DEPLOY_DESIGN

DEPLOY_DESIGN is a command for Claude Code from elizaOS/eliza. It costs 0 tokens per session (1,044 once invoked), scanned A, original, MIT.

A design for an ElizaOS command that sends an existing project to its linked Eliza Cloud app. It can optionally connect the deployed app to a custom domain and check when the deployment is ready.

In plain words
What is it for?
Use it to deploy a project with an app ID or project configuration, attach a valid custom domain, preview the deployment plan, or troubleshoot deployment settings.
Why use it?
It removes the need to manually start a cloud deployment and repeatedly check its public status. A dry run lets you see the planned sequence without making network requests.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

About the project

elizaOS is an open-source TypeScript framework and product stack for building and running autonomous AI agents. Developers use its runtime, application, command-line tool, cloud services, native bridges, and plugins to create agent-based software. The catalogue entries provide skills, commands, instructions, and rules for working with this monorepo and its agent ecosystem.

elizaOS/eliza · 19,253 stars · on GitHub · elizaresearch.ai

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 commands/elizaos/eliza/deploy_design
Clone the repo
git clone --depth 1 https://github.com/elizaOS/eliza

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 DEPLOY_DESIGN

README.md
[![agentmods](https://agentmods.dev/badge/commands/elizaos/eliza/deploy_design.svg)](https://agentmods.dev/commands/elizaos/eliza/deploy_design)
Your own site
<a href="https://agentmods.dev/commands/elizaos/eliza/deploy_design"><img src="https://agentmods.dev/badge/commands/elizaos/eliza/deploy_design.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,044 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 5.1 $0.00000 $0.01044
Opus 5 $0.00000 $0.00522
Sonnet 5 $0.00000 $0.00209
Haiku 4.5 $0.00000 $0.00104

Measured 6d ago against content hash 0b4531e2be1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

DEPLOY_DESIGN 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 6d 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.

packages/elizaos/src/commands/DEPLOY_DESIGN.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

elizaos deploy — Design Doc

Status: implemented trigger path. The CLI queues cloud deployments, can attach a custom domain, and polls public deployment status. Local build/upload, first-run credential prompting, deploy logs, and watch mode remain follow-up boundaries.

Goal

Ship a single command that takes a generated elizaOS project (template.json present in cwd) and deploys its linked Eliza Cloud app, optionally bound to a custom domain.

Command surface

elizaos deploy [--app-id <id>] [--domain <host>] [--dry-run] [--verbose]
  • --app-id <id> — Eliza Cloud app UUID. If omitted, resolved from .elizaos/template.json (values.appId / values.cloudAppId) or, failing that, by name match against GET /api/v1/apps.
  • --domain <host> — Custom external domain to attach after the deploy goes READY. Must match the same regex enforced by POST /api/v1/apps/[id]/domains: ^([a-z0-9]([a-z0-9-]*[a-z0-9])?\.)+[a-z]{2,}$. Subdomain rule is enforced server-side.
  • --dry-run — Print the planned sequence and exit 0. No network calls.
  • --verbose — Echo local deploy settings to stderr.

Auth flow

The CLI reads ELIZAOS_CLOUD_API_KEY, ELIZA_CLOUD_API_KEY, ELIZACLOUD_API_KEY, or ~/.elizaos/credentials.json. Requests are sent with Authorization: Bearer <key>. The API base defaults to https://api.eliza.app/api/v1; override with ELIZA_CLOUD_API_BASE_URL, ELIZAOS_CLOUD_API_BASE_URL, ELIZACLOUD_API_BASE_URL, or ELIZA_CLOUD_BASE_URL.

Deploy sequence

  1. auth check — load credentials and send Bearer auth with cloud requests.
  2. app lookup — resolve --app-id, .elizaos/template.json, or a single owned-app name match.
  3. trigger deployPOST /api/v1/apps/[id]/deploy with an empty body, letting the cloud service use the app's linked repository and stored env config.
  4. attach domain (only when --domain set) — POST /api/v1/apps/[id]/domains with { domain }. Server returns the verification TXT record + DNS instructions when needed; the CLI prints them.
  5. poll statusGET /api/v1/apps/[id]/deploy/status every 5s up to 10min. Terminal states: READY, ERROR.
  6. print URL — final line includes the returned vercelUrl when present and the custom domain when requested.

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 0 tokens per session scan A 0b4531e2be1a

Subscribe to this mod's changes

DEPLOY_DESIGN is a command published in the GitHub repository elizaOS/eliza (19,253 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,044 tokens. 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.