The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the oma recap CLI and jq to read and process local conversation history records.
[PROMPT_INJECTION]: The skill processes untrusted historical conversation data which creates a surface for indirect prompt injection.
Ingestion points: Accesses conversation data from ~/.claude/history.jsonl and the output of oma recap --json.
Boundary markers: No delimiters are defined to separate ingested history content from the agent's system instructions.
Capability inventory: The skill writes summary reports in Markdown format to the .agents/results/recap/ directory.
Sanitization: No validation or sanitization of the input history content is mentioned.

oma-recap