interrogate

name	interrogate
description	Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

Interrogate

Spawn independent reviewers to adversarially review code changes. Every reviewer gets the same prompt and rubric. Prefer different model families when the host supports model selection; otherwise use fresh isolated contexts. Agreement across reviewers is high-confidence signal; lone-reviewer findings remain useful but carry less weight.

The deliverable is a synthesized verdict. Do NOT auto-apply changes.

Step 1, Determine Scope

Identify what to review from context:

• If the user points at specific files or a diff, use that
• If on a feature branch, diff against the repository's declared target or merge base (for example git diff origin/main...HEAD)
• If the user's message references recent work, gather the relevant files

Package the diff (or file contents) plus any surrounding context files the reviewers need to understand the code.

Step 2, State the Intent

Before spawning reviewers, state the intent explicitly. What is this code trying to accomplish? Derive this from:

• The user's message
• Commit messages
• PR description if one exists
• The code itself

Write one clear paragraph. Reviewers challenge whether the work achieves the intent well, not whether the intent itself is correct. When context supports a reasonable interpretation, state it and continue; ask only when different interpretations would materially change the review.

Step 3, Spawn Reviewers

Launch 2-4 read-only reviewers concurrently. Use available subagents and select different model families when supported. If subagents are unavailable, run separate review passes with isolated notes and state that model diversity was unavailable.

Read references/reviewer-prompt.md and fill in the template with:

1. The stated intent
2. The diff or file contents
3. The review rubric from references/rubric.md
4. The code-quality lens from references/code-quality-review.md

The same filled template goes to all reviewers, so every model applies the code-quality lens.

Each reviewer produces structured findings as described in the prompt template.

Step 4, Synthesize

As results come back, build a unified picture:

1. Parse all findings from the reviewers
2. Identify consensus. Findings raised by 2+ reviewers independently are highest signal.
3. Identify lone-reviewer findings. Still worth reading, but weight accordingly.
4. Deduplicate. Reviewers may describe the same issue differently. Merge these and note who raised it.
5. Note disagreements. If one reviewer flags something and another explicitly says the opposite, preserve that context.

Step 5, Lead Judgment

You are the lead reviewer, a pragmatic senior engineer, not a neutral aggregator.

Read references/lead-judgment.md for the full framework. Reviewers only see a slice of the codebase. You have the full context (the goal, the constraints, the timeline, which tradeoffs were already considered). Use that context aggressively.

Categorize every finding using these buckets:

• Act on. Real issues affecting correctness, security, or maintainability given the actual goals. These would block a real PR.
• Consider. Legitimate points, but you're not sure they outweigh the cost of addressing them right now. Worth the user's attention.
• Noted. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact given the current stage.
• Dismissed. Wrong, nitpicky, or missing context. Brief explanation why.

For each finding, include:

• Which reviewer(s) raised it
• The category (act on / consider / noted / dismissed)
• A one-line rationale for the categorization

Output Format

Present the verdict in this structure:

Intent

[The stated intent paragraph from Step 2]

Reviewers

List each reviewer on its own line like - <reviewer label>: [N findings]

Act On

[Findings that should be addressed. For each: description, which reviewers raised it, why it matters.]

Consider

[Findings worth thinking about. For each: description, which reviewers raised it, tradeoff involved.]

Noted

[Valid but low-priority. Brief list.]

Dismissed

[Rejected findings with brief rationale. This shows the user what was filtered out and why, so they can override your judgment if they disagree.]

Agreement Map

[Where did reviewers agree, where did they diverge, and what does the pattern of agreement or disagreement tell us?]