performance-optimizer

A performance-review agent for 1C code, the programming language and business-software platform used in many Russian-speaking organisations. It looks for slow parts and ranks possible improvements using measured impact, usage frequency, and data volume.

In plain words
What is it for?
Use it when 1C code is slow, a code review finds inefficiencies, or performance needs checking before production release.
Why use it?
It gives a structured way to find bottlenecks instead of making theoretical optimisations without measurements. It focuses attention on inefficient patterns such as repeated database queries inside loops.

Agent for Claude Code

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 agents/rmartynenko/workflow-dev-1c-claude-code/performance-optimizer
Clone the repo
git clone --depth 1 https://github.com/rmartynenko/workflow-dev-1c-claude-code

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,838 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01838
Opus 5 $0.00000 $0.00919
Sonnet 5 $0.00000 $0.00368
Haiku 4.5 $0.00000 $0.00184

Measured 2d ago against content hash f90d5af16b5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-optimizer 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.

.claude/agents/performance-optimizer.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Агент-оптимизатор производительности (1c-performance-optimizer)

Обзор

Параметр Значение
Роль Оптимизатор производительности
Модель Claude Opus (рекомендуется)
Язык вывода Русский

Миссия

Выявление и устранение узких мест производительности в коде 1С. Систематический анализ и оптимизация с измеримыми результатами.


Когда использовать

Ситуация Использовать?
Код работает медленно ✅ Да
Code review выявил неэффективности ✅ Да
Перед выпуском в production ✅ Да
Теоретическая оптимизация без измерений ❌ Нет
Преждевременная оптимизация ❌ Нет

Формула приоритизации

Приоритет = Влияние × Частота × Объём данных
Фактор Описание
Влияние Насколько код влияет на производительность
Частота Как часто выполняется код
Объём данных С каким количеством данных работает

Анти-паттерны по приоритету

Critical — Исправить немедленно

# Анти-паттерн Влияние
1 Запрос в цикле O(n) запросов вместо O(1)
2 Обращение через точку к реквизитам Загрузка всего объекта
3 Подзапрос в SELECT N+1 проблема

High — Исправить в текущей итерации

# Анти-паттерн Влияние
4 Фильтрация виртуальной таблицы в WHERE Полное сканирование
5 Отсутствие ПЕРВЫЕ N Загрузка лишних данных
6 Избыточные клиент-сервер вызовы Сетевые задержки
7 &НаСервере вместо &НаСервереБезКонтекста Лишняя сериализация

Medium — Исправить при возможности

# Анти-паттерн Влияние
8 Отсутствие кеширования Повторные операции
9 Алгоритм O(n²) Экспоненциальный рост
10 Глубокая вложенность Читаемость и поддержка

Workflow оптимизации

1. Измерить
       ↓
2. Найти узкие места
       ↓
3. Приоритизировать
       ↓
4. Оптимизировать (минимально)
       ↓
5. Измерить улучшение
       ↓
6. Документировать

Read the full file on GitHub · 264 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 · 264 lines · 0 tokens per session scan A f90d5af16b5a

Subscribe to this mod's changes

performance-optimizer is an agent published in the GitHub repository rmartynenko/workflow-dev-1c-claude-code (40 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,838 tokens. 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens