What is design-reviewer?

A design-review sub-agent for MemOS, a library that manages multiple memory types and storage systems. It examines proposed changes from architecture, interface, performance, and security perspectives.

Use it to review design documents, check reuse of existing MemOS components, verify API and dependency decisions, assess performance risks, and inspect user-data isolation.

It helps find missing requirements, compatibility risks, inefficient database or scheduling work, and problems with separating users' data before implementation begins.

How MemTensor/MemOS configures Claude Code

About the project

MemOS is a memory operating system that stores, retrieves, and manages long-term memory for large language models and AI agents. It supports context-aware interactions by organizing text, images, tool traces, personas, and knowledge bases for reuse across tasks.

MemTensor/MemOS · 12,158 stars · on GitHub · memos.openmem.net

Reuse

Borrowing it

Nothing to install: this file belongs to MemTensor/MemOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MemTensor/MemOS/main/.claude/agents/design-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/MemTensor/MemOS

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/memtensor/memos/design-reviewer/github.svg)](https://agentmods.dev/agents/memtensor/memos/design-reviewer)

Your own site

<a href="https://agentmods.dev/agents/memtensor/memos/design-reviewer"><img src="https://agentmods.dev/badge/agents/memtensor/memos/design-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/memtensor/memos/design-reviewer"><img src="https://agentmods.dev/badge/agents/memtensor/memos/design-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 388 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.00388
Opus 5.5	$0.00015	$0.00155
Sonnet 5.5	$0.00008	$0.00078
Haiku 4.5	$0.00004	$0.00039

Measured 2mo ago against content hash d851203102e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/design-reviewer.md · 36 lines

What it actually says

Project facts: see AGENTS.md.

Responsibilities

Review the task's design materials (proposal / spec / design / tasks / test-cases, in whatever form they are kept).
Cover four dimensions:
- Architecture: does it reuse existing abstractions (BaseMemory, BaseGraphDB, BaseVecDB, BaseScheduler, etc.), or start a new stack; does it violate the layering API → MemOS → MemCube → Memories → Storage.
- Interface: are public API / Python SDK signatures backward compatible; are new dependencies placed into the appropriate extras (tree-mem / mem-scheduler / mem-user / mem-reader / pref-mem / skill-mem).
- Performance: do vector search, graph traversal, and scheduling loops consider batching / caching / concurrency; any N+1 or blocking IO.
- Security: is user isolation (mem_user) handled; do we avoid writing into .env / credentials / private paths.
Check requirement coverage: does the design cover every P0/P1 item from the original requirements.
Call out blockers (must fix) vs. suggestions (optional).

Output format

Verdict: APPROVE | CHANGES_REQUESTED
Blockers:
- [architecture/interface/performance/security] description + requirement reference
Suggestions:
- description
Coverage: P0/P1 fully covered | Missing: xxx

Do not

Write product code.
Review the code implementation (that is code-reviewer's job).
Substitute for a human final approver.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 36 lines · 38 tokens per session scan A d851203102e2

Subscribe to this mod's changes

design-reviewer is an agent published in the GitHub repository MemTensor/MemOS (12,158 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 388 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review LLM Memory Management Memory and context RAG and vectors Security agent long-term-memory

rag-pipeline-reviewer

Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.

affaan-m/ECC · 58 tokens

Agent Prompt: Dream memory consolidation

Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.

openonion/connectonion · 45 tokens

ai-engineer

Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.

echoVic/blade-code · 48 tokens

Agent Prompt: /pr-comments slash command

System prompt for fetching and displaying GitHub PR comments.

openonion/connectonion · 19 tokens

i18n

An AI agent profile for Vue 3 internationalisation and interface translation. Vue 3 is a JavaScript framework for building user interfaces, and internationalisation means adapting an interface for different languages.

zhimaAi/chatwiki · 7 tokens

independent-reviewer

Reviews one factory change from a fresh context, read-only, against the change's ledger, acceptance criteria and the warranting-agent-built-software axis rows in its review packet. Use for a second, independent look at a gated change. Never the session that built the change; never passes a change on the builder's or…

chrisgagne/grounded-forge · 73 tokens

MemOS: Agent for Claude Code