The Agent Skills Directory

[SAFE]: The skill implements a legitimate workflow for context management and lesson persistence. No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected.
[COMMAND_EXECUTION]: The skill utilizes a local Python script scripts/context_percent.py to parse context usage data. This script is part of the skill's distribution, relies solely on the Python standard library, and performs no network operations.
[DATA_EXFILTRATION]: Although the helper script reads telemetry data from ~/.claude/statusline/context.json, this access is restricted to operational metrics (token usage percentages). No sensitive files, credentials, or personal data are accessed or transmitted.

high-tide