The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the rp-cli tool. These commands are localized to codebase exploration tasks such as tree, structure, search, and read. All operations are within the expected scope of a codebase analysis tool.
[DATA_EXFILTRATION]: While the skill includes commands to export context (context --all > output.md), these are directed to local files for the user's benefit and do not show patterns of sending data to external, unauthorized servers.
[SAFE]: All referenced tools and workflows are consistent with the stated purpose of token-efficient codebase exploration. There are no detections of prompt injection, obfuscation, or persistence mechanisms.

flux-opencode-rp-explorer