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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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.
## 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
…
The line at the top of this page pins the label git:20260827.f7b391a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5830 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
shiwenbin1617/pstack · 4 stars · license a license file GitHub does not identify · pushed 2026-09-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q2gexbuurrj6udw4
GET https://markdownregistry.com/api/v1/resolve?ref=shiwenbin1617/pstack/interrogate
GET https://markdownregistry.com/api/v1/blob/5455d9dd49f4a7fe8f7e0ff5b4188e68d5fa416b89e285fc68193d57a9c59a99
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
shiwenbin1617/pstack · adapters/claude-code/overrides/setup-pstack/SKILL.md · Configure which Claude Code models pstack uses per role. Use for /setup-pstack or requests to change pstack model…
shiwenbin1617/pstack · adapters/codex/overrides/setup-pstack/SKILL.md · Configure optional per-role model preferences for pstack on Codex. Use for $setup-pstack or requests to change pstack…
shiwenbin1617/pstack · automations/benny/skills/reproduce-and-fix-issues/SKILL.md · Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft…
shiwenbin1617/pstack · automations/benny/skills/setup-benny/SKILL.md · Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker…
shiwenbin1617/pstack · skills/architect/SKILL.md · Design types, interfaces, and module ownership for a requested architectural change or an unresolved design choice.
shiwenbin1617/pstack · skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
shiwenbin1617/pstack · skills/automate-me/SKILL.md · Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a…
shiwenbin1617/pstack · skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
shiwenbin1617/pstack · skills/create-verification-skill/SKILL.md · Generate a project-local verification skill that drives your app the way a user does — any language, framework, or…
cursor/plugins · pstack/skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
cursor/plugins · harness/pstack/claude-code/skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
nightly-labs/openbot · marketplace/production-catalog/bundles/pstack/skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
michael-denyer/pstack-claude · plugins/pstack/skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
backnotprop/pstack · skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
saadshahd/moo.md · hope/skills/interrogate/SKILL.md · Make the user defend a proposal they committed to. Use when a proposal is committed but its decisions are undefended.
iap/pstack-hermes · skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
barbieri/local-openfinance · .agents/skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…