From gws
Google Model Armor: Sanitize a model response through a Model Armor template.
npx claudepluginhub fakoli/fakoli-plugins --plugin gwsThis skill uses the workspace's default tool permissions.
> **Reference:** See the `gws-shared` skill for auth, global flags, and security rules.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
Reference: See the
gws-sharedskill for auth, global flags, and security rules.
Sanitize a model response through a Model Armor template
gws modelarmor +sanitize-response --template <NAME>
| Flag | Required | Default | Description |
|---|---|---|---|
--template | ✓ | — | Full template resource name (projects/PROJECT/locations/LOCATION/templates/TEMPLATE) |
--text | — | — | Text content to sanitize |
--json | — | — | Full JSON request body (overrides --text) |
gws modelarmor +sanitize-response --template projects/P/locations/L/templates/T --text 'model output'
model_cmd | gws modelarmor +sanitize-response --template ...