agent-memory-systems · git:20261111.00f9c40 · 2026-11-11 · sha256 73ffd491c358982e
agent-memory-systems git:20261111.00f9c40A
Immutable. This exact content never changes and is served at /api/v1/blob/73ffd491c358982e.
No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_dr4nb27rdmmlvmku/73ffd491c358982e95767eb26f106b17316dc880e83457bec97b5a710ee41b9b.json
Then /plugin install agent-memory-systems@markdownregistry-dr4nb27rdmmlvmku in Claude Code. It installs this exact version, the one graded A here, pinned to the commit it was graded at, and leaves it there.
--- name: agent-memory-systems description: Design tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sessions. metadata: aas-risk: safe aas-source: vibeship-spawner-skills (Apache 2.0) aas-date-added: '2026-02-27' --- # Agent Memory Systems Choose semantic records for facts/preferences, episodic records for events, and procedural records for reusable methods. Keep retrieval quality separate from storage volume and bind persistent access to verified identity. ## Procedure 1. Establish the actual task, authenticated tenant/user, permission to retain content, retention limits and existing store/model versions. 2. Read the guide's tenant-scoped contract and relevant storage/chunking sections. Select an adapter supported by the installed SDK; the guide's historical sketches are not deployable integrations. 3. Specify record IDs, source evidence, timestamps, namespace, retrieval limits and conflict/version policy. Preserve originals and propose consolidation without deletion. 4. Test cross-identity rejection, stale/conflicting records, bounded retrieval and failed writes with isolated fixtures. Benchmark retrieval against held-out questions before expanding storage. 5. Deliver the architecture and evidence-backed change plan, listing unresolved adapters and hosted cost/data destinations. Apply only the persistence or provider operations actually authorized. ## Detailed Guide Read [the detailed guide](references/detailed-guide.md) before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely. ## When to Use - Design memory namespaces and retention for an agent serving distinct tenants or users. - Diagnose retrieval of stale, conflicting or unauthorized conversation records. - Plan an embedding/store migration while preserving source records and verifying isolation. ## Example **Request:** “Our support agent forgets preferences between sessions. Design memory for two customer tenants without sharing their history.” **Output:** Load the tenant-scoped contract and background-extraction sections. Propose a semantic namespace per verified tenant/user, records with source IDs and revisions, and bounded retrieval. Retain conflicting preferences until the owner resolves them; include tests that tenant B cannot retrieve or consolidate tenant A records. Identify the existing persistent adapter and consent/retention evidence before any write. ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.