ahel
Start free

Red Team

SkillAI & models

Adversarial stress-test of code, a plan, or an argument. Three critics attack, one defender rebuts, a referee judges, then a hostile auditor attacks the synthesis itself.

Use Red Team in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Red Team and connect your AI. About a minute.

ClaudeChatGPTAhel Desktop

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Red Team skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Red TeamStart free

What this skill tells your AI

The instructions your AI receives, as published by griffinhilly/claude-code-synthesis in skills/red-team/SKILL.md and read by ahel’s review.

Run the dialectic-review skill in review mode with the hostile auditor enabled by default. Read ~/.claude/skills/dialectic-review/SKILL.md for argument parsing and ~/.claude/skills/dialectic-review/review-prompts.md for the phase prompts. Any /dialectic-review flag is valid here — it passes straight through.

Audit default: Unless the user passed --no-audit in $ARGUMENTS, append --audit to the invocation. This is what differentiates /red-team from plain /dialectic-review --mode review: red-team always closes the loop by attacking its own synthesis.

Invocation:

  • If $ARGUMENTS contains --no-audit — run /dialectic-review $ARGUMENTS (strip --no-audit before passing through; plain review mode, no auditor).
  • Otherwise — run /dialectic-review --audit $ARGUMENTS.

Follow the full three-phase review process, then the Phase 4 Hostile Auditor defined in the dialectic-review SKILL.md.

Signals

GitHub stars
67
Forks
6
Last commit
Aug 2026
Advanced
Item type
skill
Key
red-team-griffinhilly
Source
github.com/griffinhilly/claude-code-synthesis

github.com/griffinhilly/claude-code-synthesis

More in AI & models

skill-creator
Skill · anthropics
More in AI & modelstriage
Skill · mattpocock
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsmarketing-psychology
Skill · coreyhaines31
More in AI & models