The main instructions for developing and packaging the AI Agent Hub npm package, a tool installed with Node.js's package manager.

Use it when developing the package, changing agents or skills, understanding the installation layout, or working with the CLI and generated .claude configuration.

It clarifies the repository structure, generated installation files, and the difference between source files and files created for users.

How ArieGoldkin/ai-agent-hub configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ArieGoldkin/ai-agent-hub. 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/ArieGoldkin/ai-agent-hub/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ArieGoldkin/ai-agent-hub

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ariegoldkin/ai-agent-hub/claude-md/github.svg)](https://agentmods.dev/instructions/ariegoldkin/ai-agent-hub/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ariegoldkin/ai-agent-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/ariegoldkin/ai-agent-hub/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ariegoldkin/ai-agent-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/ariegoldkin/ai-agent-hub/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,653 This file is loaded in full into every session.

When invoked 1,653 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01653	$0.01653
Opus 5	$0.00826	$0.00826
Sonnet 5	$0.00331	$0.00331
Haiku 4.5	$0.00165	$0.00165

Measured 8d ago against content hash 3df243c0150b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-main 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 8d 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 · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚀 AI Agent Hub - Source Repository

⚠️ REPOSITORY SCOPE

This is the source repository for developing the ai-agent-hub NPM package.

No .claude/ folder exists in this repo - it's gitignored and not published. The installation script CREATES .claude/ for users from /agents/, /assets/, and /skills/.

📦 Quick Overview

This repository builds the NPM package: npx ai-agent-hub@latest

Source Structure:

/agents/        # 10 agent personality definitions (source)
/assets/        # Instruction templates (source)
/skills/        # 19 knowledge modules (source)
/lib/           # TypeScript CLI & generators
/bin/           # CLI entry point
/.squad/        # Squad mode orchestration

Installation Creates (v3.5.9+ unified structure):

.claude/
├── agents/              # Copied from /agents/
├── instructions/        # Copied from /assets/ (+ squad files)
├── skills/              # Copied from /skills/
├── context/             # Initialized fresh
├── commands/            # Squad mode only
├── examples/            # Squad mode only
└── settings.local.json

CLAUDE.md               # Generated dynamically
.mcp.json               # MCP server config

🛠️ Common Development Tasks

Quick Commands

# Build
npm run build

# Test Installation (Classic)
node dist/bin/cli.js --project-only --mode classic

# Test Installation (Squad)
node dist/bin/cli.js --project-only --mode squad

# Test Migration
node dist/bin/cli.js migrate

# Publish
npm version [patch|minor|major]
npm publish

Quick Edits

Task	Location	Notes
Add/edit agent	`/agents/*.md`	Update count in help.ts, setup.ts
Add/edit instruction	`/assets/instructions/*.md`	Auto-copied on install
Add/edit skill	`/skills/*/SKILL.md`	Update count in skills-installer.ts
Modify CLI	`/bin/` or `/lib/`	Run `npm run build` after
Modify CLAUDE.md gen	`/lib/claude-md-generator/`	Test both modes
Update squad mode	`/.squad/`	Verify file locations

Read the full file on GitHub · 189 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.

8d ago First seen · 189 lines · 1,653 tokens per session scan A 3df243c0150b

Subscribe to this mod's changes

claude-main is an instructions file published in the GitHub repository ArieGoldkin/ai-agent-hub (11 stars, last pushed 9mo ago), licensed MIT. It adds 1,653 tokens to every session, about $0.0083 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ai-agent-hub: Instructions file for Claude Code