mirror of
https://github.com/affaan-m/everything-claude-code.git
synced 2026-03-31 22:23:27 +08:00
d70bab85e3
- AGENTS.md: universal cross-tool file read by Claude Code, Cursor, Codex, and OpenCode - .cursor/: 15 hook events via hooks.json, 16 hook scripts with DRY adapter pattern, 29 rules (9 common + 20 language-specific) with Cursor YAML frontmatter - .codex/: reference config.toml, Codex-specific AGENTS.md supplement, 10 skills ported to .agents/skills/ with openai.yaml metadata - .opencode/: 3 new tools (format-code, lint-check, git-summary), 3 new hooks (shell.env, experimental.session.compacting, permission.ask), expanded instructions, version bumped to 1.6.0 - README: fixed Cursor section, added Codex section, added cross-tool parity table - install.sh: now copies hooks.json + hooks/ for --target cursor
60 lines
1.7 KiB
Markdown
60 lines
1.7 KiB
Markdown
---
|
|
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
|