KunanonJ/superstacks / plugins/superstacks/skills/interrogate
interrogate
UnverifiedUse for interrogate, adversarial review, multi-model review, challenge this, stress test this code, or find blind spots.
Interrogate
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.
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, 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) plus any surrounding context files the reviewers need to understand the code.
Classify the change. A finder or refuser is code whose job is to find things or refuse things: a scanner, inventory, guard, lint rule, drift test, validator, allowlist check. Reviewers who read it and its tests tend to pass it, because its blind spots are invisible from inside. If the change adds or alters one, the "Finders and refusers" section of the rubric is mandatory and the verdict carries an Independent Check section.
Step 2, State the Intent
Before spawning reviewers, state the intent explicitly. Derive this from:
- The user's message
- Commit messages
- PR description if one exists
- The code itself
Write one clear paragraph. 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 Task tool. Use the reviewer table in the workflow-profile skill, one reviewer per entry, extending or shrinking the Reviewer A/B/C labels below to the configured entry count. If that table is missing, use the defaults here (omit model so each reviewer uses the parent).
| Subagent | Default model |
|---|---|
| Reviewer A | omit model (parent) |
| Reviewer B | omit model (parent) |
| Reviewer C | omit model (parent) |
For each reviewer:
subagent_type:generalPurposemodel: the configuredinterrogate reviewersentry, or the table default with no configured line. For anautoorinherit-parententry, omitmodelso that reviewer runs on the parent model.readonly:true; for a finder or refuser change,false, so the reviewer can run probes, with the instruction to write only inside a scratch directory outside the checkout and to leave the checkout untouched
If the Task tool rejects a configured entry, omit model for that reviewer and say so. Do not block the review on a slug issue. Never treat an alias entry as a rejected slug.
Read references/reviewer-prompt.md and fill in the template with:
- The stated intent
- The diff or file contents
- The review rubric from
references/rubric.md - 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.
Step 4, Synthesize
As results come back, build a unified picture:
- Parse all findings from the reviewers
- Identify consensus. Findings raised by 2+ models independently are highest signal.
- Identify lone-model findings. Still worth reading, but weight accordingly.
- Deduplicate. Different models may describe the same issue differently. Merge these and note which models raised it.
- Note disagreements. If one model flags something and another explicitly says the opposite, that's useful 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.
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 model(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
- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)
Act On
[Findings that should be addressed. For each: description, which models raised it, why it matters.]
Consider
[Findings worth thinking about. For each: description, which models raised it, tradeoff involved.]
Noted
[Valid but low-priority. Brief list.]
Dismissed
[Rejected findings with brief rationale.]
Independent Check
[Finder or refuser changes only. The independent method, each probe as found or missed, and for each missed form whether it exists in the real code today. Without this section the change was not reviewed.]
Agreement Map
[Where did models agree, where did they diverge, and what does the pattern of agreement/disagreement tell us?]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |