agent-operating-contract-evolution

原文涵盖的主题

• Agent Operating Contract Evolution Skill
• When to Use
• Core Principle
• Instruction files are read by a model, not by a person
• Measure the real per-turn prompt before optimizing
• Behavioral regression, not just coverage
• Layering is necessary but NOT sufficient — check what actually loads
• Ownership and routing rules are storage facts — verify before you write

Use this when the owner asks to optimize, review, evolve, or refactor an agent's identity file, operating protocol, team-agent definitions, a runtime operating contract, or a user-owned repo whose product IS an agent contract / control-plane system (research control planes, orchestration harnesses, evidence pipelines). This skill is for class-level agent behavior design, not one-off task notes. Trigger on requests like: "evolve your soul" "review all identity files" / "review the profile identities" / "audit every identity file" "review the operating protocol" "optimize your agent definition" "make the team agents work better" "reduce blocking / work async" "keep files organized" "review / optimize / improve this system" where the target is a user-owned repo whose product is an agent contract or control plane (research systems, orchestration harnesses, evidence pipelines) "unify the scattered per-project scripts" / "retire the old scripts" / "make this portable across harnesses" on such a repo — load the refactor playbook reference before executing "deprecate the legacy agent file, use the new kernel" — kernel flips on any repo an agent reads "make this repo self-contained" / "move

这里只展示节选，请以完整原文和当前要求为准。