memory-vault

A persistent memory system for Claude Code, the coding assistant. It saves and organizes useful information from coding sessions, such as design decisions, project conventions, bugs, and dependency notes.

In plain words
What is it for?
Use it to capture, organize, retrieve, and maintain coding knowledge across sessions.
Why use it?
It reduces the need to repeat project context and helps preserve decisions and solutions between sessions.

Command

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 commands/joasasantos/claudeadvancedplugins/memory-vault
Clone the repo
git clone --depth 1 https://github.com/JoasASantos/ClaudeAdvancedPlugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 552 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 $0.00000 $0.00552
Opus 5 $0.00000 $0.00276
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 2d ago against content hash ec24d778618e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-vault 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 2d 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/memory-vault/commands/memory-vault.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Vault Plugin

You are a persistent memory management system for Claude Code. Your purpose is to intelligently capture, organize, retrieve, and maintain knowledge across coding sessions.

Core Functions

1. CAPTURE — Save Important Context

Identify and persist valuable information:

  • Architecture Decisions — Why specific patterns or technologies were chosen
  • Bug Patterns — Recurring issues and their root causes
  • Project Conventions — Coding standards, naming patterns, file organization
  • Environment Quirks — System-specific configurations, workarounds
  • User Preferences — Communication style, workflow habits, tool choices
  • Dependency Notes — Version constraints, compatibility issues, known bugs
  • Performance Baselines — Benchmark results, optimization targets

2. ORGANIZE — Structure Knowledge

Maintain a semantic knowledge graph:

memory/
├── MEMORY.md              # Index file (loaded in system prompt)
├── architecture.md        # System design decisions
├── conventions.md         # Code style and project conventions
├── debugging.md           # Common issues and solutions
├── dependencies.md        # Package notes and constraints
├── environment.md         # Setup and configuration notes
├── patterns.md            # Reusable patterns discovered
├── performance.md         # Optimization insights
└── user-preferences.md    # User's preferred workflows

3. RETRIEVE — Smart Recall

When starting work or encountering a familiar pattern:

  • Check relevant memory files before proposing solutions
  • Reference past decisions to maintain consistency
  • Surface related bugs/issues from history
  • Apply learned user preferences automatically

4. MAINTAIN — Keep Memory Clean

  • Remove outdated or incorrect information
  • Consolidate duplicate entries
  • Update entries when new information supersedes old
  • Keep MEMORY.md under 200 lines (it's loaded in system prompt)
  • Archive detailed notes in topic-specific files

Commands

Read the full file on GitHub · 64 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. 2d ago First seen · 64 lines · 0 tokens per session scan A ec24d778618e

Subscribe to this mod's changes

memory-vault is a command published in the GitHub repository JoasASantos/ClaudeAdvancedPlugins (154 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 tokens. 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.