skills.rest
The-Rabak
The-RabakCOMMUNITY
Explore all skills by this author →
GitHub

disabled-skill

Disables model invocation in SKILL.md frontmatter via flag for runtime-safe plugins.

1|1|Updated Mar 3, 2026
Search Tags:#security#compliance#safety#plugins#control#disable#model-invocation
One-click install
npx skills add https://github.com/The-Rabak/compound-engineering-plugin --skill disabled-skill-the-rabak
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: disabled-skill
Source: https://github.com/The-Rabak/compound-engineering-plugin/tree/main/tests/fixtures/sample-plugin/skills/disabled-skill
Command: npx skills add https://github.com/The-Rabak/compound-engineering-plugin --skill disabled-skill-the-rabak

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Disabled model invocation in a Skill helps prevent unauthorized external AI calls, reducing risk in plugin workflows.

Core Features & Use Cases

  • Enforces a flag (disable-model-invocation) to block runtime model calls.
  • Useful for safe testing, sandbox environments, and handling confidential data.
  • Use case: When building a plugin that should never reach out to remote models, enable this feature to guarantee local-only operations.

Quick Start

In the YAML frontmatter of SKILL.md, set disable-model-invocation to true and ensure the runtime respects this by skipping all model calls.

Frequently Asked Questions about disabled-skill

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

FAQPage Schema
How do I disable model invocation in a plugin to prevent external AI calls?▼

To disable model invocation, set the disable-model-invocation flag to true in your SKILL.md YAML frontmatter. This enforces local-only operations by directing the runtime to bypass all automated external AI calls.

What is the disable-model-invocation flag used for in plugin workflows?▼

The disable-model-invocation flag is a safety mechanism used to block runtime model calls in plugin workflows. It prevents unintended external AI calls, reducing security risks when handling confidential data or operating in sandbox environments.

When should I enforce local-only operations by disabling external model calls?▼

You should enforce local-only operations when building plugins that must never reach out to remote models. Disabling external model calls guarantees safety during testing, within sandbox environments, and when processing confidential data.

Does the runtime automatically respect the disable-model-invocation flag in SKILL.md?▼

The runtime respects the disable-model-invocation flag when configured to bypass automated model usage. You must ensure your runtime environment actively checks this SKILL.md frontmatter setting to successfully skip all external model calls.

Can I use this approach to secure plugins handling confidential data in a sandbox?▼

Yes, disabling model invocation secures plugins handling confidential data in a sandbox. By enabling the flag, you guarantee local-only operations and block any unauthorized external AI calls from the runtime environment.

Related Skills

Explore More Software Engineering Skills→
bastani-incbastani-inc
484

disable-model-invocation

Prevent automatic model selection of manually controlled skills via SKILL.md frontmatter flag.

Official
Basic
Knuckles-TeamKnuckles-Team
2

python-sandbox

...

Official
Basic
trabiantrabian
18

fluxwing-validator

Validate uxscii components and screens against JSON Schema.

Official
Advanced
mathematic-incmathematic-inc
112

secure-agent

Configures agent permissions and restricts network access via NACL rules.

Official
Intermediate