Opinionated plugins and workflow extensions for Claude Code.
Agent
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
Agent
Read-only auditor for silent error swallowing in Effect code. Receives scanner JSON, reads source context, classifies severity, prescribes fixes. Spawned by /null-as-error skill.
Agent
Read-only infrastructure code auditor for /refactorlib. Searches for handcrafted infrastructure code (HTTP, retry, scheduling, platform I/O, CLI, config, concurrency) replaceable by installed library APIs. Use when /refactorlib spawns parallel exploration.
Agent
Read-only utility code auditor for /refactorlib. Searches for handcrafted utility code (string, date, collections, ID generation, encoding, URL parsing, deep clone) replaceable by installed library APIs or native APIs. Use when /refactorlib spawns parallel exploration.
Agent
Reviews plans for architectural soundness, challenges decisions, verifies best practices.
Agent
Comment slop hunter. Invoke manually with a batch of files listed in the prompt (absolute path + comment-line count + fate tag). Classifies every comment, cites file:line examples, flags stale suspects without ruling on them. Read-only. Do not auto-delegate to it for anything other than a comment hunt.
Agent
Creates 5 unique design variants sequentially in a single context.