long-term-memory

long-term-memory is a skill for Claude Code from MarcelRoozekrans/LongtermMemory-MCP. It costs 41 tokens per session (1,578 once invoked), scanned A, original, MIT.

A persistent memory skill for an AI coding agent. It stores information locally with meaning-based search, so the agent can recall relevant context in later sessions.

In plain words
What is it for?
Use it to recall context at the start of work and save important results afterward, as well as update, filter, back up, or delete stored memories.
Why use it?
It reduces repeated explanations and helps preserve decisions, preferences, task details, and debugging insights across sessions.

Skill for Claude Code

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

Part of the longterm-memory plugin — 1 skill shipped together

Good fit Use it to recall context at the start of work and save important results afterward, as well as update, filter, back up, or delete stored memories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcelroozekrans/longtermmemory-mcp/long-term-memory
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 MarcelRoozekrans/LongtermMemory-MCP --skill long-term-memory
Clone the repo
git clone --depth 1 https://github.com/MarcelRoozekrans/LongtermMemory-MCP

Made for: Claude Code.

Or install longterm-memory, the plugin that ships this one along with the rest of its 1 skill.

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 long-term-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcelroozekrans/longtermmemory-mcp/long-term-memory/github.svg)](https://agentmods.dev/skills/marcelroozekrans/longtermmemory-mcp/long-term-memory)
Your own site
<a href="https://agentmods.dev/skills/marcelroozekrans/longtermmemory-mcp/long-term-memory"><img src="https://agentmods.dev/badge/skills/marcelroozekrans/longtermmemory-mcp/long-term-memory/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 long-term-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcelroozekrans/longtermmemory-mcp/long-term-memory"><img src="https://agentmods.dev/badge/skills/marcelroozekrans/longtermmemory-mcp/long-term-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,578 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 $0.00041 $0.01578
Opus 5 $0.00020 $0.00789
Sonnet 5 $0.00008 $0.00316
Haiku 4.5 $0.00004 $0.00158

Measured 10d ago against content hash b47ea4fb5744, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

long-term-memory 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 10d 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/long-term-memory/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Long-Term Memory

Persistent, semantic memory across sessions. Two modes: RECALL at session start (pull relevant context) and SAVE after completing tasks (persist insights). All memory operations should be invisible to the user.

Tools Available

Tool Purpose
save_memory Store text with auto-generated semantic embedding, tags, importance, and type
search_memory Find relevant memories using natural language query (cosine similarity)
update_memory Modify an existing memory (content, metadata, tags, importance, type)
delete_memory Remove a specific memory by ID
delete_all_memories Wipe all memories (irreversible)
get_all_memories List all stored memories (paginated)
memory_stats Get count and database location
search_by_type Filter memories by category (general, fact, preference, conversation, task, ephemeral)
search_by_tags Find memories matching any of the provided tags
search_by_date_range Find memories created within a specific date range
create_backup Manually trigger a database backup with JSON export

When to Use

  • Session start: Always. Recall relevant memories before any work begins.
  • After debugging / bug fixes: Save root causes and fix patterns.
  • After brainstorming / design work: Save design decisions and architecture choices.
  • After planning / implementation: Save implementation approach and tech decisions.
  • After code reviews: Save style preferences and feedback patterns.
  • After writing tests: Save test patterns and strategies.
  • After any major task: Save workflow preferences discovered during the session.

RECALL Mode (Session Start)

When invoked at the start of a session:

  1. Detect context — Determine the current project from:

    • Working directory name or git remote
    • Any CLAUDE.md in the project
    • The user's first message
  2. Search memories — Call search_memory with two queries (sequentially):

    • "{project name} {task keywords from user message}" — project-specific context
    • "preference workflow" — general preferences that apply everywhere

Read the full file on GitHub · 135 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. 10d ago First seen · 135 lines · 41 tokens per session scan A b47ea4fb5744

Subscribe to this mod's changes

long-term-memory is a skill published in the GitHub repository MarcelRoozekrans/LongtermMemory-MCP (1 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,578 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

shellm

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

laude-institute/headlong · 49 tokens