skills.rest
AndrewRober
AndrewRoberCOMMUNITY
Explore all skills by this author →
GitHub

guard-users-llama

Classify Llama CLI requests into risk classes and enforce scoped approvals.

Updated Feb 23, 2026
Search Tags:#security#cli#policy#guardrails#approvals#risk-classification#llama
One-click install
npx skills add https://github.com/AndrewRober/CodexCli-GuardRails --skill guard-users-llama
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: guard-users-llama
Source: https://github.com/AndrewRober/CodexCli-GuardRails/tree/main/skills/guard-users-llama
Command: npx skills add https://github.com/AndrewRober/CodexCli-GuardRails --skill guard-users-llama

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Llama CLI users need safety controls to prevent destructive, credential-related, or risky operations. This policy provides guardrails, scoped approvals, and redaction guidance to keep workflows safe.

Core Features & Use Cases

  • Refuse catastrophic actions unconditionally and require safer alternatives.
  • Enforce explicit approvals for destructive and high-risk operations using structured payloads.
  • Enforce workspace scope, secret handling guidance, and clear risk classifications for each command.
  • Integrate with loader systems to produce policy-compliant classification outputs and approvals.

Quick Start

Provide a safe initial request to classify a Llama CLI action and generate the required approval payload.

Frequently Asked Questions about guard-users-llama

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

FAQPage Schema
How do I add approval guardrails to Llama CLI workflows?▼

To add approval guardrails to Llama CLI workflows, this policy classifies requests into risk classes (X/3/2/1/0) and enforces explicit approvals for destructive operations using structured payloads.

What is risk classification for CLI actions and how does it prevent destructive operations?▼

Risk classification for CLI actions categorizes commands into risk levels (X/3/2/1/0) to prevent destructive operations. It unconditionally refuses catastrophic actions and requires safer alternatives.

How do I enforce workspace scope and secret handling rules in a CLI policy?▼

To enforce workspace scope and secret handling rules in a CLI policy, the system validates the workdir scope, detects credential and secret risks, and ensures only safe, policy-compliant actions are allowed.

Can I require explicit approvals for high-risk CLI commands?▼

Yes, you can require explicit approvals for high-risk CLI commands. The policy enforces structured payload guidance for authorization, validating approval prefixes and risk classifications before allowing destructive operations.

What are the limitations of using automated risk classification for command-line guardrails?▼

Automated risk classification for command-line guardrails focuses on validating workdir scope, approval prefixes, and risk classes, but requires integration with loader systems to produce policy-compliant classification outputs correctly.

Related Skills

Explore More Software Engineering Skills→
hujianbesthujianbest
51

hf-frame

Define project scope and risk during HarnessFlow's Frame stage.

Community
Intermediate
tachyon-zcashtachyon-zcash
56

book-refine

Incorporate user feedback into book review policies and standards.

Official
Advanced
AdeptMindAdeptMind

secret-rotation

Scan codebases for hardcoded secrets and audit rotation policies.

Official
Advanced
AndrewRoberAndrewRober

guard-users-aider

Enforces scoped approvals and payload rules for high-risk commands in the Aider CLI.

Community
Advanced