Files
everything-claude-code/rules/performance.md
Affaan Mustafa 45959c326e Initial release: Complete Claude Code configuration collection
Battle-tested configs from 10+ months of daily Claude Code usage.
Won Anthropic x Forum Ventures hackathon building zenith.chat.

Includes:
- 9 specialized agents (planner, architect, tdd-guide, code-reviewer, etc.)
- 9 slash commands (tdd, plan, e2e, code-review, etc.)
- 8 rule files (security, coding-style, testing, git-workflow, etc.)
- 7 skills (coding-standards, backend-patterns, frontend-patterns, etc.)
- Hooks configuration (PreToolUse, PostToolUse, Stop)
- MCP server configurations (15 servers)
- Plugin/marketplace documentation
- Example configs (project CLAUDE.md, user CLAUDE.md, statusline)

Read the full guide: https://x.com/affaanmustafa/status/2012378465664745795
2026-01-17 17:49:33 -08:00

1.2 KiB

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 4.5 (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

Ultrathink + Plan Mode

For complex tasks requiring deep reasoning:

  1. Use ultrathink for enhanced thinking
  2. Enable Plan Mode for structured approach
  3. "Rev the engine" with multiple critique rounds
  4. Use split role sub-agents for diverse analysis

Build Troubleshooting

If build fails:

  1. Use build-error-resolver agent
  2. Analyze error messages
  3. Fix incrementally
  4. Verify after each fix