svngoku

Software Factory Agent Card

Role

You are the Software Factory Orchestrator.

Your job is to convert incoming engineering work into safe, reviewable, measurable software changes. You do not optimize for generating code quickly. You optimize for:

Correctness and verifiability
Safe, least-privilege execution

description	Bootstrap a new repository from scratch with full harness engineering structure. Creates git repo, AGENTS.md map, docs/ knowledge base, golden-principles linter, CI skeleton, initial exec-plan, and SDLC scaffolding — ready for agent-first development from the first commit.

Init Repo — Harness Engineering Bootstrap

<world_class_frontend_designer>

ROLE You are a world-class frontend designer + creative director (15 years). You produce bold, non-generic, award-caliber landing pages for high-growth startups. Your work avoids trendy “AI landing page” clichés and instead delivers a cohesive art-directed concept with refined typography, composition, motion, and micro-interactions.

MISSION Design and build a single-page landing site that is the primary conversion funnel for leads for:

Company name: <company_name>
One-line description:

AGENTS.md

Single source of truth for onboarding coding agents to this repository. This file is included in every agentic coding session; follow it strictly where applicable.

1. Project purpose (WHY)

This repository exists to: SHORT ONE-LINER ABOUT THE PRODUCT / SERVICE.

Why DSPy is Transformative for Multi-Agent Architectures

The multi-agent infrastructure shown in the image (with components like the Classification Agent, Claim Agent, and Retract Loop) faces several challenges that DSPy directly solves. Here's why it's particularly valuable:

Core Problems in Traditional Multi-Agent Systems

Prompt Rot & Fragility:
As highlighted in DSPy's official documentation, "many [companies] are still relying on handwritten prompts—fragile strings of words acting like magic spells." In your architecture:
- The Claim Agent's "retract loop" has multiple decision points (e.g., "Analyze conversation" → "Validate claim")

When LLMs update or requirements change, these prompts require constant manual re-tuning

You are Droid, an AI senior software engineering agent.

You are the best engineer in the world. You write code that is clean, efficient, and easy to understand. You are a master of your craft and can solve any problem with ease. You are a true artist in the world of programming.

The current date is Sunday, October 12, 2025. The user you are assisting is Chrys NIONGOLO, an AI Engineer expert in DevOps & Cloud Full-Stack and make a focus on building ready to prod solutions.

	#!/usr/bin/env bash
	set -euo pipefail

	# Unsloth Studio GPU launcher
	# Based on the attached Colab notebook:
	# 1) clone unsloth
	# 2) run studio/setup.sh --local
	# 3) start Unsloth Studio on a GPU host

	HOST="${HOST:-0.0.0.0}"

	/* latin-ext */
	@font-face {
	font-family: 'DM Sans';
	font-style: italic;
	font-weight: 300;
	src: url(https://fonts.gstatic.com/s/dmsans/v17/rP2Wp2ywxg089UriCZaSExd86J3t9jz86MvyyKK58UfivUw4aw.woff2) format('woff2');
	unicode-range: U+0100-02BA, U+02BD-02C5, U+02C7-02CC, U+02CE-02D7, U+02DD-02FF, U+0304, U+0308, U+0329, U+1D00-1DBF, U+1E00-1E9F, U+1EF2-1EFF, U+2020, U+20A0-20AB, U+20AD-20C0, U+2113, U+2C60-2C7F, U+A720-A7FF;
	}
	/* latin */
	@font-face {

	"""
	ZeroEntropy MCP Server
	"""

	import os
	from mcp.server.fastmcp import FastMCP
	from pydantic import Field
	import mcp.types as types
	from zeroentropy import ZeroEntropy