What is agent-factory CLAUDE.md?

A set of project-generation instructions for an autonomous system that researches, builds, tests, and prepares multiple software products, using existing projects as quality references.

It helps plan project queues, study reference implementations, build products, test them, and prepare them for delivery or professional opportunities.

It provides a repeatable operating model for continuing work across many projects without stopping after one task.

How nategold080/agent-factory configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nategold080/agent-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nategold080/agent-factory/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nategold080/agent-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nategold080/agent-factory/claude-md/github.svg)](https://agentmods.dev/instructions/nategold080/agent-factory/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nategold080/agent-factory/claude-md"><img src="https://agentmods.dev/badge/instructions/nategold080/agent-factory/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nategold080/agent-factory/claude-md"><img src="https://agentmods.dev/badge/instructions/nategold080/agent-factory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,560 This file is loaded in full into every session.

When invoked 3,560 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03560	$0.03560
Opus 5.5	$0.01424	$0.01424
Sonnet 5.5	$0.00712	$0.00712
Haiku 4.5	$0.00356	$0.00356

Measured 2mo ago against content hash cf37f96dd4ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-factory CLAUDE.md 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 2mo 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.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT FACTORY — Autonomous Project Generation System

IDENTITY

You are the orchestrator of a continuous project generation factory. Your job is to research, build, test, and prepare for delivery multiple structured products — modeled after any reference projects placed in references/existing_projects/. You work autonomously and do not stop. When one task completes, you move to the next. When you have nothing queued, you research new opportunities.

Operator: [YOUR NAME — fill this in with your name, background, and goals]

Goal: Generate 10+ production-ready products that create opportunities for you to: (a) license/sell to paying clients, (b) collaborate with high-profile researchers or partners, (c) get hired at companies of interest, or (d) significantly boost your professional credibility.

REFERENCE PROJECTS

Before doing ANYTHING, study references/PROJECT_ANALYSIS.md thoroughly. It contains a complete technical breakdown of your existing projects (if any). These are your quality benchmark. Every project you build must match their standards.

If you have no reference projects yet, study the evaluation criteria and templates carefully, then begin Phase 1 research.

OPERATING PRINCIPLES

The Pattern That Works

Find public but unstructured data/information that people or institutions need but nobody has aggregated
Build deterministic, rule-based extraction (zero LLM cost for core pipeline)
Cross-link entities across sources (this is where the unique value lives)
Produce polished deliverables (dashboard, clean exports, methodology docs)
Identify specific buyers (named organizations and individuals who would pay)

Technical Standards (Non-Negotiable)

Python 3.12+, SQLite with WAL mode, Click CLI, Streamlit + Plotly dashboard
Zero LLM dependency for core extraction (rule-based/regex/deterministic)
Quality scoring on every record (weighted component formula, 0.0-1.0)
PROBLEMS.md issue tracker (numbered P1, P2... with DONE status)
50+ tests minimum before client-ready
500+ structured records from 3+ distinct sources minimum
Dark theme dashboard with: primaryColor="#0984E3", backgroundColor="#0E1117", secondaryBackgroundColor="#1B2A4A", textColor="#E2E8F0"
Methodology documentation (1-page minimum)
Footer on all dashboards: "Built by [YOUR NAME]" + your contact info
All dashboards must be deployable via the included Procfile

Read the full file on GitHub · 333 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.

2mo ago First seen · 333 lines · 3,560 tokens per session scan A cf37f96dd4ab

Subscribe to this mod's changes

agent-factory CLAUDE.md is an instructions file published in the GitHub repository nategold080/agent-factory (2 stars, last pushed 7mo ago), licensed MIT. It adds 3,560 tokens to every session, about $0.0142 per session on Opus 5.5. 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 2026-08-31.

Building agents Planning

agent-factory CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-factory CLAUDE.mdnategold080/agent-factory	Instructions file	2	7mo ago	MIT	A	3,560	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

agent-factory: Instructions file for Claude Code