Turbo — Dual-Edition Skill Monorepo Map
A compact, well-annotated map of a monorepo that ships parallel Claude Code and Codex editions from one source tree. Cleanly separates…
- Type
- CLAUDE.md Example
- Repository
- tobihagemann/turbo
- GitHub stars
- 404
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Source file
- AGENTS.md
What Turbo — Dual-Edition Skill Monorepo Map is
Turbo — Dual-Edition Skill Monorepo Map is a claude.md example published in the tobihagemann/turbo repository on GitHub, which has about 404 stars. The repository describes itself as: “Reusable workflows for planning, building, reviewing, and shipping with Claude Code and Codex.”
A CLAUDE.md file holds standing instructions that Claude Code reads at the start of every session in a project, such as conventions, commands, and rules. Examples like Turbo — Dual-Edition Skill Monorepo Map show how other teams structure theirs.
In Claude Cowork, the equivalent places for this kind of guidance are your global instructions, project instructions, and folder instructions.
How to install Turbo — Dual-Edition Skill Monorepo Map
Claude Code
- Copy the parts that fit your project into CLAUDE.md at the project root, or into ~/.claude/CLAUDE.md for rules that apply everywhere.
- Keep it short and specific; remove anything that doesn't match how your team works.
Claude Cowork
- Put personal rules in Settings → Instructions for Claude (global instructions).
- Put project or folder rules in the project's instructions or the folder instructions for that directory.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from AGENTS.md, shared under the repository's MIT license. Read the full file on GitHub.
Turbo is a modular collection of agentic coding skills with sibling editions for Claude Code and Codex. Skills connect into larger pipelines like $finalize and $review-pr. See README.md for an introduction and docs/workflows.md for workflow details and diagrams.
Each docs/ guide answers one reader question: workflows.md (how it works), examples.md (what to type), requirements.md (what you need and what setup changes), customization.md (how to adapt and update). Place new doc content by the question it answers.
Project Structure
codex/ # Codex edition (canonical Codex tree)
├── skills/<skill-name>/
│ ├── SKILL.md # Skill definition (YAML frontmatter + markdown body)
│ ├── scripts/ # Optional supporting scripts
│ ├── references/ # Optional reference documentation
│ └── assets/ # Optional templates or boilerplate
├── SETUP.md
├── UPDATE.md
├── MIGRATION.md
├── ADDITIONS.md
└── SKILL-CONVENTIONS.md
claude/ # Claude Code edition (parallel tree)Each skill is self-contained. Skills compose other skills to any depth via $skill-name invocations. The key distinction is between analysis skills (return structured findings without acting) and workflow skills (compose analysis skills and act on results).
$smoke-test, $create-test-plan, and $exploratory-test share one testing domain. An execution rule (launching and driving the running app, and cleaning up after it) goes into $test-run-rules alone, which both test-running skills load. A scenario-design rule (what a test covers and what counts as a pass) that lands in $smoke-test also goes into $create-test-plan.
For Codex skill conventions, see codex/SKILL-CONVENTIONS.md. General skill-authoring principles live in codex/skills/create-skill/references/, split by topic and indexed in that skill's SKILL.md.
Key Files
- ~/.turbo/config.json — User-level configuration. Top-level oracle is shared. Per-edition state lives under codex.{excludeSkills, lastUpdateHead, configVersion, sharedClaudeAutoMemory}; the parallel claude.* object is present when the Claude edition is also installed.
- ~/.turbo/repo/ — Local clone of the upstream turbo repo (skill source for install/update)
- ~/.agents/skills/ — Installed Codex skills
A change that leaves a ~/.turbo/config.json key with no effect carries its own cleanup: add a MIGRATION.md entry deleting the key in each edition and bump the Current version in UPDATE.md. Dropping the key from SETUP.md only stops new installs from writing it, leaving it behind everywhere it was already written.
When working inside codex/, also see codex/AGENTS.md for edition-specific rules.
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Turbo — Dual-Edition Skill Monorepo Map?
Turbo — Dual-Edition Skill Monorepo Map is a claude.md example for Claude Code and Claude Cowork from the tobihagemann/turbo repository on GitHub. A compact, well-annotated map of a monorepo that ships parallel Claude Code and Codex editions from one source tree. Cleanly separates…
How do I install Turbo — Dual-Edition Skill Monorepo Map in Claude Code?
Copy the parts that fit your project into CLAUDE.md at the project root, or into ~/.claude/CLAUDE.md for rules that apply everywhere. Keep it short and specific; remove anything that doesn't match how your team works.
Can I use Turbo — Dual-Edition Skill Monorepo Map in Claude Cowork?
Put personal rules in Settings → Instructions for Claude (global instructions). Put project or folder rules in the project's instructions or the folder instructions for that directory.
Is Turbo — Dual-Edition Skill Monorepo Map safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Answer Reviewer Questions For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer… Skill · tobihagemann/turbo
- Langfuse Skills — 'Only Add If It Beats the Docs' An unusually disciplined content policy for skill authors: add a use case only when it beats fetching the docs, put 'when to use' guidance… CLAUDE.md Example · langfuse/skills
- Blueprint — Flows, Skills, and Unattended Loops A masterclass in structuring a multi-skill agent system in one file: three named flows (Setup / Decide / Deliver), a skill catalog, and a… CLAUDE.md Example · owainlewis/blueprint
- OrchestKit — Source-vs-Generated Invariants Nails the single most common agent footgun in a build-step repo: a load-bearing 'edit src/, NEVER edit plugins/' invariant, spelled out… CLAUDE.md Example · yonatangross/orchestkit
- Posit Skills — Skill-Repo Conventions & Registration A complete, transferable playbook for a skills repository: the directory contract, the SKILL.md frontmatter, the token/line budget, the… CLAUDE.md Example · posit-dev/skills
- cc-fleet — AGENTS.md as a Pointer + Essentials Demonstrates the pointer pattern done well: AGENTS.md declares CLAUDE.md the single source of truth and links the… CLAUDE.md Example · ethanhq/cc-fleet
- dbt Agent Skills — Frontmatter Rules & Error Table The most actionable take on SKILL.md frontmatter: the exact allowed fields, the lowercase-hyphen name rule, and a validation-error → fix… CLAUDE.md Example · dbt-labs/dbt-agent-skills
- dot-skills — Validator-First Definition of Done Frames a markdown-authoring repo as red-green-refactor with the validator as the test gate, and gives an explicit 'Definition of Done —… CLAUDE.md Example · pproenca/dot-skills