Performance Standards

Guidance for reviewing website and application speed, including rendering, data requests, file sizes, database queries, caching, and loading behavior.

In plain words
What is it for?
Use it when changing page rendering, API latency, images, caching, database access, large lists, or user-visible loading states.
Why use it?
It helps find slow paths that may be hidden by a fast development machine, such as unindexed queries, duplicate requests, large bundles, or network waterfalls.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/yuri-semenenko/ai-engineering-workspace/performance
Clone the repo
git clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspace

Made for: GitHub Copilot.

Per session 695 This file is loaded in full into every session.
When invoked 695 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00695 $0.00695
Opus 5 $0.00347 $0.00347
Sonnet 5 $0.00139 $0.00139
Haiku 4.5 $0.00069 $0.00069

Measured 2d ago against content hash af9798ee7540, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Performance Standards 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.

copilot/workspace-template/.github/instructions/performance.instructions.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Standards

Apply when a change affects page rendering, data fetching, API latency, bundle size, images, caching, database queries, large lists, or user-visible loading behavior.

Rationalizations

Excuses that precede a skipped measurement, paired with the answer. If you think the left, the right applies.

  • "It's fast on my machine." -> Your machine is not the p75 user. Check field data and throttle to mid-tier mobile.
  • "I'll add the index later." -> An unindexed query degrades with data growth. Later is an incident, not a task.
  • "Memoize everything to be safe." -> Memoization costs too. Without a profile it adds overhead, not speed.
  • "The bundle's only a bit bigger." -> Bloat compounds. Read the analyzer and name the KB before adding the dependency.
  • "It looks instant locally." -> Local has no network or CPU throttle. Unverified under realistic conditions is unverified.

Check

  • Critical path: know what blocks first render, route transition, interaction response, or API result, and keep it short.
  • Data fetching: avoid duplicate requests, waterfalls, unbounded queries, and fetching fields the view does not use.
  • Caching: reuse existing framework, CDN, app, or database cache patterns, and define invalidation before adding a cache.
  • Rendering: keep expensive computation out of render paths unless memoization or precomputation is justified by evidence.
  • Bundle size: do not add a dependency for a small utility, and check whether code runs on the client or the server.
  • Images and media: responsive sizes, stable dimensions, lazy loading where appropriate, and no oversized source assets.
  • Lists and tables: paginate, virtualize, or otherwise bound large collections, and keep filters and sorts close to the data source.
  • Database: check indexes, query shape, N+1 patterns, transaction scope, and payload size.

Core Web Vitals

  • LCP: do not block hero content on slow client-side work or unnecessary requests.
  • CLS: reserve stable dimensions for images, embeds, cards, tables, and dynamic controls.
  • INP: keep event handlers short and defer non-critical work off the interaction path.
  • Loading, error, and empty states: show progress for slow or remote work without skeletons that shift layout, and make retry cheap.

Read the full file on GitHub · 55 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.

  1. 2d ago First seen · 55 lines · 695 tokens per session scan A af9798ee7540

Subscribe to this mod's changes

Performance Standards is an instructions file published in the GitHub repository yuri-semenenko/ai-engineering-workspace (1 stars, last pushed 4d ago), licensed MIT. It adds 695 tokens to every session, about $0.0035 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 2026-08-31.