# maxritter/pilot-shell

How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.

Repository: https://github.com/maxritter/pilot-shell
Canonical: https://ross.abutalabs.com/products/pilot-shell
Homepage: https://pilot-shell.com
Language: JavaScript
License: NOASSERTION
License Family: other
Topics: ai-agents, ai-tools, anthropic, claude, claude-ai, claude-code, spec-driven-development, ai-assistant, ai-coding, ai-engineering, claudecode, ai-coding-tools, anthropic-claude, claude-context, claude-skills, codex, codex-cli, openai
Last push: 2026-08-26T14:16:28+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 22
- inputs: {"age_days": 319, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 229}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2051, forks 176 (observed 2026-08-28T04:06:09.044650+00:00)

## What it is
Pilot Shell is a framework that adds spec-driven planning, enforced TDD, persistent memory, and automatic quality gates to Claude Code and Codex CLI workflows. It provides slash-command workflows (/prd, /spec, /build, /fix) plus hooks, semantic code search, and team memory sharing to make AI coding agents production-ready.

## Use cases
- run claude code with spec-driven development
- enforce tdd with ai coding agents
- make ai-generated code production-ready
- persist project context across ai agent sessions
- reduce llm coding costs with token compression
- plan features with ai before writing code
- automate linting and test gates on ai edits

## When to choose
- you use Claude Code or Codex CLI daily and want structured, reviewable workflows
- your AI agents skip tests or lose context between sessions
- you want quality gates (lint, types, tests) enforced automatically on every edit
- you want to share specs and agent memory across a team

## When to avoid
- you don't use Claude Code or Codex CLI as your coding agent
- you prefer lightweight, minimal AI coding setups without opinionated workflows
- you need a framework with a permissive license (license is non-standard)
- you work outside macOS/Linux/WSL2 environments

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering, developer-tools, testing, workflow-automation
- domain: developer-tools, large-language-models
- platform: windows, cli
- tags: claude-code, codex-cli, spec-driven-development, tdd, ai-coding, quality-gates, context-engineering, persistent-memory, ai-agents, automation, macos, linux

## Member repositories
- maxritter/pilot-shell (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:09.044650+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:57:33.762516+00:00, confidence not recorded.
  - readme: https://github.com/maxritter/pilot-shell (fetched 2026-08-28T04:06:09.044650+00:00, sha 314346e2ee02)
  - homepage: https://pilot-shell.com (fetched 2026-08-29T10:37:51.046717+00:00, sha d925537518f2)
  - site_page: https://pilot-shell.com/docs (fetched 2026-08-29T10:37:51.056032+00:00, sha 4919f1351416)
- Data as of 2026-08-30T08:39:29.467469+00:00.