The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a bash command that appends execution telemetry (timestamp, skill name, workflow, status) to a local JSONL file at ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl. This operation uses shell command substitution for dynamic timestamp generation.
[PROMPT_INJECTION]: The skill ingests user-provided problem statements and context, which represents a potential surface for indirect prompt injection attacks. Ingestion points: Problem/Request and Context inputs processed in Workflows/Explore.md. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the input data. Capability inventory: The skill possesses capabilities to write to the local filesystem via shell logging and to manage tasks using tool calls (TaskCreate, TaskUpdate). Sanitization: No explicit sanitization or filtering of input content is specified in the workflow logic.

IterativeDepth