The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the user to execute node .gitnexus/run.cjs analyze in the terminal to refresh the codebase index when it becomes stale. This refers to a local script within the project's own directory structure.
[DYNAMIC_EXECUTION]: The skill describes a cypher tool that executes raw graph queries against the repository's knowledge graph to perform advanced code intelligence tasks.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external codebase data through various tools and MCP resources, creating a surface for indirect prompt injection.
Ingestion points: Codebase metadata and symbol information are retrieved via gitnexus:// URI resources and tool outputs like query and context (SKILL.md).
Boundary markers: The documentation does not specify explicit delimiters or "ignore" instructions for the agent when processing repo data.
Capability inventory: The skill leverages tools capable of multi-file refactoring (rename), data flow analysis (explain), and graph querying (cypher).
Sanitization: No explicit sanitization or validation logic for the ingested repository content is detailed in this guide.

gitnexus-guide