The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a vendor-provided library netclaw_tokens located in src/netclaw_tokens/. No arbitrary shell commands or remote code execution patterns were detected.
[CREDENTIALS_UNSAFE]: The skill utilizes the ANTHROPIC_API_KEY environment variable. This is a documented, standard credential for the host platform used as intended for token counting via the Anthropic API.
[PROMPT_INJECTION]: The skill contains instructions for the agent to append a mandatory footer to its responses. These instructions are consistent with the utility's purpose and do not attempt to bypass safety guidelines or override core agent behavior.

token-tracker