kramme-cc-workflow

Use this agent to audit UI code for WCAG 2.1 AA accessibility issues, including semantics, ARIA, keyboard navigation, focus handling, screen reader support, and contrast. Use it when accessibility is an explicit requirement or when reviewing forms, dialogs, and other interactive flows; not for general UX or visual consistency review.

Use this agent to review code changes from an architectural perspective, focusing on system boundaries, dependency direction, layering, abstractions, service interfaces, and alignment with existing patterns. Best for structural refactors, new services, or cross-cutting features; not for style-only or narrowly local implementation feedback.

Use this agent to review code for authentication, authorization, CSRF, and session management vulnerabilities. Checks that protected operations have proper auth checks, access control is enforced, and sessions are securely managed.

Use this agent to review recent code against project guidelines, CLAUDE.md conventions, and established patterns. It is best used after writing or modifying code, especially before commits or PRs, and should be pointed at the relevant files or diff scope; not for deep product, accessibility, or performance-specific review.

Use this agent after writing or modifying code to simplify the recent changes for clarity, consistency, and maintainability while preserving behavior. It focuses on the modified files or diff scope and is best for cleanup after a working implementation; not for semantic rewrites or feature changes.

(experimental) Browser operator for live product inspection. Detects available browser MCP tooling (claude-in-chrome, chrome-devtools, playwright) and provides consistent navigation, screenshots, interaction, and evidence capture. Not for code-only analysis.

Create engaging changelogs for recent merges to main branch. Triggers on requests for daily/weekly changelogs, release notes, or summarizing recent changes.

Audit a codebase for agent-nativeness — score how well-optimized it is for AI coding agents across 5 dimensions and generate a prioritized refactoring plan.

Remove AI-generated code slop from a branch. Use when cleaning up AI-generated code, removing unnecessary comments, defensive checks, or type casts. Checks diff against main and fixes style inconsistencies.

Scan the codebase (or a specified scope) for unnecessary, redundant, or duplicative UI text. Identifies labels, descriptions, placeholders, tooltips, and instructions that could be removed because the UI already communicates the same information through its structure.

5 hooks across 3 events