What is arness CLAUDE.md?

Project instructions for Arness, a marketplace containing separately installable Claude Code add-ons for development, exploration, and infrastructure work.

Use them when developing, testing, or maintaining the Arness marketplace and its three plugins.

They explain the repository structure and conventions, so contributors can place skills, specialist agents, and plugin components correctly.

arness CLAUDE.md — Instructions file by AppsVortex

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 instructions/appsvortex/arness/claude-md

Clone the repo

git clone --depth 1 https://github.com/AppsVortex/arness

Per session 3,527 This file is loaded in full into every session.

When invoked 3,527 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.03527	$0.03527
Opus 5	$0.01764	$0.01764
Sonnet 5	$0.00705	$0.00705
Haiku 4.5	$0.00353	$0.00353

Measured 2d ago against content hash bd1cc9318352, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arness CLAUDE.md 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 2d 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.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Purpose

Arness is a plugin marketplace for Claude Code containing three independently installable plugins for development, greenfield exploration, and infrastructure. The repository is itself a valid Claude Code marketplace, so plugins can be tested locally.

Architecture

arness/                                 # Marketplace repository
├── .claude-plugin/
│   └── marketplace.json                # Marketplace catalog (lists all 3 plugins)
├── plugins/
│   ├── arn-code/                        # Core development plugin
│   │   ├── .claude-plugin/plugin.json
│   │   ├── skills/                     # 25 pipeline skills
│   │   └── agents/                     # 14 specialist agents
│   ├── arn-spark/                       # Greenfield exploration plugin
│   │   ├── .claude-plugin/plugin.json
│   │   ├── skills/                     # 19 exploration skills
│   │   └── agents/                     # 13 specialist agents
│   └── arn-infra/                      # Infrastructure plugin
│       ├── .claude-plugin/plugin.json
│       ├── skills/                     # 23 infrastructure skills
│       └── agents/                     # 9 specialist agents
└── assets/                             # Shared assets (banner, etc.)

Key rule: All plugin component directories (skills/, agents/) must be at the plugin root, NOT inside .claude-plugin/.

Template Management

When updating default report templates in plugins/arn-code/skills/arn-code-save-plan/report-templates/default/:

Make changes to the template JSON files
Bump the plugin's version in the corresponding entry of .claude-plugin/marketplace.json (the marketplace entry is the authoritative version source — plugin.json intentionally omits version per commit d3434de, see the "Versioning" section below)
Test by running arn-code-init in a test project -- templates will be copied and fresh checksums generated
Projects using the previous version will be prompted to update on next Arness skill invocation (behavior depends on their Template updates preference)

Read the full file on GitHub · 194 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.

2d ago First seen · 194 lines · 3,527 tokens per session scan A bd1cc9318352

Subscribe to this mod's changes

arness CLAUDE.md is an instructions file published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 3,527 tokens to every session, about $0.0176 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 2026-08-30.

ai-workflows claude-code claude-code-plugin developer-tools infrastructure-as-code mcp

arness CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Project Purpose

Architecture

Template Management

What this file has done since we first saw it

Other instructions, from other repositories

workflowbuilder CLAUDE.md

pitway CLAUDE.md

terragrunt-mcp-server copilot-instructions.md

apijack GEMINI.md

mcp-tfstate-reader CLAUDE.md

hetzner-mcp CLAUDE.md