integrate-arcjet-guard-claude-agent-sdk-py

integrate-arcjet-guard-claude-agent-sdk-py is a skill for Claude Code from arcjet/arcjet-plugin. It costs 106 tokens per session (2,699 once invoked), scanned A, a copy of integrate-arcjet-guard-claude-agent-sdk-py, Apache-2.0.

A Python integration that adds Arcjet Guard checks to Anthropic's Claude Agent SDK. It screens incoming prompts and controls authored tools, built-in tools, and MCP tools.

In plain words
What is it for?
Use it to guard tools written with the SDK, check user prompts, and apply pre-use checks to built-in or MCP tools.
Why use it?
It helps prevent unsafe prompts, prompt injection, and unwanted tool calls in Claude agents. The Claude Agent SDK is Anthropic's software kit for building agents in Python.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event.

Part of the arcjet plugin — 11 skills, 1 agent shipped together

Good fit Use it to guard tools written with the SDK, check user prompts, and apply pre-use checks to built-in or MCP tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arcjet/arcjet-plugin/integrate-arcjet-guard-claude-agent-sdk-py
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-plugin --skill integrate-arcjet-guard-claude-agent-sdk-py
Clone the repo
git clone --depth 1 https://github.com/arcjet/arcjet-plugin

Made for: Claude Code.

Or install arcjet, the plugin that ships this one along with the rest of its 11 skills, 1 agent.

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-claude-agent-sdk-py

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

agentmods 80×15 button for integrate-arcjet-guard-claude-agent-sdk-py

Your own site · 80×15
<a href="https://agentmods.dev/skills/arcjet/arcjet-plugin/integrate-arcjet-guard-claude-agent-sdk-py"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-plugin/integrate-arcjet-guard-claude-agent-sdk-py.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,699 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 92% copy Near-identical to another mod 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 $0.00106 $0.02699
Opus 5 $0.00053 $0.01350
Sonnet 5 $0.00021 $0.00540
Haiku 4.5 $0.00011 $0.00270

Measured 5d ago against content hash 224fa7cced85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

integrate-arcjet-guard-claude-agent-sdk-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 5d 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.

Origin

This is a copy

92% identical to integrate-arcjet-guard-claude-agent-sdk-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.

plugins/arcjet/skills/integrate-arcjet-guard-claude-agent-sdk-py/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate Arcjet Guard into the Python Claude Agent SDK

arcjet.guard.claude_agent_sdk 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 Claude Agent SDK-specific.

Official claude-agent-sdk>=0.2.127,<1 only — not the JS @anthropic-ai/claude-agent-sdk adapter (@arcjet/guard/claude-agent-sdk/v0, docs https://docs.arcjet.com/guards/claude-agent-sdk/), not Vercel AI, not community forks, and not Claude Managed Agents hosted client.beta.sessions (arcjet.guard.claude_managed_agents). Importing arcjet.guard.claude_agent_sdk does not load LangChain, CrewAI, or the JS adapter. The extra is safe (no chromadb).

Exports: guard_tool, guard_hooks, claude_agent_context. Authored @tool + create_sdk_mcp_server for tools you own; guard_hooks for inbound UserPromptSubmit and unwrapped built-ins / MCP PreToolUse. There is no inbound helper and no guard_can_use_tool.

Three surfaces, one decision rule:

  • An authored @toolguard_tool. Denial is JSON-in-content + is_error: True. Python does not forward structuredContent (that is the JS adapter). Do not raise.
  • Inbound textguard_hooks UserPromptSubmit (decision: "block"). That is the only place a turn can be declined before the model reads the prompt.
  • Built-ins / unwrapped MCPguard_hooks PreToolUse (permissionDecision: "deny"). PostToolUse is capture only.
  • Correlationclaude_agent_context reads a caller-owned UUID session_id. It never mints.

Docs: https://docs.arcjet.com/guards/claude-agent-sdk/.

Unwrapped tools deny on PreToolUse via guard_hooks

Built-ins (Bash, Write, …) and MCP tools you did not pass through guard_tool have no authored handler. PreToolUse is the only deny for those. PostToolUse cannot undo a tool that already ran. List every guard_tool wrapper in exclude or each authored tool is guarded twice (two round trips, two quota units). Entries match the reported name: pass {"server": "support", "name": "lookup_order"} for an authored MCP tool (it resolves to mcp__support__lookup_order) and a bare string for a built-in such as "Bash". A bare authored name deliberately does not match every server's tool of that name.

Read the full file on GitHub · 236 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. 5d ago Changed · +7 lines 224fa7cced85
  2. 6d ago First seen · 229 lines · 106 tokens per session scan A ace4d0e680b8

Subscribe to this mod's changes

integrate-arcjet-guard-claude-agent-sdk-py is a skill published in the GitHub repository arcjet/arcjet-plugin (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 106 tokens to every session and 2,699 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to integrate-arcjet-guard-claude-agent-sdk-py, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

chief-strategy-officer

Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…

cbrock84/headcount · 93 tokens

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…

cbrock84/headcount · 74 tokens

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…

cbrock84/headcount · 85 tokens

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…

cbrock84/headcount · 88 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens

telephony-and-conferencing

Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…

cbrock84/headcount · 85 tokens