What is membank CLAUDE.md?

Project instructions for Membank, a monorepo containing several related packages for an AI memory system. A monorepo is one repository that holds multiple packages or applications, and Membank stores preferences, decisions, and learnings in a searchable database.

Use it when developing or maintaining Membank's core library, MCP server, command-line tool, or dashboard.

It explains the package dependencies and the required build order, reducing errors when changing one part of the system. It also lists the standard commands for installing, building, developing, linting, and type-checking the repository.

How draekien-industries/membank configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to draekien-industries/membank. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/draekien-industries/membank/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/draekien-industries/membank

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/draekien-industries/membank/claude-md/github.svg)](https://agentmods.dev/instructions/draekien-industries/membank/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/draekien-industries/membank/claude-md"><img src="https://agentmods.dev/badge/instructions/draekien-industries/membank/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/draekien-industries/membank/claude-md"><img src="https://agentmods.dev/badge/instructions/draekien-industries/membank/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,024 This file is loaded in full into every session.

When invoked 1,024 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01024	$0.01024
Opus 5	$0.00512	$0.00512
Sonnet 5	$0.00205	$0.00205
Haiku 4.5	$0.00102	$0.00102

Measured 2d ago against content hash 85e946d37c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

membank CLAUDE.md scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

Run any command scoped to one package with `--filter`:

CLAUDE.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Membank

LLM memory management system. Stores user preferences, corrections, decisions, and learnings in SQLite, queryable via semantic search. Distributed as an MCP server + CLI.

Monorepo structure

packages/
  core/       @membank/core      — DB, embeddings, query engine, dedup logic
  mcp/        @membank/mcp       — stdio MCP server (5 tools exposed to LLMs) + standalone membank-mcp bin
  cli/        @membank/cli       — CLI + npx entrypoint
  dashboard/  @membank/dashboard — web UI + standalone membank-dashboard bin

core has no workspace deps. mcp depends on core. cli depends on core and mcp. dashboard is independent of cli. Build order is enforced by Turborepo. After you make a change, run pnpm build to rebuild in the correct order.

Key commands

pnpm install          # install all workspace deps
pnpm build            # build all packages in dependency order
pnpm dev              # watch mode across all packages
pnpm lint             # biome check
pnpm lint:fix         # biome check --write
pnpm typecheck        # tsc --noEmit across all packages
pnpm clean            # remove all dist/ and *.tsbuildinfo

Run any command scoped to one package with --filter:

pnpm --filter @membank/core build
pnpm --filter @membank/cli dev

Tooling

Runtime: Node.js >=24, pnpm >=10 (managed via corepack)
Build: tsdown (Rolldown-based, replaces tsup)
Lint/format: Biome 2.x — single tool for both, no ESLint/Prettier
Git hooks: Lefthook pre-commit — biome check on staged files, plus scoped per-package test suites for any staged packages/<pkg>/**. test-core-integration runs with MEMBANK_INTEGRATION=true, exercising the real Claude Haiku agent — committing core changes is slow and needs network access.
Monorepo: Turborepo with pnpm workspaces

Conventions

The vector extension (sqlite-vec) is external in tsdown configs — not bundled. The SQLite driver is Node's built-in node:sqlite, which requires Node >=24.
TypeScript and lint rules: see .claude/rules/typescript.md

Read the full file on GitHub · 93 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.

2d ago Changed · +6 lines · +92 tokens per session 85e946d37c12
3d ago Changed · +1 lines · +14 tokens per session 6e7b428ec6fc
10d ago First seen · 86 lines · 918 tokens per session scan B dd5b3539c087

Subscribe to this mod's changes

membank CLAUDE.md is an instructions file published in the GitHub repository draekien-industries/membank (2 stars, last pushed 3d ago), licensed MIT. It adds 1,024 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

membank: Instructions file for Claude Code