claude-scaffold: Agent for Claude Code

.claude/agents/infra-provisioner.md

infra-provisioner is an agent for Claude Code from pyramidheadshark/claude-scaffold. It costs 20 tokens per session (701 once invoked), scanned A, original, MIT.

An infrastructure provisioning agent that creates Terraform, Packer, and Docker Compose configuration from a project’s design document. Terraform describes cloud resources, Packer builds machine images, and Docker Compose defines multi-container services.

In plain words
What is it for?
Use it after the deployment plan is filled in to create configurations for virtual machines, networking, Docker services, Kubernetes, or GPU workloads, as specified by the project’s load and deployment needs.
Why use it?
It turns a documented deployment plan into configuration files for running the project’s infrastructure.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

This is pyramidheadshark/claude-scaffold's own configuration. It tells Claude Code how to work on claude-scaffold itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-scaffold configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pyramidheadshark/claude-scaffold. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pyramidheadshark/claude-scaffold/main/.claude/agents/infra-provisioner.md
Clone the repo
git clone --depth 1 https://github.com/pyramidheadshark/claude-scaffold

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 infra-provisioner

README.md
[![agentmods](https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/infra-provisioner/github.svg)](https://agentmods.dev/agents/pyramidheadshark/claude-scaffold/infra-provisioner)
Your own site
<a href="https://agentmods.dev/agents/pyramidheadshark/claude-scaffold/infra-provisioner"><img src="https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/infra-provisioner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for infra-provisioner

Your own site · 80×15
<a href="https://agentmods.dev/agents/pyramidheadshark/claude-scaffold/infra-provisioner"><img src="https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/infra-provisioner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 701 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 $0.00020 $0.00701
Opus 5 $0.00010 $0.00351
Sonnet 5 $0.00004 $0.00140
Haiku 4.5 $0.00002 $0.00070

Measured 10d ago against content hash bb27e5f75428, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

infra-provisioner 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 10d 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.

.claude/agents/infra-provisioner.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: infra-provisioner

Purpose

Provisions project infrastructure based on the design document. Writes Terraform, Packer, and Docker Compose configurations tailored to the project's requirements.

When to Use

After design-doc.md section 8 (Deployment Plan) is filled in. Before Phase 3 (Development Loop) begins.

Decision Logic

The agent reads the design document and selects the appropriate infrastructure tier:

Condition Infrastructure
Simple service, < 500 concurrent users Docker Compose on single YC VM
Moderate load, stateless service Docker Compose + nginx on YC VM
High load or K8s explicitly required Helm chart + YC Managed Kubernetes
ML training workload GPU VM via Terraform

Workflow

See "What Gets Created" and "Makefile Standard" sections below for detailed output.

What Gets Created

Tier 1: Docker Compose on YC VM

infra/
├── packer/
│   ├── ubuntu-base.pkr.hcl
│   └── variables.pkr.hcl
├── terraform/
│   ├── main.tf            # VM + networking
│   ├── variables.tf
│   ├── outputs.tf
│   ├── versions.tf
│   └── cloud-init.yaml
└── Makefile               # convenience commands

Tier 2: K8s-Ready

Same as Tier 1, plus:

infra/
└── helm/
    └── {project-name}/
        ├── Chart.yaml
        ├── values.yaml
        ├── values.staging.yaml
        ├── values.production.yaml
        └── templates/
            ├── deployment.yaml
            ├── service.yaml
            ├── ingress.yaml
            └── configmap.yaml

Makefile Standard

.PHONY: build plan apply destroy ssh

IMAGE_ID ?= $(shell cat infra/.last_image_id 2>/dev/null)
ENV ?= staging

build:
	cd infra/packer && packer build ubuntu-base.pkr.hcl

plan:
	cd infra/terraform && terraform plan -var-file=$(ENV).tfvars

apply:
	cd infra/terraform && terraform apply -var-file=$(ENV).tfvars

destroy:
	cd infra/terraform && terraform destroy -var-file=$(ENV).tfvars

ssh:
	ssh ubuntu@$(shell cd infra/terraform && terraform output -raw vm_ip)

Read the full file on GitHub · 100 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. 10d ago First seen · 100 lines · 20 tokens per session scan A bb27e5f75428

Subscribe to this mod's changes

infra-provisioner is an agent published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 701 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.