challenge

Challenge

Apply structured provocation patterns to force reconsideration of current work.

Target: $ARGUMENTS

⚠️ AskUserQuestion Guard

CRITICAL: After EVERY AskUserQuestion call, check if answers are empty/blank. Known Claude Code bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.

If answers are empty: DO NOT proceed with assumptions. Instead:

1. Output: "⚠️ Questions didn't display (known Claude Code bug outside Plan Mode)."
2. Present the options as a numbered text list and ask user to reply with their choice number.
3. WAIT for user reply before continuing.

Dispatch

Parse first word of $ARGUMENTS as subcommand:

Subcommand	Error Type	Protocol
anchor	Premature commitment / anchoring bias	Read protocols/anchor.md → execute
verify	Factual errors / hallucination	Read protocols/verify.md → execute
framing	Wrong problem / framing errors	Read protocols/framing.md → execute
deep	High stakes — all 9 patterns in fresh context	Spawn devil-advocate sub-agent via Agent

No-Subcommand Fallback

If no subcommand detected:

AskUserQuestion: "What are you worried about with the current AI response?"

• A) Anchoring bias — AI committed too early to one approach
• B) Factual accuracy — claims may be wrong or hallucinated
• C) Wrong framing — solving the wrong problem
• D) High stakes — want all 9 patterns in fresh context (Devil's Advocate)

→ Dispatch to matching subcommand based on answer.

Deep Subcommand

Spawn via Agent tool:

• subagent_type: dstoic:devil-advocate:devil-advocate
• prompt: target description + relevant file paths to read
• The agent runs ALL 9 patterns (anchor: Gatekeeper, Reset, Alt Approaches, Pre-mortem · verify: Proof Demand, CoVe, Fact Check List · framing: Socratic, Steelman) comprehensively in fresh context
• DO NOT pass parent conversation reasoning — fresh context is the point

Thinking Transparency (applies to all subcommands)

For every finding, make reasoning explicit:

1. Observation: What specifically in the target triggered this finding
2. Technique family: Which challenge family (anchor/verify/framing) and named pattern (e.g., Gatekeeper, CoVe, Steelman) — cite mechanism from reference.md pattern catalog
3. Reasoning: Why this observation matters — what cognitive bias or error it reveals
4. Confidence: How certain is this finding (High/Medium/Low) and what evidence supports that rating

Output

All subcommands produce a Challenge Report (structured, not prose). See reference.md for report format and pattern catalog.