---
title: "Cloudflare Agents SDK: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/cloudflare-agents-sdk/
description: "Guides stateful Cloudflare agent applications through current SDK documentation, persistence, scheduling and approval-aware tool flows."
---

# Cloudflare Agents SDK: review, setup & limitations · Undominated.ai

> Guides stateful Cloudflare agent applications through current SDK documentation, persistence, scheduling and approval-aware tool flows.

[← Explore all skills](/skills/)

AGENT DEVELOPMENT / Cloudflare

# Cloudflare Agents SDK

Guides stateful Cloudflare agent applications through current SDK documentation, persistence, scheduling and approval-aware tool flows.

 See setup guidance ↓Original source ↗

SOURCE REVIEW

 Reviewed 2026-09-21
 Evidence 7 linked sources
 Publisher Cloudflare
 Licence Apache-2.0 ↗
 Revision b052c32bab7d
 Read what was—and wasn’t—checked ↓

“Build, debug, or review Cloudflare Agents SDK applications using the agents package.”

 Cloudflare · upstream description ↗ Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Treats installed SDK versions and current docs as the basis for implementation.
- Explains the difference between synchronized state, database history, chat-tool approvals and durable-workflow pauses.

### A good fit for

 - Building a persistent agent on Cloudflare Workers
- Adding scheduled work or an approval step to an agent application

### Weigh up before choosing

 - This is specific to Cloudflare’s Agents SDK and runtime, not a general multi-provider agent framework.
- Experimental browser, voice and higher-level APIs need current documentation and may change.
- Installing the skill does not configure authentication, deploy resources or verify an agent application.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/agents-sdk/SKILL.md
- skills/agents-sdk/references/human-in-the-loop.md
- skills/agents-sdk/references/state-scheduling.md
- LICENSE

### Our findings

 - The definition checks SDK installation, bindings and migrations and warns against editing old migration tags.
- The state reference separates validation of proposed updates from reactions to accepted changes.
- The human-in-the-loop reference distinguishes approval responses from client tool outputs and calls for timeout handling before gated work.

### Not established by this review

 - Source inspection only; no skill installation or workflow execution was performed.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

Upstream setup instructions ↗

DOCUMENTED COMMAND

 npx skills add https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/agents-sdk Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - Install the complete skill directory with its references and helpers; a copied SKILL.md alone may be incomplete.
- Choose the intended agent and project scope in the installer, then review its permissions before using the skill.

### Before you start

 - Node.js/npm for this installer
- An agent that supports the Agent Skills format
- A configured Workers project
- Cloudflare account access for deployment and provider credentials where used

### Compatibility

Cloudflare Workers and agents package · Compatible JavaScript/TypeScript coding agents

### Read and edit agent code, bindings and migrations

 - Read and edit agent code, bindings and migrations
- Optional deployment to persistent cloud resources
- Configured agents may store data, invoke tools or contact external model services

### Cost model

The skill is Apache-licensed; Workers resources, storage and any model/provider services are billed independently.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - Skill definition at reviewed revision ↗ Checked 2026-09-21 https://github.com/cloudflare/skills/blob/b052c32bab7dd493513260228a36c88294f343f1/skills/agents-sdk/SKILL.md Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, compatibility, access
- Reviewed reference or helper: references/human-in-the-loop.md ↗ Checked 2026-09-21 https://github.com/cloudflare/skills/blob/b052c32bab7dd493513260228a36c88294f343f1/skills/agents-sdk/references/human-in-the-loop.md Supports: review, limitations, access
- Reviewed reference or helper: references/state-scheduling.md ↗ Checked 2026-09-21 https://github.com/cloudflare/skills/blob/b052c32bab7dd493513260228a36c88294f343f1/skills/agents-sdk/references/state-scheduling.md Supports: review, limitations, access
- Upstream license or licensing declaration ↗ Checked 2026-09-21 https://github.com/cloudflare/skills/blob/b052c32bab7dd493513260228a36c88294f343f1/LICENSE Supports: license
- Publisher installation and project documentation ↗ Checked 2026-09-21 https://github.com/cloudflare/skills/blob/b052c32bab7dd493513260228a36c88294f343f1/README.md Supports: install, compatibility, access
- Skills installer source formats and selective installation ↗ Checked 2026-09-21 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md Supports: install
- Installer implementation: full commit SHA fallback ↗ Checked 2026-09-21 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/git.ts Supports: install

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Anthropic Skill Creator ↗ Develops skills through example tasks, baseline comparisons, human review and separate trigger-description evaluation.](/skills/anthropics-skill-creator/)[### OpenAI Evaluate Skill ↗ Connects a local skill review to structural checks, budget explanations and an explicitly separate live benchmark workflow.](/skills/openai-evaluate-skill/)[### Cloudflare Durable Objects ↗ Designs per-entity state and coordination with explicit persistence, concurrency and runtime-test guidance.](/skills/cloudflare-durable-objects/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)
