context-builder
bởi igorls
Coding Agents & IDEsTóm tắt
Generate LLM-optimized codebase context from any directory using context-builder CLI.
Mô tả
Kỹ năng này làm gì
context-builder scans a local directory and generates a single structured markdown file from the codebase. Output is ordered by file relevance and supports AST-aware signature extraction to minimize token usage. Token budgeting, .gitignore awareness, and automatic directory exclusions are built in.
AST-aware signatures reduce context size by 80-90% compared to raw file dumps, making large codebases fit within model token limits without manual curation.
Khi nào nên dùng
- Feed an entire Rust codebase to an LLM for architecture review
- Onboard to an unfamiliar repo by generating a full project snapshot
- Extract only public API signatures before a code review session
- Generate incremental diffs after code changes to update LLM context
- Package a specific monorepo package for focused LLM analysis
Quy trình ví dụ
User asks: Generate a context file for my Rust project at /home/user/myapp for LLM code review
- 1
Run token count preview: context-builder -d /home/user/myapp --token-count
- 2
If over budget, scope to Rust and TOML files with a token cap
- 3
Run: context-builder -d /home/user/myapp -f rs,toml --max-tokens 120000 -y -o docs/context.md
- 4
Attach docs/context.md to the LLM prompt for architecture or bug analysis
docs/context.md containing relevance-ordered Rust and TOML files, capped at 120K tokens, ready for LLM input
Yêu cầu
- Rust toolchain (rustup + cargo, required to build context-builder from source)
Cài đặt
clawhub install igorls/context-builderChạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.