monorepo-context

Monorepo Context Patterns

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "monorepo-context" with this command: npx skills add yonatangross/orchestkit/yonatangross-orchestkit-monorepo-context

Monorepo Context Patterns

Overview

Claude Code 2.1.20 introduces --add-dir for multi-directory context, enabling monorepo-aware sessions where each service maintains its own CLAUDE.md instructions.

Monorepo Detection

Indicators that a project is a monorepo:

Indicator Tool

pnpm-workspace.yaml

pnpm

lerna.json

Lerna

nx.json

Nx

turbo.json

Turborepo

rush.json

Rush

3+ nested package.json files Generic

Per-Service CLAUDE.md

Each service can have its own context instructions:

monorepo/ CLAUDE.md # Root context (workspace-wide rules) packages/ api/ CLAUDE.md # API-specific patterns package.json web/ CLAUDE.md # Frontend-specific patterns package.json shared/ CLAUDE.md # Shared library context package.json

--add-dir Usage

Start Claude Code with additional directory context:

From api service, add shared library context

claude --add-dir ../shared

Multiple directories

claude --add-dir ../shared --add-dir ../web

Environment Variable

Enable automatic CLAUDE.md loading from additional directories:

export CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1

When set, Claude Code reads CLAUDE.md from all --add-dir directories.

Root vs Service Context Separation

Root CLAUDE.md

  • Workspace-wide conventions (commit messages, branch naming)

  • Cross-service dependency rules

  • CI/CD pipeline overview

  • Shared tooling configuration

Service CLAUDE.md

  • Service-specific patterns and frameworks

  • Local test commands

  • API contracts and schemas

  • Service-specific environment variables

Related Skills

  • configure

  • OrchestKit configuration including monorepo detection

  • project-structure-enforcer

  • Folder structure enforcement

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

ui-components

No summary provided by upstream source.

Repository SourceNeeds Review
General

responsive-patterns

No summary provided by upstream source.

Repository SourceNeeds Review
General

domain-driven-design

No summary provided by upstream source.

Repository SourceNeeds Review
General

dashboard-patterns

No summary provided by upstream source.

Repository SourceNeeds Review