memory-bank

memory-bank is a skill for Claude Code from parisgroup-ai/imersao-ia-setup. It costs 70 tokens per session (4,436 once invoked), scanned A, original, MIT.

A system of project files that stores important context between coding-agent sessions. It records the project's purpose, architecture, technical setup, progress, known problems, and current focus.

In plain words
What is it for?
Use it to record project knowledge, read context at session start, update progress after significant changes, and preserve solutions to recurring problems.
Why use it?
It reduces repeated explanations and helps the agent continue work after its conversation context has been cleared or a new session begins.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the imersao plugin — 51 skills, 7 commands shipped together

Good fit Use it to record project knowledge, read context at session start, update progress after significant changes, and preserve solutions to recurring problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parisgroup-ai/imersao-ia-setup/memory-bank
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.

Any agent
npx skills add parisgroup-ai/imersao-ia-setup --skill memory-bank
Clone the repo
git clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setup

Made for: Claude Code.

Or install imersao, the plugin that ships this one along with the rest of its 51 skills, 7 commands.

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/skills/parisgroup-ai/imersao-ia-setup/memory-bank/github.svg)](https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/memory-bank)
Your own site
<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/memory-bank"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/memory-bank/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.

agentmods 80×15 button for memory-bank

Your own site · 80×15
<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/memory-bank"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/memory-bank.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.04436
Opus 5 $0.00035 $0.02218
Sonnet 5 $0.00014 $0.00887
Haiku 4.5 $0.00007 $0.00444

Measured 11d ago against content hash bc087931ebcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

memory-bank 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 11d 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.

plugins/imersao/skills/memory-bank/SKILL.md · 770 lines

How it starts

The opening of the file, as written. The whole thing — 770 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Bank Skill

This skill manages the project's memory-bank system - a structured set of files that preserve context between Claude Code sessions. The memory-bank ensures continuity, reduces repetitive explanations, and maintains project intelligence.

Core Philosophy

Claude's memory resets between sessions. The memory-bank serves as persistent project memory:

  1. Read memory-bank files at session start
  2. Use context throughout the session
  3. Update files before session ends or after significant changes

Memory Bank Structure

project-root/
├── CLAUDE.md                    # Primary entry point (required)
├── memory-bank/
│   ├── projectbrief.md          # Foundation document
│   ├── productContext.md        # Why and how
│   ├── activeContext.md         # Current focus (update frequently)
│   ├── systemPatterns.md        # Architecture patterns
│   ├── techContext.md           # Technical details
│   ├── progress.md              # What's done, what's next (keep slim!)
│   ├── errors.md                # Known issues and solutions
│   └── archive/                 # (Optional) Historical details
│       ├── index.md             # Quick lookup for archived items
│       └── YYYY-MM.md           # Monthly archives (e.g., 2025-12.md)

When to Archive

When progress.md exceeds ~500 lines, split it:

  1. Keep in progress.md: Current sprint, next up, milestone summary table, known issues
  2. Move to archive/: Detailed session logs, files created/modified, commits, lessons learned

This keeps progress.md scannable (<100 lines) while preserving full history.

File Hierarchy

┌─────────────────────────────────────────┐
│            CLAUDE.md                     │  ← Start here ALWAYS
│         (Entry Point)                    │
└─────────────────┬───────────────────────┘
                  │
                  ▼
┌─────────────────────────────────────────┐
│         projectbrief.md                  │  ← Foundation
│      (Project Foundation)                │
└─────────────────┬───────────────────────┘
                  │
        ┌─────────┴─────────┐
        ▼                   ▼
┌───────────────┐   ┌───────────────┐
│ productContext│   │  techContext  │  ← Core Context
│   (Why/How)   │   │  (Stack/Tech) │
└───────┬───────┘   └───────┬───────┘
        │                   │
        └─────────┬─────────┘
                  ▼
┌─────────────────────────────────────────┐
│         systemPatterns.md                │  ← Patterns
│     (Architecture Decisions)             │
└─────────────────┬───────────────────────┘
                  │
                  ▼
┌─────────────────────────────────────────┐
│          activeContext.md                │  ← Current State
│       (Now + Next Actions)               │
└─────────────────┬───────────────────────┘
                  │
                  ▼
┌─────────────────────────────────────────┐
│           progress.md                    │  ← History
│      (Done + Remaining Work)             │
└─────────────────────────────────────────┘

Read the full file on GitHub · 770 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. 11d ago First seen · 770 lines · 70 tokens per session scan A bc087931ebcb

Subscribe to this mod's changes

memory-bank is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 70 tokens to every session and 4,436 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories