build-agent

build-agent is a command for Claude Code from fanfan-de/anybox. It costs 11 tokens per session (316 once invoked), scanned A, original, MIT.

A command for creating an AI agent on Cloudflare with the Agents SDK. It supports persistent state, real-time WebSocket communication, scheduled tasks, tool calls, multiple cooperating agents, and RAG, which retrieves relevant information for an AI response.

In plain words
What is it for?
Use it to scaffold customer-support chatbots, real-time coding assistants, multi-agent systems, and AI applications that need memory, scheduled work, or retrieved information.
Why use it?
It turns a broad request for a Cloudflare AI agent into a project with the relevant application patterns. This avoids starting the setup and architecture from scratch.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to scaffold customer-support chatbots, real-time coding assistants, multi-agent systems, and AI applications that need memory, scheduled work, or retrieved information.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/fanfan-de/anybox/build-agent
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.

Clone the repo
git clone --depth 1 https://github.com/fanfan-de/anybox

Made for: Claude Code.

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 build-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/fanfan-de/anybox/build-agent.svg)](https://agentmods.dev/commands/fanfan-de/anybox/build-agent)
Your own site
<a href="https://agentmods.dev/commands/fanfan-de/anybox/build-agent"><img src="https://agentmods.dev/badge/commands/fanfan-de/anybox/build-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 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 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 5.1 $0.00011 $0.00316
Opus 5 $0.00005 $0.00158
Sonnet 5 $0.00002 $0.00063
Haiku 4.5 $0.00001 $0.00032

Measured 3d ago against content hash 20ba931d2186, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

build-agent 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 3d 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

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/Anybox-Plugins/cloudflare/commands/build-agent.md · 41 lines

What it actually says

Build AI Agent on Cloudflare

This command helps you build AI agents using the Cloudflare Agents SDK with state management, real-time WebSockets, scheduled tasks, and tool integration.

Arguments

The user invoked this command with: $ARGUMENTS

Instructions

When this command is invoked:

  1. Read the skill file at skills/building-ai-agent-on-cloudflare/SKILL.md for core guidance
  2. Reference skills/building-ai-agent-on-cloudflare/references/examples.md for templates
  3. Use skills/building-ai-agent-on-cloudflare/references/agent-patterns.md for tool calling and patterns
  4. Use skills/building-ai-agent-on-cloudflare/references/state-patterns.md for state management
  5. Consult skills/building-ai-agent-on-cloudflare/references/troubleshooting.md for common issues

Capabilities

  • Stateful AI agents with persistent memory
  • Real-time WebSocket communication
  • Scheduled tasks and cron jobs
  • Tool integration and function calling
  • Multi-agent orchestration
  • RAG (Retrieval Augmented Generation) patterns

Example Usage

/cloudflare:build-agent a customer support chatbot
/cloudflare:build-agent real-time coding assistant with WebSocket
/cloudflare:build-agent multi-agent workflow orchestrator
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. 3d ago First seen · 41 lines · 11 tokens per session scan A 20ba931d2186

Subscribe to this mod's changes

build-agent is a command published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 24d ago), licensed MIT. It adds 11 tokens to every session and 316 once invoked, about $0.0001 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 2026-09-03.