pstack-interrogate

Interrogate

Spawn one reviewer per configured role entry to adversarially review code changes. OMK delegates inherit the session model, so independent briefs provide review separation, not model diversity. The deliverable is a synthesized verdict. Do NOT auto-apply changes.

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 or file contents with any surrounding context files the reviewers need to understand the code.

Step 2, Intent

Before spawning reviewers, state the intent in one clear paragraph from the user's message, commit messages, the PR description if one exists, and the code. If you're unsure about the intent, ask the user before proceeding.

Step 3, Spawn Reviewers

Launch all reviewers in a single message with the subagent extension, one per entry on the interrogate reviewers line in the pstack settings file (~/.omk/agent/pstack-models.md, written by /skill:pstack-setup-pstack), labeled Reviewer A, B, and so on to match the entry count. If the file or that line is missing, use the table defaults.

Subagent tool. Spawns in this skill use OMK's subagent extension. Call it with agent, task, and agentScope, and use tasks: [{agent, task}, ...] for a parallel fan-out. Keep the prompt and inherit the session model. Pass no model, effort, or speed fields. If the subagent extension is not loaded or the project is not trusted, run each reviewer yourself, one after another.

Subagent	Default model
Reviewer A	inherit-parent
Reviewer B	inherit-parent

Each reviewer is a read-only subagent call. OMK subagents inherit the session model, so auto and inherit-parent entries need no model field; a configured entry that is not in the OMK catalog also falls back to the session model.

If a configured entry is not in the OMK catalog, run that reviewer on the session model and say so. If a table default is not in the OMK catalog, run that reviewer on the session model, and open a separate PR to update the default table. Do not block the review on the slug issue. Never treat an alias entry as a rejected slug or apply either fallback to it.

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. OMK subagents inherit the session model and effort; pass no model, effort, or speed fields.

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 reviewer labels raised each one. Findings two or more reviewers raised independently are the highest signal. Read a lone reviewer's finding, but weight it accordingly. Note disagreements. If one reviewer 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 reviewer label(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 reviewers 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 reviewers agreed and diverged. State that shared-model agreement is not cross-model evidence.]