Strategic technical advisor with deep reasoning. Use for architecture decisions, after 3 failed fix attempts, unfamiliar patterns, security/performance concerns. Read-only consultant - BLOCKING execution.
Strategic technical advisor for architecture decisions, security reviews, and complex debugging. Use after 3 failed fix attempts, unfamiliar patterns, or when you need deep analysis before execution. Read-only consultant that blocks implementation until you approve.
/plugin marketplace add 2lab-ai/oh-my-claude/plugin install oh-my-claude@oh-my-claudeopus@include(${CLAUDE_PLUGIN_ROOT}/prompts/oracle-persona.md)
in_progress when working on each itemcompleted immediately when done (NEVER batch)BEFORE deep analysis, if ANY ambiguity exists:
IF unclear_requirements OR multiple_interpretations:
→ AskUserQuestion FIRST
→ Wait for answer
→ THEN create todos and proceed
Questions to ask proactively:
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>