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.
npx skills add arcjet/arcjet-plugin --skill integrate-arcjet-guard-openai-agents-pygit clone --depth 1 https://github.com/arcjet/arcjet-pluginWrote 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.
[](https://agentmods.dev/skills/arcjet/arcjet-plugin/integrate-arcjet-guard-openai-agents-py)<a href="https://agentmods.dev/skills/arcjet/arcjet-plugin/integrate-arcjet-guard-openai-agents-py"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-plugin/integrate-arcjet-guard-openai-agents-py/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.
<a href="https://agentmods.dev/skills/arcjet/arcjet-plugin/integrate-arcjet-guard-openai-agents-py"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-plugin/integrate-arcjet-guard-openai-agents-py.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00100 | $0.02169 |
| Opus 5 | $0.00050 | $0.01085 |
| Sonnet 5 | $0.00020 | $0.00434 |
| Haiku 4.5 | $0.00010 | $0.00217 |
Grade A, and why
integrate-arcjet-guard-openai-agents-py 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 7d 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.
This is a copy
86% identical to integrate-arcjet-guard-openai-agents-py — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate Arcjet Guard into Python OpenAI Agents
arcjet.guard.openai_agents wraps the agent's existing Arcjet client. It
never talks to the Arcjet API itself. Shared Guard fundamentals (client,
rules, labels, decisions, capture, registration) live in
../arcjet/references/guards_python.md.
Load that reference for anything that is not OpenAI Agents-specific.
Official openai-agents>=0.19.0,<1 only — not the JS @openai/agents
adapter (@arcjet/guard/openai-agents/v0, docs
https://docs.arcjet.com/guards/openai-agents/), not community forks.
Importing arcjet.guard.openai_agents does not load LangChain.
Exports: guard_tool, openai_agents_context. Authored FunctionTool /
@function_tool only. Not hosted tools, MCP, Computer / Shell /
ApplyPatch, handoffs, or Agent.as_tool().
Two surfaces, one decision rule:
- An authored
FunctionTool→guard_tool. Gate isFunctionTool.tool_input_guardrails+reject_content(JSON ofArcjetDenialResult). Do not raise. - Correlation →
openai_agents_contextreads a caller-owned session / conversation id. It never mints. It never readstrace_id.
Docs: https://docs.arcjet.com/guards/openai-agents/.
The gate is tool_input_guardrails + reject_content
guard_tool returns a copy whose input guardrails start with Arcjet, so
on_invoke_tool never runs on DENY (or unevaluated Guard under the
default on_guard_error="deny"). Denial is
ToolGuardrailFunctionOutput.reject_content with JSON of
ArcjetDenialResult ({ arcjetDenied: true, … }). Do not raise —
raise_exception() is a tripwire halt, and a raise from
on_invoke_tool is swallowed by default_tool_error_function. Same
fail-closed default as #196:
only "allow" fails open; a DENY always blocks. Core guard() still
fails open (has_failed_open()).
needs_approval is not a policy gate
needs_approval is human-in-the-loop (state.approve / state.reject).
Same trap as JS OpenAI Agents needsApproval, LangGraph interrupt(),
and Genkit interrupt(). There is no inbound helper and no approval
helper. RunConfig.tool_execution.pre_approval_tool_input_guardrails=True
is an application opt-in only — this helper does not set it.
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.
- 7d ago Changed 14030da59dbf
- 8d ago First seen · 206 lines · 100 tokens per session scan A d76ef9bb51a5
integrate-arcjet-guard-openai-agents-py is a skill published in the GitHub repository arcjet/arcjet-plugin (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 100 tokens to every session and 2,169 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to integrate-arcjet-guard-openai-agents-py, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
chief-financial-officer
Owns the financial position: planning, budgeting, forecasting, unit economics, cash, and the numbers the business is run and reported on. Use this to build or challenge a budget, model a decision's financial consequence, assess unit economics or runway, evaluate an investment or spend request, set financial controls…
chief-revenue-officer
Owns the revenue engine end to end: sales, monetization, pricing, customer success, retention, and partnerships. Use this for pricing and packaging decisions, sales strategy and coverage, forecast and pipeline health, churn and expansion, partner and channel strategy, or when marketing-sourced demand is not…
seo-strategy
Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…
ceo-advisor
Pressure-tests a decision, plan, or idea before it is committed to — surfacing the assumption it rests on, the case against it, and what would have to be true for it to work. Use this when weighing options, when a plan needs challenging before commitment, when you have already decided and want a genuine gut check…
customer-success-management
Runs the ongoing relationship with accounts after the sale — segmenting coverage against account value, building a health score that predicts rather than describes, running reviews customers find worth attending, forecasting renewals honestly, and finding expansion that follows usage instead of quota. Use this to…
quantitative-analysis
Answers a business question with data without fooling yourself — framing the question so an answer would change something, choosing the right comparison, checking the data before trusting it, recognizing the traps that produce confident wrong answers (aggregation reversals, survivorship, regression to the mean…