search

search is a command for coding agents from memvid/claude-brain. It costs 7 tokens per session (170 once invoked), scanned A, original, MIT.

A command for searching Claude’s persistent memories by words or phrases.

In plain words
What is it for?
Use it to find stored memories about topics such as authentication, database schemas, or API errors, with matching context and relevance scores.
Why use it?
It avoids manually looking through the memory file when you need a past decision, fact, or discussion.

Command

Part of the claude-brain plugin — 2 skills, 4 commands, 3 hooks shipped together

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/memvid/claude-brain/search
Clone the repo
git clone --depth 1 https://github.com/memvid/claude-brain

Or install claude-brain, the plugin that ships this one along with the rest of its 2 skills, 4 commands, 3 hooks.

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 search

README.md
[![agentmods](https://agentmods.dev/badge/commands/memvid/claude-brain/search.svg)](https://agentmods.dev/commands/memvid/claude-brain/search)
Your own site
<a href="https://agentmods.dev/commands/memvid/claude-brain/search"><img src="https://agentmods.dev/badge/commands/memvid/claude-brain/search.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 170 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 $0.00007 $0.00170
Opus 5 $0.00003 $0.00085
Sonnet 5 $0.00001 $0.00034
Haiku 4.5 $0.00001 $0.00017

Measured 3d ago against content hash 4462e06eb3aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

commands/search.md · 27 lines

What it actually says

Search through Claude's persistent memories for specific content, patterns, or keywords.

Usage: /mind:search <query> [limit]

Execute the search script with user's query:

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "$ARGUMENTS" 10

Examples

  • /mind:search authentication - Find memories related to authentication
  • /mind:search "database schema" - Search for exact phrase
  • /mind:search API errors - Find memories about API errors

Response Format

  • Show matching memories with relevance scores
  • Include timestamps (convert to human-readable format)
  • Highlight matched keywords in context
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. 3d ago First seen · 27 lines · 7 tokens per session scan A 4462e06eb3aa

Subscribe to this mod's changes

search is a command published in the GitHub repository memvid/claude-brain (574 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 170 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.