serena-memory-synclisted

# Serena Memory Sync ## Purpose Keep `.serena/` useful for future Claude Code, Codex, and other GPT-based agent sessions without creating hallucinated project lore. Memories must explain what the code actually does, where it lives, how it behaves, which invariants matter, and how to safely change and verify the area. User-facing conversation stays in Russian. All stored `.serena/` knowledge files are written in English. ## When To Use Use this skill without waiting for explicit invocation when: - Meaningful code, plugin, workflow, architecture, design-system, security, integration, or configuration behavior changed. - A Stop hook, commit-like action, or stale-memory marker indicates project knowledge should be synchronized. - Durable facts were discovered while making or verifying project changes, and those facts are now encoded in code, configuration, workflow files, committed docs, or stable tests. - `.serena/memories`, `.serena/plans`, or `.serena/research` may be stale or need a fact-only audit. - A future Claude Code, Codex, or GPT-based agent session would need verified source-of-truth paths, invariants, contracts, entry points, or verification commands to implement confidently. Do not auto-invoke this skill for read-only context discovery, log/server audits, report-only reviews, exploratory debugging, or current-status snapshots unless the user explicitly asked to update/synchronize memories or a Stop/stale-memory hook requires it. In those read-only workflows,