Onboarding an existing codebase
For projects that started without Corpole: the coding agent reverse-engineers the code, tests and documents into findings; people confirm what is intended; governance grows module by module.
Principle
Code says what the system does, not what it should do. Every finding arrives as a Draft with its origin (Tested > Documented > As-built) and evidence. Conflicts between sources become questions; people decide.
How it works
- Start onboarding here. Connect the coding agent with the propose permission.
- Quick baseline (/corpole:onboard): modules, stack decisions, glossary, existing tests, conflicts, defects and risks. The agent extracts with commands first to keep token use low.
- Deep dive per module, typically right before it is changed (govern what you touch).
- Review findings per module: confirm as Approved or Authority, mark wrong behaviour as a defect, or reject. A rejected finding is remembered with its reason: agents see it in their brief and cannot submit it again.
- Agents may submit at most 300 findings per project per hour, and at most 500 may wait for review; then they stop and ask you to review first.
- Govern a module once an Authority record covers it; finish onboarding when the maturity is good enough.
Advisory or enforced
The tenant chooses (Settings → Agent gates). Advisory: agents warn and Claude Code asks you before an ungoverned module is changed; finishing with open thresholds needs a reason. Enforced: changes to ungoverned modules are refused (MCP and the Claude Code hook) and onboarding finishes only when every threshold is met.