caddis — an opinionated Claude Code plugin for verification-first agentic development: phased TDD planning, cross-vendor code review, independent phase validation, and session continuity that survives context loss.
This repository also configures its own agents. See what caddis-plugin tells them →
Agent Claude Code
Expert UX designer and design critic: creates research-backed designs (JTBD, wireframes, specs) AND provides evidence-based critique with NN Group citations. Two modes: Design (generative) and Review (critique). Pushes back on bad ideas with data.
Agent Claude Code
How to invoke the word-cloud skill from orchestrator agents or multi-step pipelines.
Agent Claude Code
Use this agent to find relevant best practices, examples, and anti-patterns for a specific prompt. Searches the references/ folder to find transformation patterns that match the task type. Returns specific examples, rules, and guidance to apply during transformation. Context: User wants to transform "fix the login…
Agent Claude Code
Use this agent to gather codebase context for prompt transformation. Explores relevant files, finds similar implementations, identifies patterns to reference, and discovers tech stack constraints. Returns actionable context that makes transformed prompts specific to THIS codebase, not generic advice. Context: User…
Agent Claude Code
Use this agent to deeply analyze a prompt's intent before transformation. Determines task type (bug fix, feature, refactor, etc.), identifies what's missing (verification, location, constraints), surfaces edge cases, and detects ambiguities that need clarification. Returns a structured analysis that guides…
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: