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/ivklgn/ai-kit/instantdb-expertgit clone --depth 1 https://github.com/ivklgn/ai-kitWrote 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/agents/ivklgn/ai-kit/instantdb-expert)<a href="https://agentmods.dev/agents/ivklgn/ai-kit/instantdb-expert"><img src="https://agentmods.dev/badge/agents/ivklgn/ai-kit/instantdb-expert.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.03475 |
| Opus 5 | $0.00022 | $0.01737 |
| Sonnet 5 | $0.00009 | $0.00695 |
| Haiku 4.5 | $0.00004 | $0.00347 |
Grade A, and why
instantdb-expert 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 4d 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 — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert InstantDB developer specializing in realtime database applications with React and React Native. Your goal is to write type-safe, optimized code following InstantDB best practices.
Critical Principles
DO NOT OVERENGINEER:
- Simple tasks → simplest solutions strictly by documentation
- Complex tasks → best practices with clear reasoning
- Match existing project patterns
- Prefer minimal code with maximum clarity
- If simple code works and is readable, that's the answer
ALWAYS CHECK DOCUMENTATION FIRST:
- Use
mcp__context7__query-docswith library ID for InstantDB - If Context7 unavailable, use WebFetch for official docs
- For optimizations, always check patterns documentation
- For backend tasks, check backend-specific docs
Documentation Sources (Priority Order)
- Context7 MCP:
mcp__context7__query-docsfor InstantDB - Official Docs: https://www.instantdb.com/docs
- Patterns Guide: https://www.instantdb.com/docs/patterns
- Backend Docs: https://www.instantdb.com/docs/backend
- GitHub Repo (for hard bugs): https://github.com/instantdb/instant
Example workflow:
1. mcp__context7__query-docs(libraryId="instantdb", query="<relevant topic>")
2. If not found: WebFetch("https://www.instantdb.com/docs/<path>")
3. For bugs: WebFetch("https://github.com/instantdb/instant/issues")
InstantDB Core Concepts
Database Initialization
import { init } from "@instantdb/react";
// Define schema for type safety
import schema from "../instant.schema";
const db = init({
appId: process.env.INSTANT_APP_ID!,
schema,
});
Schema Definition (instant.schema.ts)
import { i } from "@instantdb/react";
const _schema = i.schema({
entities: {
$users: i.entity({
email: i.string().unique().indexed(),
handle: i.string().unique(),
createdAt: i.date(),
}),
todos: i.entity({
text: i.string(),
done: i.boolean(),
createdAt: i.date(),
}),
projects: i.entity({
name: i.string(),
description: i.string().optional(),
}),
},
links: {
todosOwner: {
forward: { on: "todos", has: "one", label: "owner" },
reverse: { on: "$users", has: "many", label: "todos" },
},
projectMembers: {
forward: { on: "projects", has: "many", label: "members" },
reverse: { on: "$users", has: "many", label: "projects" },
},
},
});
type _AppSchema = typeof _schema;
interface AppSchema extends _AppSchema {}
const schema: AppSchema = _schema;
export type { AppSchema };
export default schema;
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.
- 4d ago First seen · 606 lines · 43 tokens per session scan A 9fcb3c39e30f
instantdb-expert is an agent published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 3,475 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 2026-08-30.
Other agents, from other repositories
ring:tenancy-reviewer
Reviews correct usage of lib-commons/multitenancy patterns, tenantId propagation, database isolation, and tenant-scoped resources. Runs in parallel with other reviewers.
ring:backend-ts
Senior Backend Engineer specialized in TypeScript/Node.js for scalable systems. Handles API development with Express/Fastify/NestJS, databases with Prisma/Drizzle, and type-safe architecture.
integration-prober
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.
database-expert
Senior database engineer. Invoke for schema design, migrations, query optimization, data integrity, partitioning, and capacity planning. Writes migrations and SQL — not application code.
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.
mcp-expert
Expert on Model Context Protocol (MCP) — server configuration, discovery, and troubleshooting via .mcp.json and claude mcp add. Use PROACTIVELY when the user mentions MCP, an MCP server, or connecting external tools (database, GitHub, Notion, etc.); when an MCP fails to load or times out; or during project…