ensemble-fold-promptlisted

# Ensemble Command: /ensemble:fold-prompt This Codex skill mirrors the Ensemble slash command `/ensemble:fold-prompt`. Follow the workflow below, adapt to the current repository, and keep outputs structured. <!-- DO NOT EDIT - Generated from fold-prompt.yaml --> <!-- To modify this file, edit the YAML source and run: npm run generate --> Analyze a project's codebase to extract coding conventions, optimize CLAUDE.md for minimal token cost and maximum AI productivity, and organize context with progressive disclosure. Every token in CLAUDE.md is loaded every session -- this command ensures none are wasted. ## Workflow ### Phase 1: Codebase Standards Discovery **1. Detect Technology Stack** Identify languages, frameworks, package managers, and build tools - Read package.json, Gemfile, requirements.txt, go.mod, mix.exs, *.csproj, or equivalent - Identify primary language(s) and framework(s) (e.g., Next.js 14, Rails 7, Phoenix 1.7) - Detect test framework(s) and runner commands - Detect linter/formatter config (.eslintrc, .prettierrc, rustfmt.toml, .rubocop.yml) - Note monorepo structure if present (workspaces, packages/, apps/) **2. Extract Coding Conventions** Mine the codebase for patterns that an AI assistant must follow - Sample 5-10 representative source files to detect naming conventions (camelCase vs snake_case, file naming) - Check for barrel exports, path aliases, import ordering conventions - Identify error handling patterns (Resul