gws-modelarmor-sanitize-prompt

gws-modelarmor-sanitize-prompt is a skill for Claude Code from fakoli/fakoli-plugins. It costs 24 tokens per session (298 once invoked), scanned A, original, MIT.

A command that sends user-provided text or JSON through a Google Model Armor template before it is used as a prompt. Model Armor is a Google service for filtering potentially unsafe content.

In plain words
What is it for?
Sanitizing prompts using a named Model Armor template, including text from standard input.
Why use it?
It helps screen incoming content for safety rules before passing it to a model.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the gws plugin — 94 skills, 15 commands, 11 agents shipped together

Good fit Sanitizing prompts using a named Model Armor template, including text from standard input.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fakoli/fakoli-plugins/gws-modelarmor-sanitize-prompt
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add fakoli/fakoli-plugins --skill gws-modelarmor-sanitize-prompt
Clone the repo
git clone --depth 1 https://github.com/fakoli/fakoli-plugins

Made for: Claude Code.

Or install gws, the plugin that ships this one along with the rest of its 94 skills, 15 commands, 11 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gws-modelarmor-sanitize-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/gws-modelarmor-sanitize-prompt/github.svg)](https://agentmods.dev/skills/fakoli/fakoli-plugins/gws-modelarmor-sanitize-prompt)
Your own site
<a href="https://agentmods.dev/skills/fakoli/fakoli-plugins/gws-modelarmor-sanitize-prompt"><img src="https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/gws-modelarmor-sanitize-prompt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gws-modelarmor-sanitize-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/fakoli/fakoli-plugins/gws-modelarmor-sanitize-prompt"><img src="https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/gws-modelarmor-sanitize-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00298
Opus 5 $0.00012 $0.00149
Sonnet 5 $0.00005 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 8d ago against content hash 6eaef823e406, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gws-modelarmor-sanitize-prompt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/gws/skills/gws-modelarmor-sanitize-prompt/SKILL.md · 42 lines

What it actually says

modelarmor +sanitize-prompt

Reference: See the gws-shared skill for auth, global flags, and security rules.

Sanitize a user prompt through a Model Armor template

Usage

gws modelarmor +sanitize-prompt --template <NAME>

Flags

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)

Examples

gws modelarmor +sanitize-prompt --template projects/P/locations/L/templates/T --text 'user input'
echo 'prompt' | gws modelarmor +sanitize-prompt --template ...

Tips

  • If neither --text nor --json is given, reads from stdin.
  • For outbound safety, use +sanitize-response instead.

See Also

  • gws-shared — Global flags and auth
  • gws-modelarmor — All filter user-generated content for safety commands
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 42 lines · 24 tokens per session scan A 6eaef823e406

Subscribe to this mod's changes

gws-modelarmor-sanitize-prompt is a skill published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 298 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

ai-prompting-basics

A practical guide to writing clearer requests for Claude, an AI assistant, by adding context, examples, roles, and output rules.

modu-ai/moai-cowork · 75 tokens

lyra

Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.

joaquimscosta/arkhe-claude-plugins · 56 tokens

engineering-prompts-and-output

Use when writing or reviewing system prompts, few-shot examples, structured output via tool use, JSON schema validation with retry loops, Message Batches API processing, or multi-instance/multi-pass review pipelines such as automated PR reviewers. Also when outputs are inconsistent between runs, JSON fails validation…

atretyak1985/swarmery · 118 tokens

llm-router-ops

Operate a self-hosted OpenAI-compatible LLM router/proxy (e.g. LiteLLM) in front of one or more backends — the minimal client-wiring block for every client type, the context-window advertisement gotcha, the env-vs-persisted-config gotcha, and why an unauthenticated health probe should 401, not 200. Use when wiring a…

dryvist/claude-code-plugins · 112 tokens

prompt-optimizer

Optimize prompts for Claude's latest models (Claude 5 family — Opus 5, Sonnet 5, Fable 5 — plus the still-active Opus 4.8, Sonnet 4.6, and Haiku 4.5) using Anthropic's official prompt-engineering guidance. Use when users want to improve, refine, debug, or create prompts or system prompts for Claude. Triggers include…

Aznatkoiny/zAI-Skills · 205 tokens

prompt-engineering

Expert prompt engineering guidance with proven techniques and anti-patterns. Invoke this skill whenever writing, editing, reviewing, or refining any prompt that will be interpreted by an AI model — system prompts, agent instructions, tool-use prompts, command templates, multi-step task prompts, or agentic workflows.…

berekvolgyipeter/dotclaude · 127 tokens