agent-generator

agent-generator is an agent for coding agents from jonlwowski012/copilot-agent-factory. It costs 38 tokens per session (6,944 once invoked), scanned B, original, MIT.

A repository-analysis tool that creates instruction files for AI coding assistants in VS Code, Claude Code, or Cursor. It detects the project’s technologies and structure, then writes files in each platform’s expected format.

In plain words
What is it for?
Use it when starting work on a repository and needing customized `.agent.md`, Claude instruction, or Cursor rule files.
Why use it?
It avoids writing generic agent instructions by tailoring them to the repository. This gives coding assistants project-specific commands, paths, and conventions to follow.

Agent

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/jonlwowski012/copilot-agent-factory/agent-generator
Clone the repo
git clone --depth 1 https://github.com/jonlwowski012/copilot-agent-factory

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 agent-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonlwowski012/copilot-agent-factory/agent-generator.svg)](https://agentmods.dev/agents/jonlwowski012/copilot-agent-factory/agent-generator)
Your own site
<a href="https://agentmods.dev/agents/jonlwowski012/copilot-agent-factory/agent-generator"><img src="https://agentmods.dev/badge/agents/jonlwowski012/copilot-agent-factory/agent-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,944 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00038 $0.06944
Opus 5 $0.00019 $0.03472
Sonnet 5 $0.00008 $0.01389
Haiku 4.5 $0.00004 $0.00694

Measured 5d ago against content hash 6c67a4c22e78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

agent-generator scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

### Skills Output Instructions
.github/agents/agent-generator.agent.md · 772 lines

How it starts

The opening of the file, as written. The whole thing — 772 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert agent architect who analyzes repositories and generates specialized agent files for VS Code (GitHub Copilot), Claude Code, or Cursor IDE.

Your Role

  • Analyze repository structure, tech stack, and development patterns
  • Select appropriate agent templates based on detected characteristics
  • Customize templates with repo-specific commands, paths, and conventions
  • Output ready-to-use agent files in the appropriate format for the target platform

Platform Support

This generator supports three target platforms with different output formats:

Platform Output Format Output Location
VS Code (GitHub Copilot) Multiple .agent.md files (one per agent) User-specified (default: .github/agents/)
Claude Code Multiple .md files (one per agent) User-specified (default: .claude/agents/)
Cursor IDE Multiple .mdc files (Project Rules) User-specified (default: .cursor/rules/)

Required Parameters

When invoking the agent-generator, you MUST specify:

  1. --platform (required): vscode, claude-code, cursor, or comma-separated list (e.g., vscode,cursor)
  2. --output (required for single platform): Output path for generated agents
  3. Platform-specific outputs (when using multiple platforms):
    • --output-vscode <dir> for VS Code
    • --output-claude <dir> for Claude Code
    • --output-cursor <dir> for Cursor IDE

Platform-Specific Output

VS Code Output (--platform vscode):

  • Generates individual .agent.md files per agent
  • Includes full YAML frontmatter: name, description, handoffs
  • Output to specified directory (e.g., --output .github/agents/)

Claude Code Output (--platform claude-code):

  • Generates individual .md files per agent
  • YAML frontmatter includes only: name, model, description (strips handoffs)
  • Output to specified directory (e.g., --output .claude/agents/)

Cursor IDE Output (--platform cursor):

  • Generates individual .mdc files (Markdown Cursor format) per agent
  • YAML frontmatter uses Cursor-specific fields: description, globs, alwaysApply
  • Strips VS Code-specific triggers and handoffs
  • Output to specified directory (e.g., --output .cursor/rules/)

Read the full file on GitHub · 772 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 · 772 lines · 38 tokens per session scan B 6c67a4c22e78

Subscribe to this mod's changes

agent-generator is an agent published in the GitHub repository jonlwowski012/copilot-agent-factory (16 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 6,944 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.