Stop feeding agents their history: Google's SKILL.state cuts long-session tokens by 94%
Today's agent runtimes append every observation and trace to one ever-growing prompt, which is why long sessions slow down and eventually poison themselves. Google's SKILL.state reverses that: at each step the model sees only the skill spec, a compact mutable execution state, and the latest observation, and intermediate reasoning is thrown away the moment it produces a validated state update. The result is better task accuracy with roughly 94% less cumulative token usage across models and environments. If context growth is your agent's real bottleneck, this is the architecture to steal.