The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local shell script at ~/.claude/evolution/bin/evolve-status.sh and utilizes the grep utility to scan local files for status information.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from local files which could potentially contain instructions influencing the agent's behavior. 1. Ingestion points: Reads ~/.claude/evolution/stable/global.md and sessions.jsonl (SKILL.md). 2. Boundary markers: No specific boundary markers or 'ignore' instructions are present for the ingested data. 3. Capability inventory: The skill has the ability to execute bash commands and read from the user's home directory. 4. Sanitization: The skill does not explicitly sanitize the content of the files before displaying them to the user.

session-bootstrap