| name | interrogate |
| description | Run an adversarial review of code or a diff through independent reviewers, then lead-judge consensus, disagreements, and false positives. Use when the user asks to interrogate, challenge, stress-test, find blind spots, perform multi-model review, or when `henry-mode` needs adversarial judgment of a risky change. |
Interrogate
Give independent reviewers the same intent, code, and rubric. Diversity comes from independent reasoning and, where genuinely available, different model families—not invented personas or model aliases. The deliverable is a lead-reviewed verdict; never auto-apply findings.
Availability and fallback
| Harness | Parallel mechanism | Model selection | Fallback |
|---|
| Cursor | Available Task/subagent calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes |
| Claude Code | Available Agent/Task calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes |
| Codex / T3 | spawn_agent, drained with wait_agent | Valid overrides only when offered | Run waves within slot limits; inherit the parent model |
| No delegation | None | None | Apply the rubric through separate sequential passes and label the result self-reviewed |
Only delegate when current user and system policy permit it. If true model diversity is unavailable, disclose that; never pretend reviewer labels are different models.
1. Determine scope
Use the exact files or diff the user names. Otherwise inspect the full feature-branch diff against its appropriate merge base. Include only surrounding files needed to trace the changed behavior; give every reviewer the same package.
2. State intent
Write one paragraph describing what the change is meant to accomplish, derived from the user's request, commit/PR context, and code. Ask only if ambiguity would materially change the review. Reviewers challenge execution, not the chosen product goal.
3. Launch independent reviewers
Read and fill these references:
Launch as many reviewers as the user requested or the harness can support usefully; default to three independent passes. Each reviewer is read-only and receives the identical filled prompt. Use model overrides only from valid harness-advertised choices. Require structured findings with severity, location, evidence, and an optional concrete suggestion.
4. Aggregate
Drain every reviewer. Merge duplicate findings, identify independent agreement, retain lone findings at lower confidence, and surface explicit disagreement. Inspect relevant code yourself before accepting a claim.
5. Lead judgment
Read references/lead-judgment.md, then categorize every finding:
- Act on: concrete correctness, security, or maintainability issues that should block the change.
- Consider: legitimate tradeoffs whose benefit may not exceed their cost now.
- Noted: valid but low-priority or context-dependent observations.
- Dismissed: wrong, nitpicky, hypothetical, or missing known context.
Name the reviewers that raised each finding and give a one-line rationale. Consensus is strong evidence, not a substitute for tracing the code.
Output contract
IntentReviewers—configuration, model-diversity status, and finding countAct OnConsiderNotedDismissedAgreement MapCoverage Gaps
Do not edit code or create review comments unless the user separately authorizes those actions.
