Challenge

Challenge

Apply structured provocation patterns to force reconsideration of current work or upcoming intentions.

Target: $ARGUMENTS

Critical constraint

The interviewer (this skill, running in the main conversation) DELIVERS the queue. It NEVER regenerates findings in the main context. Regenerating brings anchoring back through the side door and destroys the benefit of the fresh-context generator. All finding generation happens in deep's sub-agent or, for forward/anchor/verify/framing, in the protocol execution itself — never re-derived afterward from parent-conversation reasoning.

Dispatch

Parse first word of $ARGUMENTS as subcommand. No recognized subcommand → route.

/challenge <free-text description> with no matching subcommand keyword is route, not an error and not a menu — route is the default entry point.

Deep Subcommand

Spawn ONE sub-agent via the Agent tool:

• subagent_type: dstoic:devil-advocate:devil-advocate
• prompt: target description + relevant file paths to read
• The agent executes all 9 patterns IN SEQUENCE (anchor: Gatekeeper, Reset, Alternative Approaches, Pre-mortem · verify: Proof Demand, CoVe, Fact Check List · framing: Socratic, Steelman) inside its own fresh context — not 9 parallel agents, one agent running 9 steps.
• It returns a structured queue (reference.md §Queue Schema), not a batch report.
• DO NOT pass parent conversation reasoning into the prompt — fresh context, uncontaminated by the anchoring already present in the main conversation, is the entire point.

deep (no flag): walk the returned queue per reference.md §Interactive Delivery. deep --report: skip the walk, emit the queue as a batch Challenge Report instead — legacy fire-and-forget escape hatch for callers who cannot sustain a turn-by-turn exchange.

Thinking Transparency (applies to all subcommands)

For every item, make reasoning explicit:

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

Output

Delivery mechanics (fact-resolution order, ranking, cap, one-question-per-turn format, gate, final report) are canonical in reference.md §Interactive Delivery. Queue shape is canonical in reference.md §Queue Schema. Pattern catalog and Challenge Report format also live in reference.md. All subcommands cite these, none redefine them.