Do I need a separate Anthropic subscription to use Pilot Shell?

Yes. Pilot Shell enhances Claude Code — it doesn't replace it. You need an active Claude subscription (Max 5x or 20x for solo developers, or Team Premium for teams). Using the Anthropic API directly also works but may lead to higher costs. Pilot Shell adds quality automation on top of whatever Claude Code access you already have.

Is Pilot Shell enterprise-compliant for data privacy?

Yes. Your source code, project files, and development context never leave your machine through Pilot Shell. The only external calls are license validation (daily, license key only) and one-time activation/trial start (machine fingerprint only). No OS info, no version strings, no analytics, no telemetry.

Does Pilot Shell work with other AI coding tools?

Pilot Shell is built specifically for Claude Code. Every hook, rule, command, and workflow is engineered for Claude's tool-use protocol, prompt format, and session lifecycle. The optional Codex plugin adds OpenAI-powered adversarial review during /spec — disabled by default.

Does Pilot Shell work with existing projects?

Yes — that's the primary use case. Pilot Shell doesn't scaffold or restructure your code. You install it, run /setup-rules, and it explores your codebase to discover your tech stack, conventions, and patterns. The more complex your codebase, the more value Pilot Shell adds.

Which programming languages does Pilot Shell support?

Pilot Shell's quality hooks (auto-formatting, linting, type checking) currently support Python, TypeScript/JavaScript, and Go out of the box. TDD enforcement, spec-driven development, persistent memory, and all rules and standards work with any language Claude Code supports.

Can I use one Pilot Shell license on multiple machines?

Yes. A Solo license covers you across all your personal devices — workstation, laptop, VPS, cloud instances. One subscription, one key, multiple machines. Team licenses are for multiple people, not multiple machines.

Can I use Pilot Shell on multiple projects?

Yes. Pilot Shell installs once globally and works across all your projects. All tools, rules, commands, and hooks live in ~/.pilot/ and ~/.claude/. Each project can optionally have its own .claude/ rules, custom skills, and MCP servers.

Can I add my own rules, commands, skills, and agents?

Yes. Create your own in your project's .claude/ folder — rules, commands, skills, and agents are plain markdown files. Project-level assets load alongside Pilot Shell's defaults and take precedence when they overlap. Team plans also support sharing extensions via a connected git repository.

Pilot Shell — The Claude Code Engineering Platform

The Claude Code engineering platform. From requirement to production-grade code — planned, tested, verified. Spec-driven plans, enforced quality gates, and persistent knowledge across sessions.

What Pilot Shell adds to Claude Code

Spec-Driven Development — Plan, approve, implement, verify with the /spec workflow.
TDD Enforcement — Tests first, then implementation.
Quality Hooks — Auto-format, lint, and type-check on every edit.
Persistent Memory — Context carries across sessions automatically.
Semantic Code Search — Find code by meaning, not just keywords.
MCP & LSP Servers — Pre-wired language tooling.
Worktree Isolation — Safe parallel work via git worktrees.

Install

Run the installer in your terminal:

curl -fsSL https://raw.githubusercontent.com/maxritter/pilot-shell/main/install.sh | bash

Then run pilot in any project, generate rules with /setup-rules, and ship features with /spec.

Learn more

Documentation
Blog
GitHub repository