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-js --skill integrate-arcjet-guard-claude-agent-sdkgit clone --depth 1 https://github.com/arcjet/arcjet-jsWrote 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-js/integrate-arcjet-guard-claude-agent-sdk)<a href="https://agentmods.dev/skills/arcjet/arcjet-js/integrate-arcjet-guard-claude-agent-sdk"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-claude-agent-sdk/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-js/integrate-arcjet-guard-claude-agent-sdk"><img src="https://agentmods.dev/badge/skills/arcjet/arcjet-js/integrate-arcjet-guard-claude-agent-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.03332 |
| Opus 5 | $0.00046 | $0.01666 |
| Sonnet 5 | $0.00018 | $0.00666 |
| Haiku 4.5 | $0.00009 | $0.00333 |
Grade A, and why
integrate-arcjet-guard-claude-agent-sdk 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.
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate Arcjet Guard into a Claude Agent SDK agent
@arcjet/guard's Claude Agent SDK v0 namespace wraps the agent's existing
Arcjet client. It never talks to the Arcjet API itself. Three surfaces, one
decision rule:
- An authored tool (
tool()+createSdkMcpServer()) →guardTool(). DENY is aCallToolResultwithisError: true. Do not throw. - Inbound text →
guardHooks()UserPromptSubmit. DENY is{ decision: "block" }. Timeout already fail-closes the prompt (Claude Code v2.1.208+). - Built-ins / unwrapped MCP →
guardHooks()PreToolUsewithpermissionDecision: "deny". Timeout already fail-closes (the tool does not run).PostToolUseis capture only. - Correlation →
claudeAgentContext()readssession_idfrom hook input oroptions.sessionId. Subagents haveagent_id(metadata only). It never mints a new id.options.sessionIdmust be a UUID and can only be created once — see Step 5.
Screen inbound with UserPromptSubmit
This is the only place a turn can be declined before the model sees the
prompt. There is no guardInbound. Put detectPromptInjection on
guardHooks({ inbound }). A DENY returns { decision: "block", reason }
and Claude Code erases the prompt.
canUseTool is not a policy gate
Claude's docs say canUseTool is skipped by allowedTools, allow rules,
and bypassPermissions / acceptEdits. There is no guardCanUseTool.
Do not put Arcjet policy on canUseTool. Same trap as Google ADK
requireConfirmation: after a human yes, Guard still runs.
PreToolUse is the only deny for unwrapped tools
Built-ins (Bash, Write, …) and MCP tools you did not pass through
guardTool are gated here. Annotations (readOnlyHint, …) and sandbox
settings are not enforcement. PostToolUse cannot undo a tool that already
ran.
Questions to ask the human first
Ask only what you cannot infer from the code; suggest defaults.
- Which tools are risky (external side effects, irreversible, spends
money, sends messages)? Those get
guardTool. Built-ins and unwrapped MCP getguardHooksPreToolUse. - What limits? (e.g. "10 lookups/min per order" →
tokenBucket.) - Who is the user for metadata — an opaque user/tenant ID (never PII)?
Default: none. Pass it via
metadataon the policy. Session id is the correlation id, not the user. - Is an Arcjet outage unacceptable? Every helper defaults to
onGuardError: "deny". Ask explicitly about inboundUserPromptSubmit: failing closed there means the agent stops answering for the duration of the outage, so"allow"is a routine and legitimate choice at that one call site.
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 9e251b154de9
- 6d ago Changed · +7 lines 3a8ad5251a5d
- 11d ago First seen · 302 lines · 92 tokens per session scan A 65b2b74f18c5
integrate-arcjet-guard-claude-agent-sdk is a skill published in the GitHub repository arcjet/arcjet-js (682 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 3,332 once invoked, about $0.0005 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.
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…
claude-d3js-skill
This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.
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…
linear-claude-skill
Manage Linear issues, projects, and teams.
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.
terraform-skill
Terraform infrastructure as code best practices.