Spawn one reviewer per configured model to adversarially review code changes. The adversarial signal comes from model diversity, not assigned personas. 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 Task tool, one per entry of the interrogate reviewers role, labeled Reviewer A, B, and so on to match the entry count. Its default is the table below. Use the pstack-harness skill for the spawn. Its Spawn a role section resolves the role and builds this CLI's spawn call.
| Subagent | Default model |
|---|---|
| Reviewer A | fable |
| Reviewer B | opus |
| Reviewer C | sonnet |
For each reviewer:
subagent_type:general-purposemodeland effort: that reviewer's resolved arm, per Spawn a role.readonly:true
If the Task tool rejects a configured entry or a table default, use the pstack-harness skill to handle it. When it rejects a table default, also open a separate PR to update this step's Default model table and skills/setup-pstack/examples/pstack-models.md in the pstack repository, the file the resolver reads. Do not block the review on the slug issue. Never treat an alias entry as a rejected slug.
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.
Step 4, Synthesize
As results come back, build a unified picture. Before you merge anything, state which models the reviewers ran on and count arms that shared a model as one reviewer. 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.]