Sponsor Suno AI Music arrow_forward
Claude Cowork

Claude Cowork

Language

English 中文 日本語 한국어 繁體中文 Español Deutsch Français Português (BR) Italiano Русский Nederlands Polski Tiếng Việt Indonesia
download Download Get Started
Subagent

Performance Principles

Critique principles for high-performance code

Type
Subagent
Repository
nyldn/claude-octopus
GitHub stars
4.1k
License
MIT
Repo last updated
Sep 26, 2026
Source file
agents/principles/performance.md

What Performance Principles is

Performance Principles is a subagent published in the nyldn/claude-octopus repository on GitHub, which has about 4.1k stars. The repository describes itself as: “Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Performance Principles and get back a compact result.

How to install Performance Principles

Claude Code

  1. Download performance.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from agents/principles/performance.md, shared under the repository's MIT license. Read the full file on GitHub.

Code MUST adhere to these performance requirements:

Database & Queries

  1. No N+1 Queries - Batch database calls. Use eager loading, joins, or subqueries instead of loops.
  1. Proper Indexing - Ensure queries use appropriate indexes. Avoid full table scans on large tables.
  1. Query Optimization - Use EXPLAIN ANALYZE to verify query plans. Avoid SELECT *.

Caching & Memory

  1. Strategic Caching - Cache repeated computations and frequently accessed data. Set appropriate TTLs.
  1. Memory Efficiency - No memory leaks. Use bounded allocations. Release resources promptly.
  1. Lazy Loading - Load data only when needed. Defer expensive operations until required.

I/O & Concurrency

  1. Async I/O - Use non-blocking operations for network, file, and database access where possible.
  1. Connection Pooling - Reuse database and HTTP connections. Configure pool sizes appropriately.
  1. Parallel Processing - Use concurrent execution for independent operations. Avoid sequential bottlenecks.

Algorithm & Code

  1. Algorithmic Efficiency - Choose appropriate data structures. Avoid O(n^2) or worse when O(n) is possible.
  1. Minimize Allocations - Reduce object creation in hot paths. Reuse buffers and objects.
  1. Early Exit - Return early when conditions are met. Avoid unnecessary computation.

Checklist

When reviewing code, verify:

  • No N+1 query patterns
  • Database queries use indexes
  • Appropriate caching in place
  • No memory leaks
  • Async operations for I/O
  • Connection pooling configured
  • Efficient algorithms used
  • No unnecessary loops or iterations
  • Resources properly released
  • Pagination for large result sets

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Performance Principles?

Performance Principles is a subagent for Claude Code and Claude Cowork from the nyldn/claude-octopus repository on GitHub. Critique principles for high-performance code

How do I install Performance Principles in Claude Code?

Download performance.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Performance Principles in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Performance Principles safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.