The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python scripts to modify the local configuration file located at ~/.claude/settings.json. This is the primary method for updating the model aliases (haiku, sonnet, opus) to specific backend model identifiers.
[SAFE]: The operations are restricted to the agent's own configuration directory. No network requests are made, and the skill does not attempt to access or exfiltrate sensitive files such as SSH keys, environment variables containing secrets, or cloud provider credentials.
[SAFE]: The behavior of the code in both SKILL.md and scripts/model_config.py is consistent with the stated purpose of configuring model mappings, with no evidence of obfuscation or malicious redirection.

model-config