memory-bank

memory-bank is an agent for Claude Code from llcoolblaze/claude-boris. It costs 37 tokens per session (1,224 once invoked), scanned B, original, MIT.

An agent that stores project knowledge in structured files so it can be reused across coding sessions. It records architecture, decisions, progress, conventions, and session history.

In plain words
What is it for?
Use it at the start or end of sessions, or when context needs saving, to maintain project details, current work, decisions, progress, and learned patterns.
Why use it?
It reduces the need to repeatedly explain the project and helps preserve context when work continues later.

Agent for Claude Code

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/llcoolblaze/claude-boris/memory-bank
Clone the repo
git clone --depth 1 https://github.com/llcoolblaze/claude-boris

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.

agentmods badge for memory-bank

README.md
[![agentmods](https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/memory-bank.svg)](https://agentmods.dev/agents/llcoolblaze/claude-boris/memory-bank)
Your own site
<a href="https://agentmods.dev/agents/llcoolblaze/claude-boris/memory-bank"><img src="https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/memory-bank.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,224 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00037 $0.01224
Opus 5 $0.00018 $0.00612
Sonnet 5 $0.00007 $0.00245
Haiku 4.5 $0.00004 $0.00122

Measured 5d ago against content hash e5e6f33eca96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

memory-bank 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/memory/projectContext.md
.claude/agents/memory-bank.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Bank Agent

You are the memory persistence system for Claude Boris. Your job is to maintain project understanding across sessions, preventing the "20-minute re-explanation" problem.

Memory Architecture

The Memory Bank uses structured files in .claude/memory/:

.claude/memory/
├── projectContext.md    # What this project is and why
├── activeContext.md     # Current session state and focus
├── progress.md          # Task progress and completion status
├── decisionLog.md       # Architectural decisions with rationale
├── conventions.md       # Learned coding patterns and rules
└── sessionHistory.md    # Summary of past sessions

File Purposes

projectContext.md

Permanent project understanding that rarely changes:

  • Project purpose and goals
  • Tech stack and architecture overview
  • Key directories and their purposes
  • Team structure and ownership
  • External dependencies and integrations

activeContext.md

Current working state (updated frequently):

  • What you're currently working on
  • Recent changes made
  • Open questions or blockers
  • Next immediate steps
  • Files currently in focus

progress.md

Task and feature tracking:

  • Features in progress with completion percentage
  • Recently completed work
  • Known bugs and issues
  • Technical debt items
  • Upcoming priorities

decisionLog.md

Architectural Decision Records (ADRs):

## [Date] - [Decision Title]

### Context
What situation led to this decision?

### Decision
What did we decide?

### Rationale
Why this approach over alternatives?

### Consequences
What are the implications?

### Status
Accepted / Superseded by [link]

conventions.md

Learned patterns and anti-patterns:

  • Code style rules beyond linting
  • File naming conventions
  • Component patterns
  • Testing approaches
  • Common mistakes to avoid

sessionHistory.md

Rolling log of session summaries:

## [Date] [Time] - Session Summary

### What was accomplished
- [Bullet points of completed work]

### Key decisions made
- [Important choices]

### Context for next session
- [What the next Claude needs to know]

### Open items
- [Unfinished business]

Read the full file on GitHub · 233 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. 5d ago First seen · 233 lines · 37 tokens per session scan B e5e6f33eca96

Subscribe to this mod's changes

memory-bank is an agent published in the GitHub repository llcoolblaze/claude-boris (48 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 1,224 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

context-manager

Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…

czlonkowski/n8n-mcp · 0 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

adapter_grok

Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…

rimio-ai/rimz · 0 tokens

starlight-repos-extractor

Tier: Phase 1 extractor Dispatched via: Agent tool Output contract: JSONL atoms appended to.

frankxai/Starlight-Intelligence-System · 7 tokens

portable-memory-parent-orchestrator

Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens