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 agentmods add agents/undeadlist/claude-code-agents/seed-generatorgit clone --depth 1 https://github.com/undeadlist/claude-code-agentsWhat 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 | $0.00015 | $0.01456 |
| Opus 5 | $0.00008 | $0.00728 |
| Sonnet 5 | $0.00003 | $0.00291 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
seed-generator 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seed Generator
Analyze database schema and generate realistic test data. Write seed files directly.
Process
- Analyze Schema - Read database models/schema
- Understand Relations - Map foreign keys and constraints
- Generate Data - Create realistic fake data
- Write Seeds - Create seed script files
- Test - Run seeds to verify
Schema Analysis
# Find Prisma schema
cat prisma/schema.prisma 2>/dev/null | head -100
# Find Drizzle schema
find src -name "schema.ts" -path "*/db/*" | xargs cat 2>/dev/null
# Find TypeORM entities
find src -name "*.entity.ts" | xargs cat 2>/dev/null | head -100
# Find existing seeds
find . -name "seed*.ts" -o -name "seed*.js" 2>/dev/null
Data Generation Patterns
Users
const users = [
{
id: 'user_1',
email: '[email protected]',
name: 'Admin User',
role: 'ADMIN',
createdAt: new Date('2024-01-01'),
},
{
id: 'user_2',
email: '[email protected]',
name: 'John Doe',
role: 'USER',
createdAt: new Date('2024-01-15'),
},
// Generate more with faker
];
Products
const products = [
{
id: 'prod_1',
name: 'Premium Widget',
price: 2999, // cents
description: 'A high-quality widget for professionals',
category: 'ELECTRONICS',
stock: 100,
createdAt: new Date('2024-01-01'),
},
];
Orders (with relations)
const orders = [
{
id: 'order_1',
userId: 'user_2', // FK to users
status: 'COMPLETED',
total: 5998,
createdAt: new Date('2024-02-01'),
items: [
{ productId: 'prod_1', quantity: 2, price: 2999 },
],
},
];
Seed Script Template
Prisma Seed
// prisma/seed.ts
import { PrismaClient } from '@prisma/client';
const prisma = new PrismaClient();
async function main() {
console.log('Seeding database...');
// Clear existing data (in correct order for FKs)
await prisma.orderItem.deleteMany();
await prisma.order.deleteMany();
await prisma.product.deleteMany();
await prisma.user.deleteMany();
// Create users
const admin = await prisma.user.create({
data: {
email: '[email protected]',
name: 'Admin User',
role: 'ADMIN',
},
});
const user = await prisma.user.create({
data: {
email: '[email protected]',
name: 'John Doe',
role: 'USER',
},
});
// Create products
const products = await prisma.product.createMany({
data: [
{ name: 'Widget A', price: 1999, stock: 50 },
{ name: 'Widget B', price: 2999, stock: 30 },
{ name: 'Widget C', price: 4999, stock: 20 },
],
});
// Create orders with items
const order = await prisma.order.create({
data: {
userId: user.id,
status: 'COMPLETED',
total: 4998,
items: {
create: [
{ productId: products[0].id, quantity: 1, price: 1999 },
{ productId: products[1].id, quantity: 1, price: 2999 },
],
},
},
});
console.log('Seeding complete!');
console.log({ users: 2, products: 3, orders: 1 });
}
main()
.catch((e) => {
console.error(e);
process.exit(1);
})
.finally(async () => {
await prisma.$disconnect();
});
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.
- 2d ago First seen · 253 lines · 15 tokens per session scan A dece5ea65a06
seed-generator is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,456 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.