mirror of https://github.com/affaan-m/everything-claude-code.git synced 2026-02-15 02:43:20 +08:00

Files

Affaan Mustafa 261332dc50 feat: add Cursor IDE support with pre-translated configs

Add complete .cursor/ directory with rules, agents, skills, commands,
and MCP config adapted for Cursor's format. This makes ecc-universal
a truly cross-IDE package supporting Claude Code, Cursor, and OpenCode.

- 27 rule files with YAML frontmatter (description, globs, alwaysApply)
- 13 agent files with full model IDs and readonly flags
- 30 skill directories (identical Agent Skills standard, no translation)
- 31 command files (5 multi-* stubbed for missing codeagent-wrapper)
- MCP config with Cursor env interpolation syntax
- README.md and MIGRATION.md documentation
- install.sh --target cursor flag for project-scoped installation
- package.json updated with .cursor/ in files and cursor keywords

2026-02-11 02:31:52 -08:00

1.7 KiB

Raw Blame History

description, alwaysApply

description	alwaysApply
Performance optimization: model selection strategy, context window management, extended thinking	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 4.5 (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

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:

Ensure extended thinking is enabled (on by default)
Enable Plan Mode for structured approach
Use multiple critique rounds for thorough analysis
Use split role sub-agents for diverse perspectives

Build Troubleshooting

If build fails:

Use build-error-resolver agent
Analyze error messages
Fix incrementally
Verify after each fix

1.7 KiB Raw Blame History