johanthoren

Cook Refute — Security agent for Claude Code

Security community

jeff refute pass.

How to install Cook Refute

Installs to ~/.claude/agents/johanthoren-jeff-cook-refute.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/johanthoren/jeff/HEAD/agents/cook-refute.md -o ~/.claude/agents/johanthoren-jeff-cook-refute.md

Restart Claude Code, or start a new session, for it to be picked up.

What Cook Refute does

name: cook-refute description: jeff `refute` pass. Adversarially test exactly one blocking review, verification, or audit finding before it triggers a kickback. Verdict survives or refuted, with evidence. Do not edit. effort: xhigh tools: Read, Grep, Glob

You are the **refute** station of the jeff brigade, working one contested finding in a fresh context. A reviewer, verifier, or auditor classified it **blocking**. Before it buys an expensive kickback, test whether it is reachable and h

Alternatives in Security

  • Patina Fidelity Auditor — Triggers to audit whether a patina rewrite preserved meaning versus the original text 352 ★
  • Audit Verifier — Adversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, whe 335 ★
  • Deploy — Deploy to target platform — Vercel, Netlify, Fly.io, AWS, VPS 85 ★

Full documentation available on GitHub

View Source Repository

Related Agents

Audit Skeptic — Security agent for Claude Code

Audit Skeptic

Tries to refute one skill-audit finding through one named verification lens and returns a verdict with its evi

Security community
Cook Audit — Security agent for Claude Code

Cook Audit

jeff audit stage (conditional: runs when the plan flags a security-relevant surface, or when the mechanical sc

Security community
Finding Skeptic — Security agent for Claude Code

Finding Skeptic

Read-only adversarial verifier for audit findings. Given one finding and one skeptic lens, actively tries to r

Security community
Result Auditor — Security agent for Claude Code

Result Auditor

Use when analysis results must be adversarially verified before they enter an application. Triggers 분석 검증, 재현

Security community
Vuln Validator — Security agent for Claude Code

Vuln Validator

Independently tries to refute candidate vulnerabilities and records a reasoned verdict for each. Must be a dif

Security community
Team Reviewer — Security agent for Claude Code

Team Reviewer

Adversarial code review and verification. Operates with a single lens per invocation (security, correctness, p

Security community

Related Skills

Zp Validate — Development skill for Claude Code

Zp Validate

Adversarially verify a finding by trying to refute it. Usage: /zp-validate

Development community
Lane Verify — Development skill for Claude Code

Lane Verify

Out-of-domain verification lane. Independently REFUTE other lanes' done-claims, defaulting to refuted when unc

Development community
Recall Promote — Development skill for Claude Code

Recall Promote

Promote a recall finding (correction/preference/domain fact) into project auto-memory so it survives without n

Development community