What is integrate-arcjet-guard-openai-agents?

A security integration for text agents built with the OpenAI Agents SDK. It checks authored tools with Arcjet and expects the application to screen incoming text before starting a run.

Use it with text-based Agent and Runner workflows to guard tools and add prompt-injection or other inbound checks before run() is called.

It helps restrict tool calls and keep security decisions connected to the caller's existing session or conversation identifier. It clarifies which OpenAI Agents features this integration supports.

integrate-arcjet-guard-openai-agents — Skill for Claude Code and Codex

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-openai-agents

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-openai-agents/github.svg)](https://agentmods.dev/skills/arcjet/arcjet-js/integrate-arcjet-guard-openai-agents)

Your own site

<a href="https://agentmods.dev/skills/arcjet/arcjet-js/integrate-arcjet-guard-openai-agents"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-openai-agents/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/arcjet/arcjet-js/integrate-arcjet-guard-openai-agents"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-openai-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,722 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.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.02722
Opus 5	$0.00042	$0.01361
Sonnet 5	$0.00017	$0.00544
Haiku 4.5	$0.00008	$0.00272

Measured yesterday against content hash eb35be04efcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

integrate-arcjet-guard-openai-agents 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 yesterday.

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-openai-agents/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate Arcjet Guard into an OpenAI Agents app

@arcjet/guard's OpenAI Agents v0 namespace wraps the agent's existing Arcjet client. It never talks to the Arcjet API itself. Two surfaces, one decision rule:

An authored tool (tool({ execute })) → guardTool(). After tool() the object is a FunctionTool; the runner calls invoke. DENY returns a structured ArcjetDenialResult. Do not throw.
Correlation → openaiAgentsContext() reads a field the integrator put on runContext.context (then documented copies: conversationId, groupId, already-resolved sessionId). It never mints a new id. It never calls session.getSessionId().

This namespace is text Agent + run() / Runner. Not Realtime, not Sandbox, not hosted tools, not computer / shell / apply_patch, not MCP, not agent.asTool().

Screen inbound before `run()` (SDK `inputGuardrails` are not Arcjet)

There is no first-class inbound channel, so there is no guardInbound. Put prompt-injection (and other inbound rules) in the application before run(). SDK inputGuardrails / outputGuardrails / defineToolInputGuardrail / defineToolOutputGuardrail are the SDK's own tripwires, not this policy gate. Do not wrap them as Guard.

`needsApproval` is not a policy gate

needsApproval / requireApproval / onApproval is human-in-the-loop. The run pauses; result.state.approve / reject. Same trap as Mastra requireApproval, Claude canUseTool, LangGraph interrupt(), and Google ADK requireConfirmation. There is no guardApproval. Do not wrap them as Guard.

`tool()` execute is the deny point; hosted, MCP, and handoffs are not

The runner executes authored function tools in toolExecution.ts via invoke. Hosted tools, handoffs, computer / shell / apply_patch, and MCP (mcpServers → mcpToFunctionTool) skip that authored-execute path. agent_tool_start / agent_tool_end are void observe-only hooks; they are not a deny. There is no guardHooks and no guardToolNode (there is no ToolNode).

Read the full file on GitHub · 246 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.

yesterday Changed · +7 lines eb35be04efcf
6d ago Changed · +7 lines a8eddc6ef6ee
11d ago First seen · 232 lines · 83 tokens per session scan A 1edc4a591f98

Subscribe to this mod's changes

integrate-arcjet-guard-openai-agents is a skill published in the GitHub repository arcjet/arcjet-js (682 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 2,722 once invoked, about $0.0004 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 2026-08-30.

Building agents Security agent-security ai-agents ai-security application-security bot-detection llm-security

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

linear-claude-skill

Manage Linear issues, projects, and teams.

Agent-Threat-Rule/agent-threat-rules · 15 tokens

playwright-skill

IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.

Agent-Threat-Rule/agent-threat-rules · 60 tokens

terraform-skill

Terraform infrastructure as code best practices.

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