GitWhy — The Context Layer for Git
LocalAbout GitWhy — The Context Layer for Git
GitWhy Agent Skills teaches coding agents to save, retrieve, and search reasoning linked to Git commits. It uses GitWhy through MCP tools or CLI commands.
Key features
- 01Save context linked to commits
- 02Retrieve and search structured context
- 03Install for Claude, Cursor, or Codex
Use cases
- 01Record decisions and trade-offs behind generated code
- 02Find prior context on a topic
- 03Review a context tree or post context to a PR
MCP support
The skill works with GitWhy through MCP tools or CLI commands.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y gitwhy-mcpGITWHY_API_KEYSecretGitWhy API key for cloud sync, publish, and PR comment features. Not required for local-only context saving.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGitWhy Agent Skills
Agent skills for GitWhy — save the reasoning, decisions, and trade-offs behind AI-generated code.
Install
npx skills add gitwhy-cli/gitwhy
Or install for a specific agent:
npx skills add gitwhy-cli/gitwhy --agent claude
npx skills add gitwhy-cli/gitwhy --agent cursor
npx skills add gitwhy-cli/gitwhy --agent codex
What's Included
gitwhy skill
Teaches your AI coding agent to save, retrieve, and search structured context linked to git commits. Works via MCP tools or CLI commands.
Trigger phrases:
- "Save this session with GitWhy"
- "What context do we have on authentication?"
- "Show me the context tree"
- "Post the context to the PR"
Prerequisites
Install the GitWhy CLI first:
curl -fsSL https://gitwhy.dev/install.sh | sh
Or via Homebrew:
brew install gitwhy-cli/tap/git-why
Then run setup:
git why setup
Links
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.