agentmods.dev

mb-init

mb-init is a skill for Claude Code, Codex from mrvladd-d/memobank. It costs 17 tokens per session (1,263 once invoked), scanned A, original, MIT.

A repository setup tool that creates a standard Memory Bank: local folders and documents that store project context for coding agents. It also adds command stubs the project can use.

In plain words
What is it for?
Use it to bootstrap the Memory Bank structure in a repository. It creates folders such as .memory-bank, .tasks, and .protocols, along with starter documents and command proxies.
Why use it?
It gives agents a consistent place to find project rules, requirements, task data, and testing notes instead of relying on scattered prompts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is # Option A: copy ./scripts/shared-init-mb.js into your repo then run:.

not rated 55 3mo ago A scan 17 tokens original MIT
View the source file mrvladd-d/memobank
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mrvladd-d/memobank
agentmods
npx agentmods add skills/mrvladd-d/memobank/mb-init

Made for: Claude Code, Codex.

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 mb-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrvladd-d/memobank/mb-init.svg)](https://agentmods.dev/skills/mrvladd-d/memobank/mb-init)
Your own site
<a href="https://agentmods.dev/skills/mrvladd-d/memobank/mb-init"><img src="https://agentmods.dev/badge/skills/mrvladd-d/memobank/mb-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,263 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 5.1 $0.00017 $0.01263
Opus 5 $0.00009 $0.00632
Sonnet 5 $0.00003 $0.00253
Haiku 4.5 $0.00002 $0.00126

Measured 6d ago against content hash 1158aadab768, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mb-init 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 6d 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.

skills/mb-init/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Read the full file on GitHub · 113 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. 6d ago First seen · 113 lines · 17 tokens per session scan A 1158aadab768

Subscribe to this mod's changes

mb-init is a skill published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 1,263 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 contextProject management
Related

Other skills, from other repositories

mempalace-task

Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.

MemPalace/mempalace · 67 tokens

neat-freak

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…

KKKKhazix/khazix-skills · 202 tokens

gsd-mempalace-capture

File a phase artifact into MemPalace; mirror decision facts into its temporal KG.

open-gsd/gsd-core · 25 tokens

md-hive-sync

Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…

chaitanyagiri/munder-difflin · 109 tokens

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

github-ops

GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.

fuyuxiang/echo-agent · 31 tokens