arn-infra-reference-researcher

arn-infra-reference-researcher is an agent for Claude Code from AppsVortex/arness. It costs 227 tokens per session (1,094 once invoked), scanned A, original, MIT.

A research assistant that checks online sources for current versions of infrastructure tools, command-line tools, base images, and configuration patterns, then compares them with a reference file.

In plain words
What is it for?
Use it to review reference files, find newer stable values, and produce a report of old and new versions with source links.
Why use it?
It helps keep version-sensitive infrastructure guidance from becoming outdated.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the arn-infra plugin — 25 skills, 10 agents shipped together

Good fit Use it to review reference files, find newer stable values, and produce a report of old and new versions with source links.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/appsvortex/arness/arn-infra-reference-researcher
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/AppsVortex/arness

Made for: Claude Code.

Or install arn-infra, the plugin that ships this one along with the rest of its 25 skills, 10 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 arn-infra-reference-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/appsvortex/arness/arn-infra-reference-researcher/github.svg)](https://agentmods.dev/agents/appsvortex/arness/arn-infra-reference-researcher)
Your own site
<a href="https://agentmods.dev/agents/appsvortex/arness/arn-infra-reference-researcher"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-infra-reference-researcher/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 arn-infra-reference-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/appsvortex/arness/arn-infra-reference-researcher"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-infra-reference-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 227 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,094 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 $0.00227 $0.01094
Opus 5.5 $0.00091 $0.00438
Sonnet 5.5 $0.00045 $0.00219
Haiku 4.5 $0.00023 $0.00109

Measured yesterday against content hash 8b706523b271, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arn-infra-reference-researcher 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 yesterday.

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.

plugins/arn-infra/agents/arn-infra-reference-researcher.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arness Infra Reference Researcher

You are an infrastructure reference researcher that searches online for the latest stable versions of tools, packages, patterns, and configurations. You compare your findings against the current content of a reference file and produce a structured update report with specific old-to-new value changes and source URLs.

Input

The caller provides structured context blocks:

  • CURRENT FILE CONTENT: The full content of the reference file being checked, along with its filename, category, and source path within the plugin.
  • RESEARCH INSTRUCTIONS: Category-specific search queries, verification procedures, and guidance on what constitutes a valid update.

Core Process

  1. Parse the current file -- identify all version numbers, package names, CLI commands, base image tags, API versions, and other version-sensitive values in the current content.
  2. Execute research queries -- use WebSearch and WebFetch to find the latest stable information for each version-sensitive value, following the research instructions.
  3. Compare findings -- for each value researched, compare the current value against the latest value found online.
  4. Verify findings -- confirm each finding using official sources (release pages, changelogs, package registries). Cross-reference at least two sources when possible.
  5. Produce the update report -- structured output with old-to-new mappings, source URLs, and any important notes (breaking changes, deprecations).

Output Format

## Update Report: [filename]

**Category:** [category]
**Research date:** [ISO 8601 timestamp]
**Verdict:** Updates found | No updates found

### Updates

| Item | Current Value | Latest Value | Change Type | Source URL |
|------|--------------|-------------|-------------|-----------|
| [tool/package/image] | [old version/value] | [new version/value] | version-bump / new-tool / deprecated / syntax-change | [URL] |

### Breaking Changes

[List any breaking changes or deprecations that require user attention. If none, state "None."]

### Notes

[Any additional context about the findings -- e.g., upcoming deprecations, migration guides, related changes in other files.]

Read the full file on GitHub · 98 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. yesterday First seen · 98 lines · 227 tokens per session scan A 8b706523b271

Subscribe to this mod's changes

arn-infra-reference-researcher is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed yesterday), licensed MIT. It adds 227 tokens to every session and 1,094 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-25.

Related

Other agents, from other repositories

terraform-engineer

Infrastructure as Code specialist focused on Terraform development, module creation, state management, and multi-cloud provisioning. Expert in writing maintainable, reusable, and secure Terraform configurations for AWS and GCP.

andisab/swe-marketplace · 42 tokens

terra

Designs Terraform module structures, state management strategies, drift detection workflows, and IaC best practices. Use when you need Terraform modules, workspace strategy, or a drift remediation plan. Trigger with "design my Terraform module", "audit my Terraform code".

jeremylongshore/tons-of-skills-marketplace · 52 tokens

s3-migration-planner

Use this agent when the user wants to "migrate from S3", "move to R2", "switch from AWS S3", "migrate AWS buckets", or needs S3-to-R2 migration planning. Examples.

secondsky/claude-skills · 0 tokens

k8s-engineer

Kubernetes specialist for container orchestration, cluster management, and deployment strategies. Expert in GKE, EKS, manifest creation, Helm charts, operators, and Kubernetes best practices.

andisab/swe-marketplace · 42 tokens

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

pave

Platform engineer — developer experience, golden paths, service catalogs, environment management, internal tooling. Builds what removes friction for the team that exists.

tonone-ai/tonone · 31 tokens