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.
npx skills add alivirgo/Major-AI-Skills --skill batch-file-creationgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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.
[](https://agentmods.dev/skills/alivirgo/major-ai-skills/batch-file-creation)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/batch-file-creation"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/batch-file-creation/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.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/batch-file-creation"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/batch-file-creation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.01380 |
| Opus 5 | $0.00012 | $0.00690 |
| Sonnet 5 | $0.00005 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade A, and why
batch-file-creation 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch File Scaffolding (Single-Turn Scripted Generation)
Overview
When an agent initializes a new microservice, UI component directory, or test suite, creating each file through individual write_to_file tool calls requires 10 to 20 consecutive agent turns.
Each turn re-sends the entire conversation transcript, accumulating quadratic token costs and taking 1 to 2 minutes of back-and-forth roundtrips.
The Batch File Scaffolding Protocol enables agents to create 10+ directory structures and boilerplate files in a single turn by writing and executing a local generator script or using a multi-file dictionary writer.
15-Turn Sequential Invocations vs. 1-Turn Batch Scaffolding
┌─────────────────────────────────────────────────────────────┐
│ Scaffolding Turn Mechanics │
│ │
│ Sequential Tool Calls (10 Files): │
│ • Turn 1: `write_to_file("Button.tsx")` │
│ • Turn 2: `write_to_file("Button.test.tsx")` │
│ • Turn 3: `write_to_file("Button.module.css")` │
│ • ... (10 turns, 10 API roundtrips, 15,000 tokens billed) │
│ │
│ Single-Turn Batch Scaffolding (10 Files): │
│ • Turn 1: Agent writes & executes `scratch/scaffold.py` │
│ ↳ All 10 files created on disk simultaneously in 50ms │
│ ↳ 1 Turn, 1 API roundtrip, 650 tokens billed (95% Savings) │
└─────────────────────────────────────────────────────────────┘
Production Batch Scaffolding Implementations
1. Python Dictionary-Driven Multi-File Writer
Use this pattern to scaffold multiple files across directories in a single command:
# scratch/scaffold_component.py
from pathlib import Path
FILES = {
"src/components/Modal/Modal.tsx": """import React from 'react';
import styles from './Modal.module.css';
export interface ModalProps {
isOpen: boolean;
onClose: () => void;
title: string;
children: React.ReactNode;
}
export const Modal: React.FC<ModalProps> = ({ isOpen, onClose, title, children }) => {
if (!isOpen) return null;
return (
<div className={styles.overlay} onClick={onClose}>
<div className={styles.modal} onClick={(e) => e.stopPropagation()}>
<h2>{title}</h2>
{children}
</div>
</div>
);
};
""",
"src/components/Modal/Modal.module.css": """.overlay { position: fixed; inset: 0; background: rgba(0,0,0,0.5); }
.modal { background: #fff; padding: 24px; border-radius: 8px; margin: 100px auto; max-width: 500px; }
""",
"src/components/Modal/Modal.test.tsx": """import { render, screen } from '@testing-library/react';
import { Modal } from './Modal';
describe('Modal Component', () => {
it('renders children when isOpen is true', () => {
render(<Modal isOpen={true} onClose={() => {}} title="Test"><div>Content</div></Modal>);
expect(screen.getByText('Content')).toBeInTheDocument();
});
});
""",
"src/components/Modal/index.ts": """export { Modal } from './Modal';
export type { ModalProps } from './Modal';
"""
}
for file_path, content in FILES.items():
p = Path(file_path)
p.parent.mkdir(parents=True, exist_ok=True)
p.write_text(content.strip() + "\n", encoding="utf-8")
print(f"Created: {file_path}")
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.
- today Changed · -10 tokens per session ff197e161c0f
- 6d ago First seen · 140 lines · 33 tokens per session scan A 5c0034b0d3d0
batch-file-creation is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,380 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
advogado-criminal-v2
ADVOGADO CRIMINALISTA SENIOR — ESPECIALISTA EM DIREITO PENAL E MARIA DA PENHA workflow skill. Use this skill when the user needs Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal and the operator should…
ad-creative-v2
Ad Creative workflow skill. Use this skill when the user needs Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization and the operator…
armada-verification
Mandatory pre-completion verification and evidence checklist before reporting done.
armada-resume
Resume a killed or interrupted armada session. Use on session start or when nextAction is non-empty. Triggers on: resume, reconcile, killed session, /armada-resume.
airtable-automation-v2
Airtable Automation via Rube MCP workflow skill. Use this skill when the user needs Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas and the operator should preserve the upstream workflow, copied support files, and provenance before…
trueline-workflow
Use when editing, reading, searching, or exploring files with trueline MCP tools (truelineread, truelineedit, truelinesearch, truelineoutline, truelineverify, truelinechanges). Covers when to pick trueline over built-in Read/Edit/Grep, ref reuse, hash-verified edits, search-then-edit, insertafter semantics, workflows…