The Agent Skills Directory

[SAFE]: The skill provides instructional logic for an ownership management workflow ('claiming') that emphasizes validation and authorization before performing actions.
[SAFE]: Access is restricted to specific project configuration files (.and/config.yml) and a controlled backend contract (and-backend-contract), which is standard for specialized tooling.
[SAFE]: The use of disable-model-invocation: true in the frontmatter serves as a safety constraint that prevents the model from autonomously calling tools unless explicitly handled by the platform.
[SAFE]: The instructions explicitly forbid the agent from overriding ownership or releasing claims without explicit approval, reducing the risk of unauthorized state changes.

and-claim