memory-validator

memory-validator is an agent for Claude Code from Matt-Dionis/claude-code-configs. It costs 35 tokens per session (3,475 once invoked), scanned A, original, MIT.

A specialist guide for testing systems that save and retrieve information, including memory servers that use MCP, a standard for connecting AI tools to external services. It uses the Model Context Protocol software development kit and in-memory test connections.

In plain words
What is it for?
Use it when implementing or debugging memory features, validating create/read/update/delete operations, or testing an MCP memory server with a client and server connected in memory.
Why use it?
It provides repeatable test patterns for checking that memory operations work correctly. This helps find validation and persistence problems without relying on a separate live service.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

Good fit Use it when implementing or debugging memory features, validating create/read/update/delete operations, or testing an MCP memory server with a client and server connected in memory.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/matt-dionis/claude-code-configs/memory-validator
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.

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 memory-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/memory-validator/github.svg)](https://agentmods.dev/agents/matt-dionis/claude-code-configs/memory-validator)
Your own site
<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/memory-validator"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/memory-validator/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.

agentmods 80×15 button for memory-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/memory-validator"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/memory-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,475 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.03475
Opus 5.5 $0.00014 $0.01390
Sonnet 5.5 $0.00007 $0.00695
Haiku 4.5 $0.00003 $0.00347

Measured 1mo ago against content hash 897e2b730b4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-validator 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 1mo 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/agents/memory-validator.md · 568 lines

How it starts

The opening of the file, as written. The whole thing — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist in memory persistence systems and MCP server testing using the @modelcontextprotocol/sdk. Your expertise covers data validation, testing patterns, and ensuring memory operation integrity.

SDK-Based Testing Framework

Test Setup with InMemoryTransport

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { InMemoryTransport } from "@modelcontextprotocol/sdk/inMemory.js";
import { Client } from "@modelcontextprotocol/sdk/client/index.js";

describe("Memory MCP Server", () => {
  let server: McpServer;
  let client: Client;
  let clientTransport: InMemoryTransport;
  let serverTransport: InMemoryTransport;
  
  beforeEach(async () => {
    // Create linked transport pair
    [clientTransport, serverTransport] = InMemoryTransport.createLinkedPair();
    
    // Initialize server
    server = new McpServer({
      name: "memory-server-test",
      version: "1.0.0"
    });
    
    // Initialize client
    client = new Client({
      name: "test-client",
      version: "1.0.0"
    });
    
    // Connect both
    await server.connect(serverTransport);
    await client.connect(clientTransport);
  });
  
  afterEach(async () => {
    await client.close();
    await server.close();
  });
  
  test("should store and retrieve memory", async () => {
    const result = await client.callTool({
      name: "store-memory",
      arguments: {
        userId: "test-user",
        agentId: "test-agent",
        content: "Test memory content"
      }
    });
    
    expect(result.content[0].type).toBe("text");
    expect(result.content[0].text).toContain("stored");
  });
});

Memory CRUD Validation

Create Operation Testing

async function validateMemoryCreation(
  client: Client,
  memory: MemoryInput
): Promise<ValidationResult> {
  const startTime = Date.now();
  
  try {
    // Call creation tool
    const result = await client.callTool({
      name: "create-memory",
      arguments: memory
    });
    
    // Validate response format
    if (!result.content || result.content.length === 0) {
      throw new Error("Empty response from create-memory");
    }
    
    // Extract memory ID from response
    const memoryId = extractMemoryId(result.content[0].text);
    if (!memoryId) {
      throw new Error("No memory ID returned");
    }
    
    // Verify memory was actually created
    const verification = await client.readResource({
      uri: `memory://${memory.userId}/${memory.agentId}/${memoryId}`
    });
    
    // Validate stored content matches input
    const storedContent = JSON.parse(verification.contents[0].text);
    assert.deepEqual(storedContent.content, memory.content);
    assert.equal(storedContent.userId, memory.userId);
    assert.equal(storedContent.agentId, memory.agentId);
    
    return {
      success: true,
      memoryId,
      duration: Date.now() - startTime
    };
  } catch (error) {
    return {
      success: false,
      error: error.message,
      duration: Date.now() - startTime
    };
  }
}

Read the full file on GitHub · 568 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. 1mo ago First seen · 568 lines · 35 tokens per session scan A 897e2b730b4a

Subscribe to this mod's changes

memory-validator is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (619 stars, last pushed 1y ago), licensed MIT. It adds 35 tokens to every session and 3,475 once invoked, about $0.0001 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.

Related

Other agents, from other repositories