version: "1.0.1" 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

Delegation and optional capabilities follow ../poteto-mode/references/codex-agent-runtime.md.

Spawn one reviewer per configured model to adversarially review code changes. Each model gets the same prompt and rubric. The adversarial signal comes from model diversity, not assigned personas. Models differ in blind spots, priors, and reasoning patterns. Agreement across models is high-confidence signal; lone-model findings are worth reading but lower confidence.

Step 1, Scope

Identify what to review from context:

• If the user points at specific files or a diff, use that.
• If on a feature branch, run git diff main...HEAD (or the appropriate base branch) for the full changeset.
• If the user's message references recent work, gather the relevant files.

Package the diff and the surrounding context each reviewer needs.

Step 2, Intent

Derive the intent from the user request, code, commit messages, and any PR description. Write one clear paragraph. Reviewers challenge whether the work achieves the intent well, not whether the intent itself is correct. If you're unsure about the intent, ask the user before proceeding.

Step 3, Spawn Reviewers

Launch all reviewers in a single message using the supported subagent tools. Use the interrogate reviewers list from the installed pstack model profiles when present, one reviewer per entry, extending or shrinking the Reviewer A/B/C/D labels below to the configured entry count; otherwise use the table defaults.

Each reviewer uses a validated configured profile or a generic read-only agent with an inherited model pair. Keep model and reasoning_effort separate. When a requested pair is unavailable, follow that role's declared substitute, inherit, skip, or fail-closed policy. Report skipped lanes and unverified served identities. Do not open a configuration PR unless the active request authorizes repository writes.

Read references/reviewer-prompt.md and fill in the same template for every reviewer with the stated intent, the diff or file contents, the rubric from references/rubric.md, and the code-quality lens from references/code-quality-review.md. Inherit the parent model and reasoning effort unless the user or a validated profile requests another available pair.

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

Step 4, Synthesize

As results come back, build a unified picture. Parse every reviewer's findings. Merge findings that describe the same issue differently, and note which models raised each one. Findings two or more models raised independently are the highest signal. Read a lone model's finding, but weight it accordingly. Note disagreements. If one model flags something and another explicitly says the opposite, that is context for the verdict.

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. Put every finding in one of four buckets, with the model(s) that raised it and a one-line rationale.

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

Output Format

Intent

[The stated intent paragraph from Step 2]

Reviewers

• Reviewer [label]: [model name], [N findings] (one bullet per reviewer)

Act On

[Each: description, which models raised it, why it matters.]

Consider

[Each: description, which models raised it, the tradeoff.]

Noted

[Brief list.]

Dismissed

[Each with a brief rationale.]

Agreement Map

[Where models agreed and diverged, and what that pattern tells us.]