token-efficiency 3

Context engineering and token optimization plugin for DeepSeek Harness (DSH): tool output filtering, context pruning and progressive skill disclosure for LLM coding agents

Generic stateless dialogue compression that mimics human memory — forgetting-curve bounded context for LLM conversations, with a ready-to-use adapter module for DeepSeek Harness (DSH).

DSH 对抗多智能体三层失效的防御插件：读取台账去重度量(read-ledger)、免疫压缩规则区+完成机械门禁(immutable-core+completion-gate)、低成本审查lane(role-router)。零外部依赖，注入即用。