sourcegraph-search

## What I do I help you perform large-scale code analysis and discovery by searching Sourcegraph. I use the `src` CLI to execute precise queries that can match literal strings, regular expressions, or structural code patterns. I can filter results by repository, file type, language, commit history, and time ranges. I am particularly effective at finding usage examples, security vulnerabilities, deprecated patterns, and architectural inconsistencies across massive codebases. ## When to use me Use this skill when: - You need to search across a large codebase or multiple repositories for specific patterns, functions, or dependencies. - You need to find real-world usage examples of a function or API across many repositories. - You are auditing a codebase for security tokens, keys, or vulnerable dependencies. - You want to perform "structural search" to match code patterns regardless of whitespace or formatting (e.g., finding all try-catch blocks with empty catches). - You need to track recent changes or history using `type:diff` or `type:commit` (e.g., "what changed in the last week"). - You want to find projects that use specific dependencies (e.g., "who relies on `lodash` version 4.17.19"). - You need to identify repositories that are contributor-friendly (e.g., contain `CONTRIBUTING.md`). ## Instructions ### 1. Basic Search Execute searches using the `src search` command. **Always** use the `-json` flag to ensure the output is machine-readable and easy to parse. Enclose you...