Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Managed Agent Memory Architecture

ASecurity

Use when implementing 3-tier memory for managed agents — per-account persistent agents, cross-account concepts, user/org preferences. Triggers on "managed agent memory", "per-account agent memory", "cross-account memory", "three-tier memory", "account agent fleet".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill managed-agent-memory-architecture --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Managed Agent Memory Architecture?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Managed Agent Memory Architecture
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-managed-agent-memory-architecture/badge)](https://www.skillsdirectory.com/skills/majinmagros-managed-agent-memory-architecture)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: managed-agent-memory-architecture
description: Use when implementing 3-tier memory for managed agents — per-account persistent agents, cross-account concepts, user/org preferences. Triggers on "managed agent memory", "per-account agent memory", "cross-account memory", "three-tier memory", "account agent fleet".
metadata:
  origin: ECC
  source_docs:
    - https://docs.anthropic.com/en/docs/managed-agents/memory
  video_source: "hm8NzEd5io0 - How founders build on Claude Managed Agents (Claude Oficial)"
  related_skills:
    - unified-memory
    - context-ledger
    - agent-swarm-ops
    - autonomous-agent-harness
---

# Skill: managed-agent-memory-architecture — Memória 3 Tiers (Managed Agents)

Arquitetura oficial do **Managed Agents SDK** em 3 níveis. Código completo em `references/implementation.md` (Tier 1) e `references/watchtower.md` (Tiers 2-3 + Watchtower).

## Quando usar

- Você está usando **Managed Agents SDK** e precisa arquitetar memória
- Precisa de **frotas de agents por conta** (um agent por conta, perene)
- Precisa de **conceitos cross-account** (forecasting, processos organizacionais)
- Precisa de **preferências user/org** gerenciadas pelo SDK
- Quer evitar **corrupção de memória** ao longo do tempo
- Precisa de **indexação eficiente** para queries em larga escala

## Quando NÃO usar

- Memory patterns genéricos → use `unified-memory`, `context-ledger`
- Single agent com memória simples → use `autonomous-agent-harness`
- Swarm coordination → use `agent-swarm-ops`
- RAG corporativo → use `rag-corporativo-seguro`

---

## Os 3 Tiers (resumo)

| Tier | Escopo | Persistência | Quem gerencia |
|---|---|---|---|
| **1. Per-account agents** | Um agent por account, memória detalhada | Forever (segue lifecycle) | **Você** (indexação custom + proteção) |
| **2. Cross-account concepts** | Forecasting, prioritization, org processes | Longo prazo | SDK (`managed: true`) |
| **3. User/org preferences** | Workflows, field semantics, preferências | Longo prazo | SDK (`managed: true`) |

```
Tier 1 (100 agents, detalhado, você indexa)
   │ roll up
   ▼
Tier 2 (conceitos org, gerenciado) ──→ Watchtower (fan-out + roll-up)
   │ shared
   ▼
Tier 3 (user/org, gerenciado)
```

---

## Tier 1: Per-Account Agents (O Core)

- **Escopo:** um agent por account (100 accounts = 100 agents), contexto completo, detalhado
- **Indexação custom — você implementa** (ElasticSearch, pgvector, inverted index)
- **Corrupção:** risco real → checks nightly (consistency, freshness >90d, schema, cross-refs) + auto-repair/alerta

> *"We manage ourselves, because we have to index it in certain ways to make it efficiently queryable."* — Mihir. Salesforce tem 30 campos deprecated com o mesmo significado: a indexação precisa entender **seu** schema.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →