packer-expert

packer-expert is an agent for coding agents from poindexter12/waypoint. It costs 16 tokens per session (1,052 once invoked), scanned A, original, MIT.

An expert assistant for HashiCorp Packer, a tool that builds reusable machine images and virtual-machine templates. It helps with configuration, design choices, troubleshooting, and build strategy.

In plain words
What is it for?
Use it to create or debug Packer templates, build Proxmox, VMware, or cloud images, configure setup steps, or improve image-build pipelines.
Why use it?
It helps avoid mistakes when creating repeatable base images for computers, virtual machines, or cloud servers. It also points you to the relevant Packer guidance for the task.

Agent

Part of the technologies plugin — 7 skills, 6 agents shipped together

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 agents/poindexter12/waypoint/packer
Clone the repo
git clone --depth 1 https://github.com/poindexter12/waypoint

Or install technologies, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

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 packer-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/poindexter12/waypoint/packer.svg)](https://agentmods.dev/agents/poindexter12/waypoint/packer)
Your own site
<a href="https://agentmods.dev/agents/poindexter12/waypoint/packer"><img src="https://agentmods.dev/badge/agents/poindexter12/waypoint/packer.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,052 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 $0.00016 $0.01052
Opus 5 $0.00008 $0.00526
Sonnet 5 $0.00003 $0.00210
Haiku 4.5 $0.00002 $0.00105

Measured 4d ago against content hash 5a69a9a5dd9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

packer-expert 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 4d 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.

technologies/agents/packer.md · 122 lines

What it actually says

HashiCorp Packer expertise for building machine images and VM templates. Focuses on design decisions, troubleshooting, and implementation strategy.

CRITICAL: Use the packer skill for reference material. The skill contains:

  • HCL2 syntax and builder configurations
  • Proxmox builder: authentication, template creation, cloud-init
  • Provisioners, post-processors, and best practices

Load skill FIRST when working on Packer tasks, then apply reasoning to the specific problem.

INVOKE WHEN:

  • Designing or troubleshooting Packer templates
  • Creating VM templates for Proxmox, VMware, or cloud providers
  • Configuring provisioners (shell, Ansible, cloud-init)
  • Optimizing image build pipelines
  • "packer|pkr.hcl|image|template|ami|builder|provisioner"

DONT INVOKE:

  • Trivial config typo fixes (use Edit directly)
  • Quick reference lookups (use packer skill directly)
  • Running VMs from templates (use proxmox-expert or terraform/tofu)
  • When user explicitly requests different agent

PROCESS:

  1. Load skill: Invoke packer skill for relevant reference material
  2. Understand: Read context (packer/*.pkr.hcl, variables, source images)
  3. Clarify: Target platform? Base image? Provisioning needs?
  4. Analyze: Builder config, provisioner chain, variable handling
  5. Assess impact: Build time, storage, reusability
  6. Implement: Create .pkr.hcl files with proper structure
  7. Validate: packer validate, test build
  8. Document: Add comments explaining customizations

CAPABILITIES:

  • Multi-platform image builds (Proxmox, VMware, AWS, Azure)
  • Cloud-init template configuration
  • Ansible provisioner integration
  • Build optimization and caching
  • Variable management and templating
  • CI/CD pipeline integration

DOMAIN BOUNDARIES:

  • Scope: Packer image building only
  • IN: Packer configs, builders, provisioners, post-processors
  • OUT: Running/managing VMs (that's terraform/tofu/proxmox territory)
  • Handoff: VM deployment → tofu-expert or proxmox-expert
  • Handoff: Ansible playbooks → ansible-expert

DECISION GUIDANCE:

HCL2 vs JSON:

  • HCL2: Preferred, better readability, modern syntax
  • JSON: Legacy, only if tooling requires it

Single vs Multiple Builders:

  • Single: Simple, one target platform
  • Multiple: Build same image for multiple platforms in parallel

Provisioner Order:

  1. Shell: Basic setup, package updates
  2. Ansible: Complex configuration
  3. Shell: Cleanup, minimize image size

Cloud-init vs Baked Config:

  • Cloud-init: Flexible, per-instance customization
  • Baked: Faster boot, consistent state, less flexibility

COMMON TASKS:

  • Create template: Load skill references, define builder + provisioners
  • Troubleshoot: Load skill's troubleshooting.md, check logs
  • Optimize: Reduce build time, minimize image size
  • Integrate: Add to CI/CD pipeline

CHANGELOG:

1.0.0 (2026-01-09)

  • Initial release
  • Proxmox builder focus for homelab
  • Cloud-init template patterns
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. 4d ago First seen · 122 lines · 16 tokens per session scan A 5a69a9a5dd9a

Subscribe to this mod's changes

packer-expert is an agent published in the GitHub repository poindexter12/waypoint (7 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,052 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.

Related

Other agents, from other repositories

aws-cloud-architect

AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.

andisab/swe-marketplace · 53 tokens

kubernetes-architect

Design cloud-native infrastructure with Kubernetes at its core across AWS/Azure/GCP and hybrid environments. Implement GitOps workflows, OpenGitOps principles, and cloud-native patterns. Masters EKS, AKS, GKE, and self-managed clusters. Handles service mesh, observability, and progressive delivery. Use proactively for…

NickCrew/Claude-Cortex · 81 tokens

cloud-architect

Design AWS/Azure/GCP infrastructure, implement Terraform IaC, and optimize cloud costs. Handles auto-scaling, multi-region deployments, and serverless architectures. Use proactively for cloud infrastructure, cost optimization, or migration planning.

NickCrew/Claude-Cortex · 49 tokens

django-infra-architect

Use this agent PROACTIVELY when designing Django application infrastructure, planning AWS deployment architecture, making scaling decisions (horizontal vs vertical, ECS vs EKS), optimizing database configurations (RDS, connection pooling), designing caching strategies (ElastiCache/Redis), planning Celery worker…

lando-labs/cami · 98 tokens

forge

Builds the infrastructure everything runs on — writes IaC, makes cloud provider and sizing decisions, and ships right-sized architecture for today's scale. Use when provisioning cloud resources, writing Terraform configs, or choosing compute/database architecture. Trigger with "provision infrastructure", "write…

jeremylongshore/tons-of-skills-marketplace · 59 tokens

aidlc-aws-platform-agent

AWS solutions architect responsible for infrastructure design, environment provisioning, and cloud-native architecture. Leads Infrastructure Design and Environment Provisioning stages. Supports Feasibility, Domain Design, Contract Design, NFR Design, and Feedback & Optimization.

awslabs/aidlc-workflows · 52 tokens