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 instructions/yuri-semenenko/ai-engineering-workspace/performancegit clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspaceWhat 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 | $0.00695 | $0.00695 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
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.
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.
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 · 55 lines · 695 tokens per session scan A af9798ee7540
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.
Other instructions, from other repositories
apm architecture.instructions.md
Single canonical owner discipline: one authority per durable decision, guarded by a regression test + a static boundary check.
spec-kitty AGENTS.md
AGENTS.md instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
apm python.instructions.md
Python development guidelines.
mcp-server-excel excel-com-interop.instructions.md
Instructions for sbroenne/mcp-server-excel, covering excel com interop, api selection, batch execution and exceptions, com lifetime and excel application state.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.
mcp-server-excel mcp-llm-guidance.instructions.md
Instructions for sbroenne/mcp-server-excel, a project described as: Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.