The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command using the claude CLI tool to launch background processes with generated summaries.
[PROMPT_INJECTION]: The skill serves as a vector for indirect prompt injection by summarizing current conversation data and using it as a system prompt for a new session.
Ingestion points: The skill ingests the entire conversation history and user-provided arguments as described in SKILL.md.
Boundary markers: There are no specific delimiters or markers defined to separate the generated summary from the new agent's system instructions.
Capability inventory: The skill possesses the ability to execute shell commands using the claude binary.
Sanitization: The instructions include a mandatory redaction step for sensitive information like API keys, passwords, and PII before passing data to the new agent.

claude-handoff