attack-shape

# Attack shape ## Contract | Field | Bound contract | |---|---| | Trigger | User wants adversarial stress-testing of an architecture, structure, or shape. Either the agent attacks and the human defends, or the agent proposes and the human attacks. | | Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. The agent emits chat output only. | | Side effect | An attack or proposal transcript in chat, plus the surviving or broken shape recorded in chat. | | Done | The shape has been attacked from both directions, the human has defended or attacked, and the surviving shape (or non-converged record) is recorded. | ## Inputs The proposed architecture, structure, or shape to test. The human must supply it as text, a diagram description, or a reference to an artifact already in context. Without it the skill stops. Optional: named attack axes the human wants prioritized (coupling, abstraction depth, failure modes, scalability, ownership boundaries). Optional: a scope limit naming what is out of bounds for the attack. Optional: constraints, scale, existing components, and non-goals for a proposal round. A human participant must be present; the skill does not converge without one. ## Procedure 1. Restate the target shape from the supplied input and confirm scope with the human before attacking or proposing. Do not test material outside the stated scope. Done when: the shape is restated and scope is confirmed. 2. Determine the direction....