane for AI coding agents.
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.
Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified.
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
Tutorials, Guides and Agent Skills Directories
Explore other popular mcp server tools:
pilot-shell is Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, h. It is categorized as a MCP Server with 2.1k GitHub stars.
pilot-shell is primarily written in JavaScript. It covers topics such as agent-skills, agentic-engineering, ai-coding.
You can find installation instructions and usage details in the pilot-shell GitHub repository at github.com/maxritter/pilot-shell. The project has 2.1k stars and 177 forks, indicating an active community.
The top alternatives to pilot-shell on Agent Skills Hub include ai-devkit, autoprompt-skill, claude-code-skills. 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: