The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown files that provide documentation and step-by-step workflows for using Sourcegraph search tools. It does not include any executable scripts, binaries, or configuration files that could be used for malicious purposes.
[SAFE]: The search patterns provided in files like query-patterns.md and examples/common-searches.md follow standard developer practices for code exploration and are intended to help the agent find relevant implementation details within a codebase.
[SAFE]: All tool references (e.g., sg_keyword_search, sg_read_file, sg_deepsearch_read) are standard Model Context Protocol (MCP) functions provided by Sourcegraph for code analysis.
[SAFE]: No evidence of prompt injection, obfuscation, data exfiltration, or unauthorized command execution was found in the provided files.

searching-sourcegraph