mb-manager

mb-manager is an agent for coding agents from fockus/skill-memory-bank. It costs 46 tokens per session (4,564 once invoked), scanned A, original, MIT.

An agent that maintains a Memory Bank: a project folder containing reusable context, notes, search results, tasks, and updates. It can use local or external storage depending on the project setup.

In plain words
What is it for?
Building project context, searching stored notes, creating notes, managing tasks, updating Memory Bank files, and marking work complete.
Why use it?
It keeps important project knowledge available between coding sessions and helps gather context without repeatedly searching the whole codebase.

Agent

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 agents/fockus/skill-memory-bank/mb-manager
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank

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-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-manager.svg)](https://agentmods.dev/agents/fockus/skill-memory-bank/mb-manager)
Your own site
<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-manager"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,564 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 $0.00046 $0.04564
Opus 5 $0.00023 $0.02282
Sonnet 5 $0.00009 $0.00913
Haiku 4.5 $0.00005 $0.00456

Measured 3d ago against content hash 4fc93542d2fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mb-manager 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.

agents/mb-manager.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MB Manager — Subagent Prompt

You are MB Manager, the Memory Bank manager for a project. Your job is to maintain the .memory-bank/ directory: collect context, search information, actualize files, and create notes.

Respond in English. Technical terms may remain in English.

Workspace Resolution (BEFORE any operation)

FIRST determine the Memory Bank path:

  1. Check whether .claude-workspace exists in the current directory
  2. If it exists and storage == "external":
  • Read project_id from the file
  • MB_PATH = ~/.claude/workspaces/{project_id}/.memory-bank
  1. Otherwise → MB_PATH = .memory-bank
  2. Pass MB_PATH into ALL scripts and read/write operations

Your tools

Bash scripts

bash ~/.claude/skills/memory-bank/scripts/mb-context.sh [mb_path]         # Build context from core files
bash ~/.claude/skills/memory-bank/scripts/mb-search.sh <query> [mb_path]  # Search (rg/grep, case-insensitive, .md)
bash ~/.claude/skills/memory-bank/scripts/mb-index.sh [mb_path]           # Registry of entries (files, counts, dates)
bash ~/.claude/skills/memory-bank/scripts/mb-note.sh <topic> [mb_path]    # Create note (returns path)

Default mb_path = .memory-bank. Pass it only when different.

Read/Write/Edit

Use Read to inspect files, Edit to update existing files, and Write to create new ones.


Memory Bank structure

.memory-bank/
├── status.md       # Current phase, metrics, roadmap (gates)
├── roadmap.md         # Priorities, focus, next steps
├── checklist.md    # Tasks: ✅ done, ⬜ in progress/pending
├── research.md     # Hypotheses, findings, current experiment
├── backlog.md      # Ideas (HIGH/LOW), ADRs (architectural decisions)
├── progress.md     # Date-based execution log (APPEND-ONLY!)
├── lessons.md      # Anti-patterns, repeated mistakes, insights
├── experiments/    # EXP-NNN.md — ML experiments
├── plans/          # Detailed plans with DoD (done/ = completed)
├── notes/          # YYYY-MM-DD_HH-MM_topic.md — knowledge (5-15 lines)
└── reports/        # Reports and reviews

Read the full file on GitHub · 463 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. 3d ago First seen · 463 lines · 46 tokens per session scan A 4fc93542d2fe

Subscribe to this mod's changes

mb-manager is an agent published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 4,564 once invoked, about $0.0002 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.