💡 Usage Tips

16 documents in this category

Model Selection Guide
Understand the characteristics and applicable scenarios of different AI models to make the best choice.
Updated
Cost Optimization Guide
Master Claude Code's cost control techniques to accomplish more with fewer tokens
Updated
Context Management
Understanding and managing Claude Code's context window, and effectively using commands like /compact and /clear
Updated
CLAUDE.md Configuration Guide
Using CLAUDE.md to provide Claude Code with project context and coding conventions
Updated
AGENTS.md Configuration Guide
AGENTS.md is Codex's project configuration file -- define your AI coding assistant's behavior rules, similar to Claude Code's CLAUDE.md
Updated
CLI Tips
34 practical Claude Code CLI tips to boost your development efficiency
Updated
Best Practices
Best practices for efficient Claude Code usage, a comprehensive guide from project initialization to team collaboration
Updated
Workflow Tips
Efficient Claude Code development workflows to boost team productivity
Updated
Dynamic Workflows
Use Claude Code's Dynamic Workflows to orchestrate dozens to hundreds of background sub-agents for repo-wide review, migration, and research — works through QCode
Updated
Output formats: json / text / stream-json
Use claude -p's --output-format to handle Claude Code output in scripts and CI — structured json parsing, real-time stream-json event streams, default plain text, with jq and pipe recipes
Updated
Permission Configuration
Configure Claude Code's permission modes to control which operations require human confirmation
Updated
Adaptive Thinking Configuration Guide
Adaptive thinking on Claude Opus 4.8 / Sonnet 4.6 / Haiku 4.5: thinking + effort parameters, differences from the legacy budget_tokens, and quality vs. cost trade-offs
Updated
Chinese Models
Call GLM / Kimi / DeepSeek / Qwen with the same QCode.cc cr_ key: current ids on sale, protocol paths, a curl self-test, and pairing with the Claude 5 family
Updated
Image Input (Vision)
Feed images to Claude Code: paste, drag-and-drop, or reference a file path so the model can read screenshots, mockups, architecture diagrams, and charts. Powered by QCode.cc vision models — one API Key works across every endpoint.
Updated
gpt-image-2 Image Generation and Editing
OpenAI-compatible gpt-image-2 text-to-image + image-edit API: drop in by switching base_url, multi-region endpoints, unified billing with your QCode key
Updated
Use QCode with 9router
Add QCode.cc as a custom provider in 9router, a local multi-provider router, for cross-provider fallback and unified management
Updated
← Back to docs hub