Skip to content
Skills Library
AI & agents · Review & audit

interrogate

/interrogate

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.

Repository
t3-pstack ↗
Licence
MIT
Last repository change
27.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
5
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

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.

Triggers from the description

interrogate\adversarial review\multi-model review\challenge this\stress test this code\find blind spots\tear this apart\
Original author 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.

How it works

  1. Step 1, Scope
  2. Step 2, Intent
  3. Step 3, Spawn Reviewers
  4. Step 4, Synthesize
  5. Step 5, Lead Judgment
  6. Output Format
  7. Models
Original SKILL.md headings · 77 lines, 815 words
SKILL.md preview
---
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."
disable-model-invocation: true
---

# Interrogate

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 response with `delegate_task`, one per entry on the `interrogate reviewers` line in the model sheet, labeled Reviewer A, B, and so on to match the entry count. If the sheet or that line is missing, use the table defaults.

| Subagent | Default model |
|----------|---------------|
| Reviewer A | `claudeAgent/claude-opus-5-5 effort=xhigh` |
| Reviewer B | `codex/gpt-6.1-sol reasoningEffort=xhigh` |
| Reviewer C | `grok/grok-4.7 reasoningEffort=xhigh` |

Each reviewer gets `role: "review"`, a brief that says to inspect only and change no file, and `target` set from its configured entry, or from its table default when there is no configured line. Omit `target` for an `auto` or `inherit-parent` entry, so that reviewer runs on the parent model.

If `delegate_task` rejects a configured entry, run that reviewer on another target of the same family from `orchestrator_capabilities` and say so. A model's family is the first segment of its ID's last `/` part, such as `claude`, `gpt`, or `grok`, whatever provider instance serves it. With no family match, use Reviewer A's default. If it rejects a table default, spawn on the closest target of the same family from `orchestrator_capabilities` (prefer the same reasoning tier), 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`. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill.

## 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.]

## Models

Role defaults on T3, stamped from `plugins/pstack/models.json`. A role line in the model sheet overrides each one. The sheet is `~/.config/t3-pstack/models.md` (`$XDG_CONFIG_HOME/t3-pstack/models.md` when that is set), one per machine, and `/setup-pstack` writes it. When it is missing, read `t3-pstack-models.md` in the host's config directory (`$CLAUDE_CONFIG_DIR` or `~/.claude` on Claude Code, `$CODEX_HOME` or `~/.codex` on Codex). An entry is `<providerInstanceId>/<modelId>` plus `<optionId>=<value>` pairs, and it maps onto `delegate_task`'s `target`, with the provider instance as `providerInstanceId`, the model as `model`, and the pairs as `options`. It splits at its first `/`, so a model ID with its own `/`, such as OpenCode's `<provider>/<model>`, is written whole after it. Option IDs differ per provider, so take them from `orchestrator_capabilities`. `inherit-parent` or `auto` omits `target`.

- interrogate reviewers: `claudeAgent/claude-opus-5-5 effort=xhigh`, `codex/gpt-6.1-sol reasoningEffort=xhigh`, `grok/grok-4.7 reasoningEffort=xhigh`
Files in this package (5)
  • SKILL.md 6 KB
  • references/code-quality-review.md 5 KB
  • references/lead-judgment.md 2 KB
  • references/reviewer-prompt.md 2 KB
  • references/rubric.md 5 KB

Versions

RepositoryScoreLicence
This page · chhoumann/t3-pstack90MIT
hootener/brain100MIT
requie/endostack100MIT
Sup-Film/pstack-omp-lean100MIT
RIJUDEVx/agent-skills90MIT
chmonitor/chmonitor90GPL-3.0
richardochristjia/skills90MIT
backnotprop/pstack90MIT
arjitj2/open-pstack90MIT

Database snapshot: 13.11.2026 · package version 39f3168506f0 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100comms-interrogate
    Multi-reviewer critique of a diff, run as parallel read-only subagents from distinct angles, then synthesized into one verdict. Use for "interrogate", "adversarial review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
  • 100lie-detector
    Toph's lie detector for multi-model adversarial review. She feels a heartbeat through the ground and knows when someone is lying, so a change that only claims to work does not fool her. Use for interrogate, /interrogate, adversarial review, multi-model review, "challenge this",…
  • 90mroowa-interrogate
    Adversarially review code changes with one read-only reviewer and a parent judgment pass. Use for interrogate, challenge this code, stress test this diff, find blind spots, or a requested adversarial code review.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.