Mechanical implementation agent for corpus generation and regeneration, linkification, doc placement, test refactors, catalog sweeps, and format migrations. Pinned to sonnet at low effort per the CLAUDE.md orchestration cost policy; never inherits the session model. Use for mechanical, self-contained in-harness build…
Cheapest-tier sweep agent for catalog sweeps, find-and-replace passes, link and reference checks, list hygiene, and mechanical verification. Pinned to haiku at low effort per the CLAUDE.md orchestration cost policy; never inherits the session model.
Checks a finished frontend change against the WRITTEN decisions rather than against what the implementer thought they were building. Reads the decision documents and the checkable requirement lines, drives a real browser through the Playwright MCP server, and reports pass or fail per requirement with the measured…
Looks at a finished screen in a real browser and judges whether a person who has never used this product could work out what to do. Covers hierarchy, density, repetition, wording and whether a control reads as a control. Use when a frontend change is done and you want a second pair of eyes on how it looks and reads…
Use when working with the HemmaBo federation MCP server: understanding pricing logic, checking availability rules, reviewing booking flows, explaining the ACP/Stripe integration, or making code changes to the server. Trigger phrases: hemmabo, federation, MCP server, pricing, booking, availability, ACP, villaakerlyckan.