shihchengwei-lab/separation-and-audit-claude-code
Agent
Code diff review — reads staged diff, returns four categories of suggestions (bug risk / performance / duplication / naming). No pass/fail verdict.
Runnable reference implementation of the separation-and-audit-alignment architecture for Claude Code multi-agent projects.
shihchengwei-lab/separation-and-audit-claude-code
Agent
Code diff review — reads staged diff, returns four categories of suggestions (bug risk / performance / duplication / naming). No pass/fail verdict.
shihchengwei-lab/separation-and-audit-claude-code
Agent
Database migration SQL review — reads staged migration files, returns risk list (breaking change / RLS hole / index / data migration). No pass/fail verdict.
shihchengwei-lab/separation-and-audit-claude-code
Agent
Policy-layer text reviewer. Reads user-visible content (copy, UI strings, error messages, docs) and returns an evidence-level audit against your policy checklist. Runs mechanism recall on Step 0 automatically.
shihchengwei-lab/separation-and-audit-claude-code
Agent
A writing and design-review assistant for text that users see inside a product, such as instructions, character descriptions, dialogue, interface text, notifications, store copy, and error messages. It also checks other agents’ text against the project’s design principles.
shihchengwei-lab/separation-and-audit-claude-code
Agent
A visual-planning assistant that turns a project manager’s requests into artwork specifications or image-generation prompts. It also checks that new visuals follow the project’s established style.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: