A full Claude Code workspace with skills, hooks, and tests
A reusable Claude Code has been released after being used for months to run company work. It includes about 70 skills for research, email, Telegram, a personal CRM, content, and . A single router rule connects plain-language requests to the right skill.
Hooks run before tools, after tools, and when a session starts, so they can block a file write before it happens, clean up output, and keep work inside set boundaries. Optional daemons support a local plus mail and calendar sync, but they can all be controlled from the CLI and do not require a browser. The setup includes about 2,000 tests, including tests that fail the build if an important guarantee breaks.
The public engine stores no real personal data; CRM records, notes, and outputs live in a separate private repo that is connected at runtime.
Key points
- The Claude Code is public, with a repo and docs available.
- It includes about 70 skills across research, messaging, CRM, content, and .
- Hooks can block unsafe writes, clean outputs, and enforce boundaries.
- Optional daemons handle a local and mail or calendar sync through the CLI.
- Private CRM data, notes, and outputs are kept outside the public engine repo.