A persistent-memory system that stores project observations, decisions, problems, and other learnings in a portable file.

It helps search past discoveries, ask questions about earlier decisions, view recent memories, and inspect memory statistics.

It helps retain useful project context between sessions instead of starting from memory each time.

memory — Skill by memvid

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 skills/memvid/claude-brain/memory

Any agent

npx skills add memvid/claude-brain --skill memory

Clone the repo

git clone --depth 1 https://github.com/memvid/claude-brain

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 551 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.

Model	Per session	Once invoked
Fable 5	$0.00021	$0.00551
Opus 5	$0.00010	$0.00275
Sonnet 5	$0.00004	$0.00110
Haiku 4.5	$0.00002	$0.00055

Measured 3d ago against content hash bcb7bc164eb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mind — 95% identical, 2 lines differ

skills/memory/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Mind

You have access to a persistent memory system powered by Claude Mind. All your observations, discoveries, and learnings are stored in a single .claude/mind.mv2 file.

How to Execute Memory Commands

Use the bundled SDK scripts via Node.js (NOT the CLI). The scripts are at ${CLAUDE_PLUGIN_ROOT}/dist/scripts/.

Search Memories

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "<query>" [limit]

Examples:

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "authentication" 5
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/find.js" "database schema" 10

Ask Questions

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "<question>"

Examples:

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "Why did we choose React?"
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/ask.js" "What was the CORS solution?"

View Statistics

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/stats.js"

View Recent Memories

node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/timeline.js" [count]

Memory Types

Memories are automatically classified into these types:

discovery - New information discovered
decision - Important decisions made
problem - Problems or errors encountered
solution - Solutions implemented
pattern - Patterns recognized in code/data
warning - Warnings or concerns noted
success - Successful outcomes
refactor - Code refactoring done
bugfix - Bugs fixed
feature - Features added

File Location

Your memory is stored at: .claude/mind.mv2

This file is:

Portable - Copy it anywhere, share with teammates
Git-friendly - Commit to version control
Self-contained - Everything in ONE file
Searchable - Instant semantic search

Usage Tips

Start of session: Recent memories are automatically injected as context
During coding: Observations are captured automatically from tool use
Searching: Use natural language queries to find relevant past context
Sharing: Send the .mind.mv2 file to teammates for instant onboarding

Read the full file on GitHub · 72 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.

3d ago First seen · 72 lines · 21 tokens per session scan A bcb7bc164eb2

Subscribe to this mod's changes

memory is a skill published in the GitHub repository memvid/claude-brain (574 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 551 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 2026-08-30.

Memory and context ai-tools anthropic claude claude-agents claude-ai claude-code

memory

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

Claude Mind

How to Execute Memory Commands

Search Memories

Ask Questions

View Statistics

View Recent Memories

Memory Types

File Location

Usage Tips

What this file has done since we first saw it

Other skills, from other repositories

golden-chat

golden-epub

golden-html-multi

golden-pdf

golden-man

golden-man-single