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 perniemann/pnCore --skill pn-graphqlgit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-graphql)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-graphql"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-graphql/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/perniemann/pncore/pn-graphql"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-graphql.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 | $0.00041 | $0.01366 |
| Opus 5 | $0.00020 | $0.00683 |
| Sonnet 5 | $0.00008 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
pn-graphql 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 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.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GraphQL
When to use
- Designing or implementing a GraphQL API (schema-first or code-first)
- Writing resolvers, mutations, or subscriptions
- Reviewing a GraphQL schema for N+1 problems, over-fetching, or security issues
- Setting up Apollo Server, GraphQL Yoga, or Pothos
- Adding GraphQL Federation (supergraph / subgraph split)
Core principles
- Schema is the contract — design the schema from the consumer's perspective, not the database shape.
- Solve N+1 before shipping — every list resolver that calls a data source must use DataLoader or a batch-aware fetcher.
- Depth and complexity limits are non-negotiable — unprotected GraphQL endpoints are trivially DoS-able via nested queries.
- Mutations are commands, not CRUD — name mutations after business operations (
placeOrder,cancelSubscription) not database verbs (updateOrder). - Never expose internal IDs — use opaque cursor-based pagination and global IDs (
node(id: "User:123")).
Schema design
# Use clear domain language; avoid database column names as field names
type User {
id: ID!
email: String!
displayName: String!
orders(first: Int, after: String): OrderConnection!
createdAt: DateTime!
}
type OrderConnection {
edges: [OrderEdge!]!
pageInfo: PageInfo!
totalCount: Int!
}
type OrderEdge {
cursor: String!
node: Order!
}
# Errors as values — union return types for mutations
type PlaceOrderResult {
order: Order
error: PlaceOrderError
}
enum PlaceOrderError {
INSUFFICIENT_INVENTORY
PAYMENT_DECLINED
INVALID_ADDRESS
}
Resolvers (Apollo Server / GraphQL Yoga)
import { ApolloServer } from "@apollo/server";
import DataLoader from "dataloader";
// Batch loader — resolves N users in one query
const userLoader = new DataLoader<string, User>(async (ids) => {
const users = await db.user.findMany({ where: { id: { in: [...ids] } } });
return ids.map((id) => users.find((u) => u.id === id) ?? new Error(`User ${id} not found`));
});
const resolvers = {
Query: {
user: (_: unknown, { id }: { id: string }, { loaders }: Context) =>
loaders.user.load(id),
},
Order: {
// Field resolver — batched via DataLoader, not N+1
customer: (order: Order, _: unknown, { loaders }: Context) =>
loaders.user.load(order.customerId),
},
Mutation: {
placeOrder: async (_: unknown, args: PlaceOrderInput, { user }: Context) => {
if (!user) throw new GraphQLError("Unauthorized", { extensions: { code: "UNAUTHENTICATED" } });
// business logic
},
},
};
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.
- 5d ago First seen · 178 lines · 41 tokens per session scan A 54f8becc9b78
pn-graphql is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,366 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
architecture-patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or…
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
chat-sdk
Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…
developing-genkit-tooling
Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
output-dev-workflow-cost
Calculate and display the cost of an Output SDK workflow execution run. Use when checking LLM token costs, API service costs, or total spend for a specific workflow run.