harness-coding-protocol

Bootstrap a target repo via /harness-init — ground, read, judge, confirm, apply. The IDE_Agent itself reads, judges, and writes the root-truth files after one confirmation, without requiring Node/npm/npx/tsx.

Audit and improve a target repo's AI entry documentation (AGENTS.md, CLAUDE.md, steering, .cursor rules). Use after /harness-init or when AI context drifts. Generic harness protocol skill — parameterize paths to the open workspace.