The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts to gather temporal metadata and analyze user prompts.
The capture_temporal_context.py script retrieves system-level information including the hostname, OS platform, and Python version using standard library modules (socket, platform).
It also accesses environment variables (e.g., LANG, TZ, LC_TIME) and the /etc/localtime file path to determine timezone and locale settings.
[DATA_EXFILTRATION]: While the skill accesses system metadata (hostname, platform version, and timezone configuration), this data is used locally to anchor the session's temporal context. No network operations or external transmissions were identified in the provided scripts.
[PROMPT_INJECTION]: The recency_guard.py script analyzes user-supplied prompts using regular expressions to detect keywords like "latest" or "today". This is used to determine if the agent should prioritize live verification. The skill does not contain instructions aimed at bypassing agent safety protocols or overriding core behaviors.

temporal-awareness