Michael RamosEQTY Lab co-founder, Plannotator creator, 9k+ stars503 installs on skills.sh

Interrogate

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test...

Works in any agentClaude CodeCodexCursorClaude appChatGPT+ any other agent
backnotprop/pstack
Security state: reviewed

3 static scans, 0 counted findings.

Edge checks it again each time your agent loads it.

SKILL.md5 files · 21.7 KB

From the backnotprop public repository. Edge did not write or edit this skill.

What it does

  • 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.
MR

Why Michael Ramos

Co-founder at EQTY Lab. Each fact links its public source.

  • 9k+ GitHub stars on Plannotator

    His Plannotator lets teams annotate and review coding agent plans and diffs, with over 9,000 stars.

    GitHub
  • Co-founder at EQTY Lab

    He is a co-founder at EQTY Lab, after a decade building complex public sector systems.

    X profile
  • Authored the Claude Code hooks request

    He wrote the feature request behind Claude Code hooks and built agent policy tools at EQTY Lab.

    backnotprop.com

Public sources, checked Oct 26, 2026.

How it works

  1. 1
    Copy

    Try for free gives you one prompt.

  2. 2
    Paste

    Paste it into Claude Code, Codex or Cursor.

  3. 3
    Ask

    Ask for the outcome. Your agent loads Interrogate.

What you can inspect

3 static scans, 0 counted findings.

Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.

State definitions

Skill details

Security scansReviewed

3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.

Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .

Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 1.

Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .

Edge static checks
Pass · 0 counted findings · 2026-09-27
Cisco skill-scanner
Pass · 0 counted findings · 2026-09-27
Semgrep Edge rules
Pass · 0 counted findings · 2026-09-27
Creator, source & licencebacknotprop

From the backnotprop public repository. Edge did not write or edit this skill.

Revision
157aae39a733135e93d8b5b19ff62c6a84b0ad56
Package hash
sha256:c85e93a4592d3407092f8b445244004acfe14e9dc5743ef95a1cc48d7a761ba2
Licence
MIT
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.
Quoted from the skill’s own description
Read skill files5 files

5 files, 21.7 KB at revision 157aae39a733.

Questions about Interrogate

What does Interrogate do?

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test... Published by Michael Ramos (backnotprop/pstack).

Is Interrogate safe to use?

Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.

How do I use Interrogate in Claude Code, Codex or Cursor?

Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.