integrate-agentkit

An integration guide for adding Worldcoin AgentKit to an x402 server or payment facilitator. It covers access modes, supported EVM payment networks, request verification, and agent registration choices.

In plain words
What is it for?
Use it to add free, trial, or discounted access, verify requests, connect supported blockchain payments, and complete an AgentKit server integration.
Why use it?
It helps an agent choose the required payment and verification setup before wiring protected server routes.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/worldcoin/agentkit/integrate-agentkit
Any agent
npx skills add worldcoin/agentkit --skill integrate-agentkit
Clone the repo
git clone --depth 1 https://github.com/worldcoin/agentkit

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.01201
Opus 5 $0.00030 $0.00600
Sonnet 5 $0.00012 $0.00240
Haiku 4.5 $0.00006 $0.00120

Measured 2d ago against content hash dfcd38888a12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integrate-agentkit 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 2d 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.

skills/integrate-agentkit/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate AgentKit

Use this skill for end-to-end server-side integration work with @worldcoin/agentkit.

Start by clarifying the integration

If the developer has not already answered these, ask before choosing an implementation:

  1. Which access mode do they want: free, free-trial, or discount?
  2. Which payment network should the protected route use?
  3. Do they control the facilitator path, or are they using a hosted facilitator?
  4. Do they also need agent registration, or only request-time verification?

Default recommendation

For most production integrations:

  • Put paid routes on whichever network the developer's facilitator already supports (commonly World Chain eip155:480 or Base eip155:8453).
  • Leave AgentBook lookup alone — createAgentBookVerifier() always resolves against the canonical World Chain deployment. The developer does not need to think about which chain the registry lives on.
  • Start with free-trial unless the developer explicitly wants free or discount.
  • Only choose discount when you can wire hooks.verifyFailureHook into the facilitator flow you control.

Key pieces

  • x402 resource server: the protected HTTP route and 402 challenge flow
  • facilitator: verifies and settles payment payloads; required for discount
  • AgentKit extension: adds the CAIP-122 challenge and verifies the signed agentkit header
  • AgentBook: on-chain registry on World Chain that maps the agent wallet to an anonymous human ID. Lookup is always against World Chain regardless of the payment chain — the caller side is chain-agnostic.
  • storage: per-human usage tracking for free-trial and discount
  • registration path: separate from request-time verification; use npx @worldcoin/agentkit-cli --llms if the developer also needs registration help

Workflow

  1. Read ../../x402/DOCS.md first. It should be the primary integration playbook.
  2. Confirm exported APIs in ../../core/src/index.ts and ../../x402/src/index.ts before adding imports.
  3. Prefer the hooks-based path:
    • declareAgentkitExtension
    • agentkitResourceServerExtension
    • createAgentkitHooks
    • createAgentBookVerifier
  4. If the payment network is World Chain (eip155:480), add a custom ExactEvmScheme().registerMoneyParser(...) for World Chain USDC. Do not assume the server scheme has a working default stablecoin for World Chain.
  5. Call createAgentBookVerifier() with no arguments in the common case. Pass rpcUrl or contractAddress only for custom World Chain endpoints or non-canonical deployments.
  6. If the mode is free-trial or discount, add persistent AgentKitStorage. InMemoryAgentKitStorage is only for demos.
  7. If the mode is discount, wire hooks.verifyFailureHook into the facilitator. Without it, discounted underpayments will fail verification.
  8. Verify the whole path end-to-end:
    • 402 response includes the agentkit extension
    • registered agent gets the intended behavior
    • unregistered agent falls back to normal payment
    • replay protection and storage behavior work as expected

Read the full file on GitHub · 79 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. 2d ago First seen · 79 lines · 0 tokens per session scan A dfcd38888a12

Subscribe to this mod's changes

integrate-agentkit is a skill published in the GitHub repository worldcoin/agentkit (23 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session and 1,201 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

migrate

Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic…

launchdarkly/ai-tooling · 96 tokens

launchdarkly-flag-qualitative-feedback-setup

Integrate LaunchDarkly qualitative user feedback into a JavaScript/TypeScript codebase. Guides framework and design system detection, builds the sendFeedback utility and feedback widget matching existing project patterns. Use when the user wants to add a Give Feedback widget, collect user sentiment tied to feature…

launchdarkly/ai-tooling · 86 tokens

onboarding

Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag. Use when adding LaunchDarkly, setting up or integrating feature flags in a project, SDK integration, or 'onboard me'.

launchdarkly/ai-tooling · 67 tokens

should-flag-change

Decide whether a given code change should be placed behind a LaunchDarkly feature flag. Use when a developer asks whether a change should be behind a flag, when reviewing a diff or pull request, or when running in CI on a PR. Reads the diff and surrounding code, then emits a structured advisory recommendation.…

launchdarkly/ai-tooling · 78 tokens

launchdarkly-metric-create

Create a LaunchDarkly metric that measures what matters for an experiment or rollout. Use when the user wants to create a metric, track an event, measure page views, button clicks, conversion, latency, error rate, or any custom numeric or binary outcome. Instruments the event first when needed (including SDK setup and…

launchdarkly/ai-tooling · 80 tokens

first-flag

Create a boolean first flag, add evaluation, toggle on/off for end-to-end proof. Parent onboarding Step 6; uses MCP, API, or ldcli; optional flag-create skill.

launchdarkly/ai-tooling · 42 tokens