review

review is a command for Claude Code from Matt-Dionis/claude-code-configs. It costs 8 tokens per session (1,032 once invoked), scanned A, original, MIT.

A code-review command for a Memory MCP Server, a server that gives AI clients tools for storing and searching information. It checks security, MCP protocol compliance, and the correctness of memory and vector-search behavior.

In plain words
What is it for?
Use it to review server code, database queries, access controls, tool definitions, error handling, embeddings, indexes, and memory expiration or archival logic.
Why use it?
It helps find unsafe data separation, injection risks, invalid protocol messages, authentication problems, and errors in how memories are stored or searched.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/matt-dionis/claude-code-configs/review
Clone the repo
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configs

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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/review.svg)](https://agentmods.dev/commands/matt-dionis/claude-code-configs/review)
Your own site
<a href="https://agentmods.dev/commands/matt-dionis/claude-code-configs/review"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.01032
Opus 5 $0.00004 $0.00516
Sonnet 5 $0.00002 $0.00206
Haiku 4.5 $0.00001 $0.00103

Measured 6d ago against content hash bfa1f865f2a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

review 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 6d 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.

configurations/mcp-servers/memory-mcp-server/.claude/commands/review.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory MCP Server Code Review

Perform a comprehensive review of $ARGUMENTS with focus on MCP protocol compliance and memory system integrity:

Critical Security & Safety

  • Data Isolation: Verify companion/user boundary enforcement
  • SQL Injection: Check all database queries for parameterization
  • Embedding Leakage: Ensure vector data doesn't cross tenant boundaries
  • Auth Tokens: Validate secure storage and transmission
  • API Keys: Check for hardcoded credentials (OpenAI, Neon)
  • Session Hijacking: Review session management implementation

MCP Protocol Compliance

  • JSON-RPC 2.0: Validate message format compliance
  • Error Codes: Use standard MCP error codes (-32700 to -32603)
  • Tool Registration: Verify proper tool manifest structure
  • Parameter Validation: Check Zod schemas match MCP expectations
  • Response Format: Ensure consistent response structure
  • Streaming Support: Validate partial result handling

Memory System Integrity

  • Vector Dimensions: Ensure consistent embedding dimensions (1536 for OpenAI)
  • Index Configuration: Review IVFFlat/HNSW parameters
  • Memory Lifecycle: Check expiration and archival logic
  • Consolidation Rules: Validate memory merging algorithms
  • Importance Scoring: Review decay and update mechanisms
  • Deduplication: Check for duplicate memory prevention

Performance Optimization

  • N+1 Queries: Identify and fix database query patterns
  • Vector Search: Optimize similarity thresholds and limits
  • Index Usage: Verify proper index hints and scans
  • Connection Pooling: Check pool size and timeout settings
  • Batch Operations: Look for opportunities to batch DB operations
  • Caching Strategy: Review memory and query result caching

Database & Schema

  • Migration Safety: Check for backward compatibility
  • Transaction Boundaries: Verify ACID compliance
  • Deadlock Prevention: Review lock ordering
  • Foreign Keys: Ensure referential integrity
  • Soft Deletes: Validate is_archived handling
  • Timestamps: Check timezone handling

Read the full file on GitHub · 148 lines

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.

  1. 6d ago First seen · 148 lines · 8 tokens per session scan A bfa1f865f2a5

Subscribe to this mod's changes

review is a command published in the GitHub repository Matt-Dionis/claude-code-configs (625 stars, last pushed 1y ago), licensed MIT. It adds 8 tokens to every session and 1,032 once invoked, about $0.0000 per session on Opus 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.