deploy

deploy is a command for Claude Code from AlexK020908/infra-designer. It costs 17 tokens per session (640 once invoked), scanned A, original, MIT.

A deployment command that turns an infrastructure specification into Terraform files or AWS CLI scripts, then applies them to create cloud resources. Terraform is a tool that describes infrastructure as code.

In plain words
What is it for?
Rendering and deploying the infrastructure described in an `infra/<project-name>/spec.json` file, with Terraform by default or AWS CLI scripts when preferred.
Why use it?
It provides a repeatable path from a saved infrastructure design to a deployed environment and supports fixing errors reported during deployment.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the infra-designer plugin — 19 skills, 5 commands shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AlexK020908/infra-designer
Claude Code
/plugin install infra-designer

Made for: Claude Code.

Or install infra-designer, the plugin that ships this one along with the rest of its 19 skills, 5 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexk020908/infra-designer/deploy.svg)](https://agentmods.dev/commands/alexk020908/infra-designer/deploy)
Your own site
<a href="https://agentmods.dev/commands/alexk020908/infra-designer/deploy"><img src="https://agentmods.dev/badge/commands/alexk020908/infra-designer/deploy.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 640 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 $0.00017 $0.00640
Opus 5 $0.00009 $0.00320
Sonnet 5 $0.00003 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured 5d ago against content hash d45b976dbe0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deploy 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 5d 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.

infra-plugin/commands/deploy.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy infrastructure

Compile the spec to Terraform and apply it. Keep the fail → read-error → fix loop in the terminal — that's where you're strongest.

Spec path: $ARGUMENTS. If omitted, look under infra/ in the current working directory for a <project-name>/spec.json; if there are several projects, ask the user which one. All paths are relative to the user's cwd, never ${CLAUDE_PLUGIN_ROOT}. Below, <dir> is the folder the spec lives in (e.g. infra/todo-app) — write all generated output back into that same folder.

1. Compile the spec

Pick a backend. Default is Terraform; offer awscli if the user prefers not to use IaC.

# Terraform (default — full feature set, all wiring)
python ${CLAUDE_PLUGIN_ROOT}/engine/cli.py render <dir>/spec.json <dir>/terraform

# or AWS CLI (idempotent shell scripts, no IaC)
python ${CLAUDE_PLUGIN_ROOT}/engine/cli.py render <dir>/spec.json <dir>/deploy --backend=awscli

Terraform writes providers.tf + main.tf (+ network.tf); awscli writes deploy.sh + destroy.sh. Both write <dir>/spec.lock.json pinning component versions — commit the lock so the handoff is reproducible. Read the output and confirm it matches the spec before applying.

2. Preview

  • Terraform: cd <dir>/terraform && terraform init && terraform plan -out tfplan. If terraform isn't installed, tell the user how to install it and stop.
  • AWS CLI: read <dir>/deploy/deploy.sh aloud — it's the exact set of commands that will run. Requires the aws CLI configured with credentials.

Show the user what will be created and get explicit confirmation before applying — this creates real, billable cloud resources.

3. Apply and iterate

  • Terraform: terraform apply tfplan
  • AWS CLI: bash <dir>/deploy/deploy.sh (idempotent — safe to re-run; destroy.sh tears down)

If apply fails:

  • Read the actual Terraform error.
  • The fix usually belongs in <dir>/spec.json (a config value, a missing edge), not in the generated Terraform — regenerate with step 1 after editing the spec, so the spec stays the source of truth. Only hand-edit main.tf for a genuine engine gap, and report that gap.
  • Re-plan and re-apply.

Read the full file on GitHub · 63 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. 5d ago First seen · 63 lines · 17 tokens per session scan A d45b976dbe0d

Subscribe to this mod's changes

deploy is a command published in the GitHub repository AlexK020908/infra-designer (2 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 640 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 2026-08-31.