Mb Init logo

Mb Init

Community
mrvladd-d
mb-init

Create the Memory Bank skeleton and project command proxies in the current repository.

Overview

Publishermrvladd-d
Repositorymemobank
Skill namemb-init
Stars
56
Forks
11
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mrvladd-d on GitHub. Read the source before you install it.

Installation

Install the Mb Init AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mrvladd-d/memobank/tree/main/skills/mb-init
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mrvladd-d/memobank.git /tmp/memobank
mkdir -p .claude/skills
cp -r /tmp/memobank/skills/mb-init .claude/skills/mb-init
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mb Init in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mb Init on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mb Init is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

mb-init — Initialize Memory Bank skeleton

  • What it does: creates the base folders, core docs, and project-native command proxies.
  • Use it when: you want the skeleton only, without immediately choosing PRD or brownfield mapping.
  • Input: repository root.
  • Output: .memory-bank/, .tasks/, .protocols/, AGENTS.md, and generated command stubs.

Goal

Create a consistent baseline so agents can work with repo-local context instead of ad-hoc prompts.

Steps

1) Create directories

Create (if missing):

  • .memory-bank/ with subfolders (see ./references/shared-structure-template.md)
  • .tasks/
  • .protocols/

2) Create core Memory Bank files

From templates, create:

  • AGENTS.md
  • CLAUDE.md → symlink/copy to AGENTS.md
  • .memory-bank/index.md
  • .memory-bank/constitution.md
  • .memory-bank/mbb/index.md
  • .memory-bank/spec-index.md
  • .memory-bank/glossary.md
  • .memory-bank/invariants.md
  • .memory-bank/product.md
  • .memory-bank/requirements.md
  • .memory-bank/schemas/task.schema.json
  • .memory-bank/tasks/index.json
  • .memory-bank/testing/index.md
  • .memory-bank/skills/index.md

Fresh PRD-less bootstrap must not create .memory-bank/features/FT-001-*.md, .memory-bank/tasks/TASK-001.task.json, or any other fake roadmap artifact. .memory-bank/tasks/index.json starts as { "version": 1, "tasks": [] }; /write-prd creates a clarified PRD, /spec-init prepares only the lightweight SDD route map, /prd creates real features, mandatory /spec-design creates a minimal or full backbone gate, /spec-improve FT-<NNN> completes or marks unnecessary feature design, and /prd-to-tasks FT-<NNN> creates real TASK-*.task.json records after that. /clarify-feature FT-<NNN> is optional for explicitly pending/blocked features.

Also create optional folders that support the richer normative layer without making it mandatory:

  • .memory-bank/contracts/
  • .memory-bank/states/
  • .memory-bank/runbooks/

3) Create command stubs

So links from AGENTS.md are not broken, create minimal docs under .memory-bank/commands/. Use ./references/shared-commands-*.md:

  • mb.md
  • analysis.md
  • brainstorm.md
  • brief.md
  • constitution.md
  • write-prd.md
  • spec-init.md
  • prd.md
  • spec-design.md
  • spec-improve.md
  • spec-auto.md
  • clarify-feature.md
  • prd-to-tasks.md
  • execute.md
  • verify.md
  • red-verify.md
  • autopilot.md
  • autonomous.md
  • map-codebase.md
  • discuss.md
  • add-tests.md
  • review.md
  • find-skills.md

4) Create native skills (proxy commands)

Create thin proxy skills for each command so they work natively across runtimes:

  • .claude/skills/<name>/SKILL.md → Claude Code + OpenCode
  • .agents/skills/<name>/SKILL.md → Codex CLI + OpenCode

Each proxy contains: Read and follow the instructions in .memory-bank/commands/<name>.md. This registers commands natively: /mb in Claude Code, $mb in Codex, /mb in OpenCode.

The init-mb.js script creates both sets automatically.

Agents must read .memory-bank/constitution.md early during priming. It records project governing principles and does not replace .memory-bank/invariants.md, .memory-bank/contracts/*, or .memory-bank/spec-index.md; use /constitution only to create or amend those principles.

5) Enforce MBB rules immediately

  • Every .memory-bank/**/*.md must have frontmatter (description, status).

Optional fast path

If Node.js is available, you may run the helper script (safe: doesn’t overwrite existing files):

bash
# Option A: copy ./scripts/shared-init-mb.js into your repo then run:
node scripts/init-mb.js

If you don’t want a script, just create the files manually using the templates.

Definition of done

  • AGENTS.md exists and points to .memory-bank/index.md.
  • CLAUDE.md exists and mirrors AGENTS.md.
  • .memory-bank/ has the seeded docs.
  • .memory-bank/constitution.md exists as the governing-principles doc and /constitution is available in .memory-bank/commands/.
  • .memory-bank/tasks/index.json and .memory-bank/schemas/task.schema.json exist; task state is JSON-backed.
  • .memory-bank/tasks/index.json has an empty tasks array in a PRD-less skeleton.
  • Skeleton bootstrap creates no fake feature docs; task planning starts later with /write-prd, /spec-init, /prd, mandatory /spec-design, /spec-improve FT-<NNN>, then /prd-to-tasks FT-<NNN>.
  • No .memory-bank/tasks/TASK-001.task.json is created by bootstrap.
  • Future task records must contain mandatory tier: T0|T1|T2|T3; routing is only through task.tier, not the removed risk / risk.level model.
  • .memory-bank/commands/ has stub command docs.
  • .tasks/ and .protocols/ exist.

Frequently asked questions

What does the Mb Init AI skill do?

Create the Memory Bank skeleton and project command proxies in the current repository.

Why use Mb Init on TypingMind?

Because you install it once and use it with any model. Mb Init is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mb Init in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mrvladd-d/memobank/tree/main/skills/mb-init. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mb Init?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mb Init?

As many as you like. As long as a model supports skills, you can use Mb Init with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mb Init AI skill free?

Yes. It is published on GitHub by mrvladd-d under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇