README

README is an agent for Claude Code from alirezarezvani/claude-code-skill-factory. It costs 0 tokens per session (2,262 once invoked), scanned A, original, MIT.

An interactive guide system for creating custom Claude Code Skills, prompts, and agents through a central guide and three specialist guides.

In plain words
What is it for?
Use it to plan and build a custom Skill, generate a detailed prompt, or create a Claude agent for a project.
Why use it?
It turns the process of deciding what to build and how to structure it into a guided conversation.

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/readme
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 README

README.md
[![agentmods](https://agentmods.dev/badge/agents/alirezarezvani/claude-code-skill-factory/readme.svg)](https://agentmods.dev/agents/alirezarezvani/claude-code-skill-factory/readme)
Your own site
<a href="https://agentmods.dev/agents/alirezarezvani/claude-code-skill-factory/readme"><img src="https://agentmods.dev/badge/agents/alirezarezvani/claude-code-skill-factory/readme.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,262 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 $0.00000 $0.02262
Opus 5 $0.00000 $0.01131
Sonnet 5 $0.00000 $0.00452
Haiku 4.5 $0.00000 $0.00226

Measured 5d ago against content hash ff489fee991c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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 5d 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/README.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Factory Navigation Agents

Interactive guide system for building custom Skills, Prompts, and Agents using the Claude Code Skills Factory.


Architecture: Orchestrator + 3 Specialists

User Request
    ↓
factory-guide (Orchestrator)
    ├→ skills-guide (Build Claude Skills)
    ├→ prompts-guide (Generate Mega-Prompts)
    └→ agents-guide (Build Claude Agents)

🤖 Available Agents (4 Total)

1. factory-guide (Orchestrator) - START HERE

Purpose: Main entry point - asks what you want to build and delegates to specialists

Use when: "I want to build something" or "Help me with the skills factory"

What it does:

  • Asks 1 simple question: What to build? (Skill, Prompt, or Agent)
  • Delegates to appropriate specialist
  • Provides final summary

Tools: Read, Grep (lightweight) Model: haiku (fast) Color: Purple (orchestration)

Invoke:

I want to build something for my project

2. skills-guide (Specialist)

Purpose: Build custom Claude Skills (multi-file capabilities)

Questions: 4-5 straightforward

  1. Business type/domain?
  2. What tasks should the skill handle?
  3. Need Python code or just prompts?
  4. How many skills to generate?
  5. Any special requirements?

What it generates:

  • Complete skill folder (SKILL.md, Python if needed, samples)
  • ZIP file for distribution
  • Validation of YAML frontmatter
  • Installation instructions

Tools: Read, Write, Bash, Grep, Glob (full file creation) Model: sonnet (intelligent) Color: Blue (strategic)

Example:

Help me build a skill for analyzing customer feedback

Output: generated-skills/customer-feedback-analyzer/


3. prompts-guide (Specialist)

Purpose: Generate mega-prompts using prompt-factory skill

Questions: 3-4 simple

  1. Preset (69 options) or Custom?
  2. What role? (if custom)
  3. Output format? (XML/Claude/ChatGPT/Gemini)
  4. Core or Advanced mode?

What it does:

  • Guides you to use the prompt-factory skill
  • Helps choose from 69 professional presets
  • Explains format differences
  • Shows how to use generated prompts

Read the full file on GitHub · 397 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. 5d ago First seen · 397 lines · 0 tokens per session scan A ff489fee991c

Subscribe to this mod's changes

README is an agent published in the GitHub repository alirezarezvani/claude-code-skill-factory (855 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,262 tokens. 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.