everything-claude-code / rules
tpavanipradeep/everything-claude-code/.cursor/rules/common-performance.md
Performance: model selection, context management, build troubleshooting
Cursor rule104 starsChanged 7 months ago
What's in it
- Performance Optimization
- Model Selection Strategy
- Context Window Management
- Extended Thinking + Plan Mode
- Build Troubleshooting
--- description: "Performance: model selection, context management, build troubleshooting" alwaysApply: true --- # Performance Optimization ## Model Selection Strategy **Haiku 4.5** (90% of Sonnet capability, 3x cost savings): - Lightweight agents with frequent invocation - Pair programming and code generation - Worker agents in multi-agent systems **Sonnet 4.6** (Best coding model): - Main development work - Orchestrating multi-agent workflows - Complex coding tasks **Opus 4.5** (Deepest reasoning): - Complex architectural decisions - Maximum reasoning requirements - Research and analysis tasks ## Context Window Management Avoid last 20% of context window for: - Large-scale refactoring - Feature implementation spanning multiple files - Debugging complex interactions Lower context sensitivity tasks: - Single-file edits - Independent utility creation - Documentation updates - Simple bug fixes ## Extended Thinking + Plan Mode Extended thinking is enabled by default, reserving up to 31,999 tokens for internal reasoning. Control extended thinking via: - **Toggle**: Option+T (macOS) / Alt+T (Windows/Linux) - **Config**: Set `alwaysThinkingEnabled` in `~/.claude/settings.json` - **Budget cap**: `export MAX_THINKING_TOKENS=10000` - **Verbose mode**: Ctrl+O to see thinking output For complex tasks requiring deep reasoning: 1. Ensure extended thinking is enabled (on by default) 2. Enable **Plan Mode** for structured approach 3. Use multiple critique rounds for thorough analysis 4. Use split role sub-agents for diverse perspectives ## Build Troubleshooting If build fails: 1. Use **build-error-resolver** agent 2. Analyze error messages 3. Fix incrementally 4. Verify after each fix
More agent context in tpavanipradeep/everything-claude-code
81 other files this repository gives its agents, the first 60 shown.
AGENTS.md
CLAUDE.md
Cursor rule
- .cursor/rules/common-agents.md
- .cursor/rules/common-coding-style.md
- .cursor/rules/common-development-workflow.md
- .cursor/rules/common-git-workflow.md
- .cursor/rules/common-hooks.md
- .cursor/rules/common-patterns.md
- .cursor/rules/common-security.md
- .cursor/rules/common-testing.md
- .cursor/rules/golang-coding-style.md
- .cursor/rules/golang-hooks.md
- .cursor/rules/golang-patterns.md
- .cursor/rules/golang-security.md
- .cursor/rules/golang-testing.md
- .cursor/rules/kotlin-coding-style.md
- .cursor/rules/kotlin-hooks.md
- .cursor/rules/kotlin-patterns.md
- .cursor/rules/kotlin-security.md
- .cursor/rules/kotlin-testing.md
- .cursor/rules/php-coding-style.md
- .cursor/rules/php-hooks.md
- .cursor/rules/php-patterns.md
- .cursor/rules/php-security.md
- .cursor/rules/php-testing.md
- .cursor/rules/python-coding-style.md
- .cursor/rules/python-hooks.md
- .cursor/rules/python-patterns.md
- .cursor/rules/python-security.md
- .cursor/rules/python-testing.md
- .cursor/rules/swift-coding-style.md
- .cursor/rules/swift-hooks.md
- .cursor/rules/swift-patterns.md
- .cursor/rules/swift-security.md
- .cursor/rules/swift-testing.md
- .cursor/rules/typescript-coding-style.md
- .cursor/rules/typescript-hooks.md
- .cursor/rules/typescript-patterns.md
- .cursor/rules/typescript-security.md
- .cursor/rules/typescript-testing.md
Skill
- api-design.agents/skills/api-design/SKILL.md
- article-writing.agents/skills/article-writing/SKILL.md
- backend-patterns.agents/skills/backend-patterns/SKILL.md
- bun-runtime.agents/skills/bun-runtime/SKILL.md
- claude-api.agents/skills/claude-api/SKILL.md
- coding-standards.agents/skills/coding-standards/SKILL.md
- content-engine.agents/skills/content-engine/SKILL.md
- crosspost.agents/skills/crosspost/SKILL.md
- deep-research.agents/skills/deep-research/SKILL.md
- dmux-workflows.agents/skills/dmux-workflows/SKILL.md
- documentation-lookup.agents/skills/documentation-lookup/SKILL.md
- e2e-testing.agents/skills/e2e-testing/SKILL.md
- eval-harness.agents/skills/eval-harness/SKILL.md
- exa-search.agents/skills/exa-search/SKILL.md
- fal-ai-media.agents/skills/fal-ai-media/SKILL.md
- frontend-patterns.agents/skills/frontend-patterns/SKILL.md
- frontend-slides.agents/skills/frontend-slides/SKILL.md
- investor-materials.agents/skills/investor-materials/SKILL.md
Also found in 13 other repositories
The same file, byte for byte, in the weekly crawl of public GitHub; the 10 with the most stars.
- loulanyue/awesome-claude-notes272
- mit-network/everything-claude-code76
- Infopibe/everything-claude-code8
- yapota2018/affaan-m-everything-claude-code4
- ArogyaReddy/https-github.com-affaan-m-everything-claude-code12
- ashutoshrathi0909-oss/everything-claude-code1
- divenhuang88/everything-claude-code1
- elainesmithburkel-code/everything-claude-code1
- pcoulbourne/everything-claude-code1
- TironFox/everything-claude-code1
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.

