decision-razor

Infer and execute the best action without seeking user permission.

Updated Nov 30, 2025
One-click install
npx skills add https://github.com/poisontr33s/chthonic-archive --skill decision-razor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision-razor
Source: https://github.com/poisontr33s/chthonic-archive/tree/main/.codex/skills/decision-razor
Command: npx skills add https://github.com/poisontr33s/chthonic-archive --skill decision-razor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Anti-paralysis behavior protocol that prevents agent stalls by inferring and executing actions without unnecessary questioning.

Core Features & Use Cases

  • Embedded into agent behavior to prevent permission loops and indecision.
  • Provides a single-path execution when faced with multiple options.
  • Improves responsiveness in high-stakes tasks by avoiding analysis paralysis.

Quick Start

Apply the decision razor to infer the best action and execute without asking for permission when hesitation is detected.

Frequently Asked Questions about decision-razor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stop my AI agent from getting stuck in permission loops?

To stop AI agent permission loops, apply an anti-paralysis protocol that forces inference-first decisions and immediate execution without seeking user permission, delivering a single decisive output.

What is the best way to handle ambiguity in automated agent workflows?

Handling ambiguity in automated agent workflows requires a decision razor that infers the best action from multiple options and executes it immediately, preventing analysis paralysis and improving task responsiveness.

How do I enforce single-path execution when an AI agent faces multiple options?

Enforcing single-path execution involves applying a behavior protocol that automatically infers the best action when hesitation is detected, bypassing preparatory dialogue to output a minimal final artifact.

Can I prevent analysis paralysis in high-stakes AI tasks without manual intervention?

Yes, preventing analysis paralysis in high-stakes AI tasks without manual intervention is possible by embedding a decision protocol that executes actions automatically without asking for permission when ambiguity arises.

When should I avoid using an automatic inference and execution protocol for agents?

You should avoid using an automatic inference and execution protocol when your specific task explicitly requires user confirmation before taking action, as this protocol skips permission loops and preparatory dialogue entirely.