agent-memory-systems

agent-memory-systems is a skill for Claude Code from latestaiagents/agent-skills. It costs 51 tokens per session (2,854 once invoked), scanned A, original, MIT.

A guide for giving AI agents memory that can persist information and context. It covers temporary working context, session history, long-term knowledge, past events, and shared information between agents.

In plain words
What is it for?
Use it to design persistent memory, shared agent knowledge, conversation context, state management, and systems that record facts or past experiences.
Why use it?
It helps agents retain useful facts across conversations and long-running tasks instead of starting with no history. It also helps choose how information should be stored and shared.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-architect plugin — 13 skills, 1 command, 5 MCP servers shipped together

Good fit Use it to design persistent memory, shared agent knowledge, conversation context, state management, and systems that record facts or past experiences.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/agent-memory-systems
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 latestaiagents/agent-skills --skill agent-memory-systems
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install agent-architect, the plugin that ships this one along with the rest of its 13 skills, 1 command, 5 MCP servers.

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 agent-memory-systems

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/agent-memory-systems.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/agent-memory-systems)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/agent-memory-systems"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/agent-memory-systems.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,854 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 $0.00051 $0.02854
Opus 5 $0.00026 $0.01427
Sonnet 5 $0.00010 $0.00571
Haiku 4.5 $0.00005 $0.00285

Measured 8d ago against content hash 566fb8ad5578, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-memory-systems 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 8d 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/agent-architect/skills/patterns/agent-memory-systems/SKILL.md · 471 lines

How it starts

The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Memory Systems

Design and implement memory systems that give agents persistent knowledge and context.

When to Use

  • Agents need to remember across sessions
  • Multiple agents share knowledge
  • Long-running tasks require state persistence
  • Building agents that learn from experience

Memory Types

┌─────────────────────────────────────────────────────────────┐
│                    AGENT MEMORY TAXONOMY                     │
├─────────────────────────────────────────────────────────────┤
│                                                              │
│  Working Memory (Active Context)                             │
│  └─ Current conversation, immediate task state               │
│                                                              │
│  Short-Term Memory (Session)                                 │
│  └─ Recent interactions, temporary facts                     │
│                                                              │
│  Long-Term Memory (Persistent)                               │
│  ├─ Episodic: Past events, experiences                       │
│  ├─ Semantic: Facts, knowledge, learned info                 │
│  └─ Procedural: How to do things, skills                     │
│                                                              │
└─────────────────────────────────────────────────────────────┘

Working Memory

The agent's current context window.

interface WorkingMemory {
  // Current task context
  task: {
    description: string;
    requirements: string[];
    progress: string[];
  };

  // Active entities being discussed
  entities: Map<string, Entity>;

  // Recent messages
  conversationWindow: Message[];

  // Scratchpad for reasoning
  scratchpad: string;
}

class WorkingMemoryManager {
  private memory: WorkingMemory;
  private MAX_MESSAGES = 20;

  addMessage(message: Message) {
    this.memory.conversationWindow.push(message);

    // Evict old messages
    if (this.memory.conversationWindow.length > this.MAX_MESSAGES) {
      const evicted = this.memory.conversationWindow.shift();
      // Optionally summarize and store
      this.summarizeToShortTerm(evicted);
    }
  }

  updateEntity(id: string, entity: Entity) {
    this.memory.entities.set(id, entity);
  }

  getContext(): string {
    return `
Task: ${this.memory.task.description}
Progress: ${this.memory.task.progress.join(', ')}
Key Entities: ${[...this.memory.entities.values()].map(e => e.summary).join('\n')}
Recent Discussion: ${this.memory.conversationWindow.slice(-5).map(m => m.content).join('\n')}
    `;
  }
}

Read the full file on GitHub · 471 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. 8d ago First seen · 471 lines · 51 tokens per session scan A 566fb8ad5578

Subscribe to this mod's changes

agent-memory-systems is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 2,854 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.