The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill uses npx to download and execute the @codevoyant/agent-kit package. This pattern allows for the execution of arbitrary code fetched from a remote registry at runtime.
[EXTERNAL_DOWNLOADS]: The skill fetches the @codevoyant/agent-kit package from the public npm registry during execution.
[COMMAND_EXECUTION]: The skill executes shell commands to perform memory indexing and suggests modifying CLAUDE.md to establish persistence for the tool across future sessions.
[PROMPT_INJECTION]: The skill performs a bulk dump of knowledge into the context without using boundary markers or sanitization, creating a surface for indirect prompt injection. Ingestion points: Team knowledge is loaded via output from an external tool. Boundary markers: Absent; instructions direct the agent to print output directly without reformatting. Capability inventory: The skill can execute shell commands and suggest file modifications. Sanitization: Absent; data is treated as a bulk dump.

mem-remember