← ClaudeAtlas

memorylisted

Use durable Patcher memory when prior project knowledge or cross-project user preferences can improve the current task, and save durable new learning through the Patcher memory CLI.
laruss/patcher-browser · ★ 0 · AI & Automation · score 64
Install: claude install-skill laruss/patcher-browser
# Patcher memory This plugin is provider-independent. Recommend disabling provider-native memory under Settings → Providers to avoid duplicated or conflicting stores. The memory plugin automatically injects a compact index of global memories and memories for the current Patcher project. The index contains summaries only. ## Retrieve progressively When a memory summary may be relevant, inspect it instead of guessing: 1. Search with `patcher memory search "<query>" --scope all --json`. 2. Read the selected record with `patcher memory get <id> --scope all --json`. 3. Treat remembered facts as potentially stale. Verify drift-prone facts when doing so is cheap or consequential. Do not load every memory. Stop after the relevant records are clear. ## Save durable learning The agent may proactively write memory when information is likely to help in a future thread and is costly or error-prone to rediscover. Use project scope for repository-specific information: - commands, conventions, architecture decisions, paths, and environments; - project-specific user preferences; - verified quirks, failure causes, and reusable workarounds. Use global scope only for broadly applicable information: - user identity, communication preferences, and general workflow habits; - preferences that clearly apply across repositories; - stable cross-project operating conventions. When scope is ambiguous, use project scope. Global scope must be explicit. Create a memory with: ```bash patche