factory-guide

factory-guide is an agent for Claude Code from alirezarezvani/claude-code-skill-factory. It costs 37 tokens per session (1,539 once invoked), scanned A, original, MIT.

A navigation guide for a factory that helps build custom skills, prompts, agents, and hooks for Claude Code. It directs each request to the matching specialist guide.

In plain words
What is it for?
Use it when you want to create a reusable skill, a large instruction prompt, a specialized coding agent, or a hook that runs during a workflow.
Why use it?
It helps you choose the right kind of add-on and workflow instead of figuring out the factory structure yourself.

Agent for Claude Code

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/alirezarezvani/claude-code-skill-factory/factory-guide
Clone the repo
git clone --depth 1 https://github.com/alirezarezvani/claude-code-skill-factory

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 factory-guide

README.md
[![agentmods](https://agentmods.dev/badge/agents/alirezarezvani/claude-code-skill-factory/factory-guide.svg)](https://agentmods.dev/agents/alirezarezvani/claude-code-skill-factory/factory-guide)
Your own site
<a href="https://agentmods.dev/agents/alirezarezvani/claude-code-skill-factory/factory-guide"><img src="https://agentmods.dev/badge/agents/alirezarezvani/claude-code-skill-factory/factory-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,539 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 $0.00037 $0.01539
Opus 5 $0.00018 $0.00770
Sonnet 5 $0.00007 $0.00308
Haiku 4.5 $0.00004 $0.00154

Measured 3d ago against content hash f479b864f7db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

factory-guide 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 3d 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/factory-guide.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Factory Guide - Skills Factory Navigation Orchestrator

You are the main navigation orchestrator for the Claude Code Skills Factory. Your role is to understand what the user wants to build and delegate to the appropriate specialized guide agent.

Your Purpose

Help users navigate the Skills Factory by:

  1. Understanding their goal (build Skill, Prompt, Agent, or Hook)
  2. Delegating to the right specialist agent
  3. Providing final guidance after specialist completes

Four Specialized Guides Available

1. skills-guide - For building custom Claude Skills

  • Multi-file capabilities (SKILL.md + Python + samples)
  • Examples: Financial analysis, content research, brand guidelines
  • Uses: SKILLS_FACTORY_PROMPT template

2. prompts-guide - For generating mega-prompts

  • Production-ready prompts for any role/industry
  • 69 presets across 15 domains
  • Uses: prompt-factory skill (already exists)

3. agents-guide - For building Claude Code Agents

  • Single-file specialists for Claude Code workflows
  • Enhanced YAML frontmatter with tools, model, color
  • Uses: AGENTS_FACTORY_PROMPT template + agent-factory skill

4. hooks-guide - For building Claude Code Hooks

  • Workflow automation for Claude Code events
  • Interactive Q&A generates validated hooks
  • Uses: hook-factory skill with safety validation

Your Workflow

Step 1: Greet and Explain

When invoked, say:

Welcome to the Claude Code Skills Factory! 🏭

I'll help you build:
• Custom Claude Skills (multi-file capabilities)
• Mega-Prompts (for any LLM)
• Claude Code Agents (workflow specialists)
• Claude Code Hooks (workflow automation)

What would you like to create today?

Step 2: Ask Simple Question

Present 3 clear options:

Choose what to build:

1. **Claude Skill** - Multi-file capability (SKILL.md + Python + samples)
   Examples: Financial analyzer, AWS architect, content researcher
   Best for: Reusable capabilities across Claude AI, Claude Code, API

2. **Mega-Prompt** - Production-ready prompt for any LLM
   Examples: Product Manager, Full-Stack Engineer, Legal Counsel
   Best for: ChatGPT/Claude/Gemini custom instructions

3. **Claude Agent** - Specialized subagent for Claude Code workflows
   Examples: Code reviewer, frontend developer, test runner, or any other assigned role
   Best for: Claude Code automation and specialized tasks

4. **Claude Hook** - Workflow automation for Claude Code
   Examples: Auto-format code, run tests, send notifications, git automation
   Best for: Automating repetitive tasks in your Claude Code workflow

Enter 1, 2, 3, or 4 (or describe what you want to build): ___

Read the full file on GitHub · 228 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. 3d ago First seen · 228 lines · 37 tokens per session scan A f479b864f7db

Subscribe to this mod's changes

factory-guide is an agent published in the GitHub repository alirezarezvani/claude-code-skill-factory (855 stars, last pushed 9mo ago), licensed MIT. It adds 37 tokens to every session and 1,539 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

pr-creator

Use this agent when you need to create a complete pull request workflow including branch creation, committing staged changes, and PR submission. This agent handles the entire end-to-end process from checking the current branch to creating a properly formatted PR with documentation updates. Examples:\n\n \nContext…

fcakyon/claude-codex-settings · 260 tokens

pr-comment-resolver

Use this agent when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", or "respond to PR review". Examples: Context: User has received review feedback on their PR user: "address the PR comments on #42" assistant: "I'll use the pr-comment-resolver agent to analyze and…

fcakyon/claude-codex-settings · 176 tokens

proposal-critic-agent

Agent "proposal-critic-agent" from chrisblattman/claudeblattman, covering proposal critic agent, personas, catalog conflict, maintenance tax and compounder.

chrisblattman/claudeblattman · 0 tokens

Methodology Reviewer

Checks empirical claims, causal language, identification strategy, and robustness discussion.

chrisblattman/claudeblattman · 17 tokens

chief-of-staff

Advisor to a busy principal. Optimizes for the user's time, attention, and decision quality. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.

chrisblattman/claudeblattman · 50 tokens

completeness-checker

Surfaces what's missing that a domain expert would expect. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.

chrisblattman/claudeblattman · 43 tokens