mem:search

mem:search is a command for Claude Code from Xsaven/vector-memory-mcp. It costs 10 tokens per session (871 once invoked), scanned A, original, MIT.

A command for finding saved memories by meaning rather than only exact words. It also accepts category, tag, result-count, and offset filters.

In plain words
What is it for?
Use it to search stored development knowledge, decisions, or notes such as authentication patterns, APIs, or framework solutions.
Why use it?
It helps locate related notes when you do not remember their exact wording.

Command for Claude Code

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/xsaven/vector-memory-mcp/search
Clone the repo
git clone --depth 1 https://github.com/Xsaven/vector-memory-mcp

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 mem:search

README.md
[![agentmods](https://agentmods.dev/badge/commands/xsaven/vector-memory-mcp/search.svg)](https://agentmods.dev/commands/xsaven/vector-memory-mcp/search)
Your own site
<a href="https://agentmods.dev/commands/xsaven/vector-memory-mcp/search"><img src="https://agentmods.dev/badge/commands/xsaven/vector-memory-mcp/search.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 871 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 $0.00010 $0.00871
Opus 5 $0.00005 $0.00436
Sonnet 5 $0.00002 $0.00174
Haiku 4.5 $0.00001 $0.00087

Measured 2d ago against content hash 2cc94b1de4b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mem:search 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 2d 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/commands/mem/search.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Input

STORE-AS($RAW_INPUT = $ARGUMENTS) STORE-AS($SEARCH_QUERY = {search query extracted from $RAW_INPUT})

Role

Semantic memory search utility that queries vector storage with optional filters and displays formatted results with similarity scores.

Workflow step1

STEP 1 - Parse Arguments for Query and Filters

  • format-1: Simple query: /mem:search "authentication patterns"
  • format-2: With filters: /mem:search query="auth" category=code-solution limit=20
  • format-3: With tags: /mem:search query="api" tags=laravel,php
  • extract: STORE-AS($QUERY = {parse query from $RAW_INPUT, required})
  • filters: STORE-AS($FILTERS = {parse category?, limit?, offset?, tags? from $RAW_INPUT})
  • defaults: Defaults: limit=10, offset=0
  • output: STORE-AS($PARAMS = {query: $QUERY, ...$FILTERS})

Workflow step2

STEP 2 - Execute Semantic Search

  • search: mcp__vector-memory__search_memories('STORE-GET($PARAMS)')
  • store: STORE-AS($RESULTS = search results array)

Workflow step3

STEP 3 - Handle Empty Results

  • check: IF(STORE-GET($RESULTS) is empty) → Display: "No memories found for: {query}" → Suggest: "Try broader search terms" → Suggest: "Remove category/tag filters" → Suggest: "Use /mem:list to see recent memories" → END-IF

Workflow step4

STEP 4 - Format and Display Results

  • header: Display: "--- Memory Search Results ---"
  • meta: Display: "Query: {query} | Found: {count} | Category: {category or all}"
  • list: FOREACH(memory in STORE-GET($RESULTS)) → Display: "#{id} [{category}] (similarity: {score})" → Display: " {content_preview} (first 100 chars)" → Display: " Tags: {tags} | Accessed: {access_count}x" → END-FOREACH
  • pagination: IF(more results available (total > limit + offset)) → Display: "More results available. Use offset={next_offset} to see more" → END-IF

Read the full file on GitHub · 79 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. 2d ago First seen · 79 lines · 10 tokens per session scan A 2cc94b1de4b4

Subscribe to this mod's changes

mem:search is a command published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 871 once invoked, about $0.0001 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 2026-09-01.