Portable AI agent stacks. Collect, install, and share across Claude Code, Cursor, and more.

promptpit

Every AI tool has its own config files. pit turns them into one bundle you can share and actually keep track of.

pit collect to bundle. pit install to write it out for each tool. pit status to see what drifted. Commit .promptpit/ and your team stays in sync.

pit init           # scaffold a new .promptpit/ stack
pit collect        # bundle your AI config into .promptpit/
pit install        # write it out for each tool
pit status         # see what drifted
pit diff           # text diff between installed and source
pit watch          # live-sync skill changes
pit validate       # check if a stack is well-formed
pit check          # CI integration — verify config is fresh and in sync

Features

• Stack composition via extends. Layer stacks on top of each other: company base stack + team overrides + personal preferences. pit install resolves the dependency graph recursively.
• Five adapters: Claude Code, Cursor, Codex CLI, GitHub Copilot, and cross-tool standards (AGENTS.md, .mcp.json). One stack, every tool configured.
• Install from any GitHub repo, even ones that don't use promptpit. pit auto-collects from raw configs. Use --save to add it to your extends list.
• Skills follow the Agent Skills spec, symlinked or translated per tool (SKILL.md, .mdc, .instructions.md)
• Portable rules: conditional rules in .promptpit/rules/*.md with YAML frontmatter, translated per-adapter (Claude Code, Cursor, Cursor)
• Portable agents: custom agent definitions in .promptpit/agents/*.md, written natively to Claude Code and Cursor, inlined for other tools
• Drift detection: pit status shows what's synced, drifted, or deleted across all adapters, including upstream extends changes
• Dry-run previews: --dry-run