interrogate

An adversarial code-review skill that asks multiple language models to inspect the same changes independently. It combines their findings into a verdict instead of applying edits automatically.

In plain words
What is it for?
Use it to review a diff or selected files, challenge an implementation, find hidden problems, and compare review findings across configured models.
Why use it?
It exposes blind spots that one reviewer may miss and makes agreement between independent reviewers a stronger signal.

Skill for Claude CodeCodex

Part of the pstack plugin — 52 skills, 2 agents, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/michael-denyer/pstack-claude/interrogate
Any agent
npx skills add michael-denyer/pstack-claude --skill interrogate
Clone the repo
git clone --depth 1 https://github.com/michael-denyer/pstack-claude

Made for: Claude Code, Codex.

Or install pstack, the plugin that ships this one along with the rest of its 52 skills, 2 agents, 1 hook.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.01311
Opus 5 $0.00026 $0.00656
Sonnet 5 $0.00010 $0.00262
Haiku 4.5 $0.00005 $0.00131

Measured 3d ago against content hash 01c2ab1a3b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interrogate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to interrogate — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/pstack/skills/interrogate/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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. 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.

The deliverable is a synthesized verdict. Do NOT auto-apply changes.

Platform note. On Codex or another non-Claude runtime, the subagent_type/model/readonly dispatch fields and the claude-* model slugs below are Claude defaults. Resolve them via codex-tools.md (dispatch maps to spawn_agent; substitute your configured Codex models, keeping the panel model-diverse).

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.

Step 2, State the Intent

Before spawning reviewers, state the intent explicitly. What is this code trying to accomplish? Derive this from:

  • The user's message
  • Commit messages
  • PR description if one exists
  • The code itself

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 Agent tool. Use the interrogate reviewers list from ~/.claude/pstack-models.md 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.

Subagent Default model
Reviewer A claude-opus-5
Reviewer B claude-fable-5
Reviewer C claude-sonnet-5

Read the full file on GitHub · 115 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 115 lines · 51 tokens per session scan A 01c2ab1a3b10

Subscribe to this mod's changes

interrogate is a skill published in the GitHub repository michael-denyer/pstack-claude (142 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 1,311 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to interrogate, differing in 17 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens