The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to run a local script, node .gitnexus/run.cjs analyze, to perform repository analysis and update the knowledge graph (SKILL.md).
[COMMAND_EXECUTION]: The documentation describes the rename tool, which is capable of performing coordinated, multi-file modifications across the codebase (SKILL.md).
[PROMPT_INJECTION]: The skill interacts with external codebase data through various intelligence tools, creating an indirect prompt injection surface.
Ingestion points: Codebase symbols, execution flows, and file content are ingested into the GitNexus knowledge graph for use with tools like query and explain (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters to isolate ingested code content from agent instructions.
Capability inventory: The skill allows for file writes (via the rename tool) and subprocess execution (via the analyze command) (SKILL.md).
Sanitization: The skill documentation does not describe any sanitization or validation of the ingested code data.

gitnexus-guide