# Performance At Scale

> Use when writing code that runs per item, per frame, or per event, or building a cache or lookup over a collection that can grow large.

- **Type:** Skill
- **Install:** `agentstack add skill-fergius-engineering-instincts-performance-at-scale`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Fergius-Engineering](https://agentstack.voostack.com/s/fergius-engineering)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Fergius-Engineering](https://github.com/Fergius-Engineering)
- **Source:** https://github.com/Fergius-Engineering/instincts/tree/main/skills/performance-at-scale

## Install

```sh
agentstack add skill-fergius-engineering-instincts-performance-at-scale
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## The rule

Hot-path code meets your data at production scale, not at the handful of rows in your test fixture. A linear scan that's instant on ten items freezes the UI on a hundred thousand. The cost is invisible in the test and brutal in the field. Design the hot path for the largest realistic input before you write it, not after a user reports a freeze.

## Fires when

Writing code that runs per item, per frame, or per event. Building a cache or a lookup. Iterating a collection that could grow large. Rebuilding a whole list when one entry changed.

## How to apply

Before writing data-path code, ask "does this hold at the largest realistic input?"

Use O(1) lookups with an early exit — a map keyed by the thing you're asking about, so 99% of queries return immediately. Prefer incremental point updates (remove one, add one) over rebuilding the whole structure. Keep allocations and copies out of tight loops. Verbose logging in a hot loop is fine, but only after the early exit, never before it.

If the answer is "no, it won't scale", redesign before you write it, not after.

## Worked example

A handler runs once per tile and scans a flat list of issues linearly to find the ones that match. With a dozen issues in the test, it's instant. In a real project the list holds four thousand issues, and every tile now costs a one-to-two second freeze. Keyed into a map by tile, each query early-exits in O(1) and the freeze is gone. The scan looked fine because the test never had enough data to make it hurt.

## Red flags

| Thought | Reality |
|---|---|
| "It's fast enough" | Fast on the fixture, frozen at scale. |
| "I'll rebuild the whole list, it's simpler" | Simpler to write, O(N) to run every time. |
| "Just loop and find it" | A linear scan on a hot path is a freeze waiting for data. |

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Fergius-Engineering](https://github.com/Fergius-Engineering)
- **Source:** [Fergius-Engineering/instincts](https://github.com/Fergius-Engineering/instincts)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-fergius-engineering-instincts-performance-at-scale
- Seller: https://agentstack.voostack.com/s/fergius-engineering
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.