qualitylayer
Plan, implement and verify software with your favorite coding agents. Work in the App or browser, or in your own terminal, IDE or agent app.
What is qualitylayer?
Plan, implement and verify software with your favorite coding agents. Work in the App or browser, or in your own terminal, IDE or agent app.
Overview of qualitylayer
What it is
Pilot Shell is a professional context and harness engineering system for Claude Code and OpenAI Codex. It coordinates the complete engineering process around the model, providing persistent knowledge, enforced quality, and runtime proof. It is not a collection of rules and skills but a harness that integrates quality gates, persistent context, professional toolchain, runtime verification, human control plane, workflow neutrality, structured delivery, and support for both Claude Code and Codex.
Key features
- Quality on every layer: hooks, stop guards, independent reviews, full test/build gates, and browser or device verification prevent “looks done” handoffs
- Persistent context: relevant source, architecture, project standards, prior decisions, and session state survive long work and compaction, with useful findings remembered automatically across Claude Code and Codex
- Professional toolchain: Semble, CodeGraph, ast-grep, language servers, browser automation, and MCP integrations support discovery, structural search, impact analysis, implementation, and runtime proof
- Runtime verification: tests, builds, real CLI/API execution, browser automation, and device checks turn completion claims into evidence
- Human control plane: the Console connects plan and diff review, annotations, progress, evidence, session recovery, shared project knowledge, and usage
- Workflow neutrality: direct requests, native Plan/Goal tools, and Pilot workflows are peer ways to work inside the same harness
- Structured delivery when wanted: /spec, /build, /fix, and /prd add durable artifacts and explicit lifecycle contracts without becoming routing rules for ordinary requests
- One system for Claude Code and Codex: platform-specific adapters preserve one engineering standard while the underlying models continue to improve
Use cases
Building production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification. Professional context and harness engineering around Claude Code and OpenAI Codex for any existing project.
Getting started
Prerequisites: At least one AI agent – Claude Code (primary) or Codex (via Codex CLI or ChatGPT desktop app). Install one before running the Pilot installer.Installation (works with any existing project):bashcurl -fsSL https://raw.githubusercontent.com/maxritter/pilot-shell/main/install.sh | bashAfter installation, run claude or codex directly. On macOS, restart ChatGPT desktop and open the project there. Run pilot update to check for updates. For uninstall or reset, see the repository README.
License and pricing
The license is not explicitly stated (NOASSERTION in metadata). The project is open source (pricing_type: open_source).
Based on the project's public README and repository metadata.