integrate-arcjet-guard-google-adk

integrate-arcjet-guard-google-adk is a skill for Claude Code, Codex from arcjet/arcjet-js. It costs 111 tokens per session (3,275 once invoked), scanned A, original, Apache-2.0.

A security integration for Google ADK JavaScript applications using Arcjet to decide whether tool calls may run. Google ADK is a framework for building AI agents, and this integration places the check in the agent runner.

In plain words
What is it for?
Use it when adding Arcjet checks to Google ADK agents, limiting or screening their tools, or protecting inbound agent requests with a caller-provided session identifier.
Why use it?
It gives the application a gate that can deny a tool call before the tool executes, while passing the denial result back to the agent instead of relying on errors or unhandled exceptions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when adding Arcjet checks to Google ADK agents, limiting or screening their tools, or protecting inbound agent requests with a caller-provided session identifier.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arcjet/arcjet-js/integrate-arcjet-guard-google-adk
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 arcjet/arcjet-js --skill integrate-arcjet-guard-google-adk
Clone the repo
git clone --depth 1 https://github.com/arcjet/arcjet-js

Made for: Claude Code, Codex.

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 integrate-arcjet-guard-google-adk

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-google-adk/github.svg)](https://agentmods.dev/skills/arcjet/arcjet-js/integrate-arcjet-guard-google-adk)
Your own site
<a href="https://agentmods.dev/skills/arcjet/arcjet-js/integrate-arcjet-guard-google-adk"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-google-adk/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 integrate-arcjet-guard-google-adk

Your own site · 80×15
<a href="https://agentmods.dev/skills/arcjet/arcjet-js/integrate-arcjet-guard-google-adk"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-google-adk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,275 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00111 $0.03275
Opus 5.5 $0.00044 $0.01310
Sonnet 5.5 $0.00022 $0.00655
Haiku 4.5 $0.00011 $0.00328

Measured 13d ago against content hash 1ceefc34e58e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

integrate-arcjet-guard-google-adk 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 13d 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.

arcjet-guard/skills/integrate-arcjet-guard-google-adk/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate Arcjet Guard into Google ADK JS

@arcjet/guard's Google ADK v2 namespace wraps the agent's existing Arcjet client. It never talks to the Arcjet API itself. Two surfaces, one decision rule:

  • Tool calls → guardPlugin(). A Runner BasePlugin whose beforeToolCallback is the run-wide gate. DENY is a dictionary (ArcjetDenialResult) so ADK skips runAsync and the model sees the payload. undefined lets the tool execute. Do not throw from the callback — PluginManager treats a throw as a plugin error, not skip. Tools already branded by a sibling guardTool are skipped so Guard is not double-called. Inbound guard() before Runner.runAsync does not brand tools and does not skip this gate. The plugin does not screen inbound (onUserMessageCallback / beforeModelCallback are no-ops) so a preceding guard() does not double-call.
  • Correlation → googleAdkContext() reads a caller-owned id from helper options (guardPlugin({ sessionId })) or a wrap (googleAdkContext({ context: appContext })). ADK Context has no nested context field. Durable session state loses to helper options. It never mints a new id. It never reads invocationId (ADK always generates it). It never reads traceId. It never reads toolContext.sessionId / session.id (session auto-ids).

There is no guardTool. Skip is the plugin return, not throw-from-execute. There is no guardInbound, no guardApproval, and this namespace does not use ADK SecurityPlugin as the Arcjet policy gate.

This namespace is Google ADK JS Runner + BasePlugin.beforeToolCallback. Not @google/genai. Not the Python SDK. Do not also wrap with @arcjet/guard/vercel-ai/v7 or @arcjet/guard/claude-managed-agents/v0.

Docs live at docs.arcjet.com/guards/google-adk/. Do not overwrite any other /guards/... slug.

Put Arcjet first in new Runner({ plugins }). PluginManager is first-win; if another plugin (including SecurityPlugin) returns a value first, Guard never runs.

Read the full file on GitHub · 294 lines

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. 13d ago Changed · +1 lines 1ceefc34e58e
  2. 21d ago Changed · +2 lines cad3d670ef72
  3. 22d ago Changed · +5 lines c4d20c33bd3a
  4. 26d ago Changed 85030be348cf
  5. 1mo ago Changed · +1 lines f7dc7930044b
  6. 1mo ago Changed b2ed666ce21e
  7. 1mo ago Changed · +7 lines 6675c0b0ac66
  8. 1mo ago First seen · 278 lines · 111 tokens per session scan A bde526504e9c

Subscribe to this mod's changes

integrate-arcjet-guard-google-adk is a skill published in the GitHub repository arcjet/arcjet-js (694 stars, last pushed 4d ago), licensed Apache-2.0. It adds 111 tokens to every session and 3,275 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-05.

Related

Other skills, from other repositories

clinical-trial-protocol-skill

Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…

Agent-Threat-Rule/agent-threat-rules · 70 tokens

claude-d3js-skill

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.

Agent-Threat-Rule/agent-threat-rules · 25 tokens

adr-skill

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…

Agent-Threat-Rule/agent-threat-rules · 89 tokens

terraform-skill

Terraform infrastructure as code best practices.

Agent-Threat-Rule/agent-threat-rules · 10 tokens

create-auth-skill

Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.

Agent-Threat-Rule/agent-threat-rules · 66 tokens

prior-auth-review-skill

Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization…

Agent-Threat-Rule/agent-threat-rules · 63 tokens