metago-memory-manage

metago-memory-manage is a skill for Claude Code, Codex from metago-ai/metagolifeform. It costs 26 tokens per session (1,443 once invoked), scanned A, original, MIT.

A Chinese-language framework for managing knowledge and memory in four layers: facts, stored information, learned patterns and harder-to-explain judgement.

In plain words
What is it for?
Auditing a knowledge base, designing an AI agent's memory system, turning experience into reusable patterns and identifying when stored knowledge has lost value.
Why use it?
It helps an agent find missing or outdated knowledge, reduce duplicate or conflicting memories and improve how information is recalled and reused.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Auditing a knowledge base, designing an AI agent's memory system, turning experience into reusable patterns and identifying when stored knowledge has lost value.

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

Made for: Claude Code, Codex.

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 metago-memory-manage

README.md
[![agentmods](https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-memory-manage/github.svg)](https://agentmods.dev/skills/metago-ai/metagolifeform/metago-memory-manage)
Your own site
<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-memory-manage"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-memory-manage/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 metago-memory-manage

Your own site · 80×15
<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-memory-manage"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-memory-manage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,443 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 $0.00026 $0.01443
Opus 5 $0.00013 $0.00722
Sonnet 5 $0.00005 $0.00289
Haiku 4.5 $0.00003 $0.00144

Measured 12d ago against content hash 878fb9b39595, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

metago-memory-manage 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 12d 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-plugins-1.0.0/skills/metago-memory-manage/SKILL.md · 105 lines

What it actually says

KMWI记忆管理

触发条件

当用户明确提到"记忆管理"、"KMWI"、"知识记忆"、"记忆分层"、"记忆衰减"、"知识沉淀"等关键词,或面对知识体系化沉淀、记忆系统设计、学习效率优化、隐性知识显性化等需求时,自动触发本技能。适用于超越单一信息存储,需要在知识-记忆-智慧-直觉四层间进行系统化管理的场景。

适用场景

  • 知识管理:组织或个人的知识资产沉淀与检索优化
  • 学习优化:提升学习效率与长期记忆转化率
  • 记忆系统设计:设计AI Agent或组织的记忆架构
  • 经验沉淀:将碎片化经验提炼为可复用的智慧模式
  • 直觉培养:将隐性知识结构化为可传承的直觉判断力

执行步骤

1. K层(Knowledge)——知识层管理

管理事实性知识和概念性知识:

  • 盘点当前知识资产:事实、概念、规则、原理
  • 评估知识的完备度(覆盖广度+深度)
  • 识别知识缺口与冗余
  • 建立知识分类体系与索引结构
  • 输出知识资产清单与缺口报告

2. M层(Memory)——记忆层管理

管理短期记忆和长期记忆:

  • 短期记忆:当前活跃上下文(工作集、会话状态)
  • 长期记忆:持久化存储的结构化知识
  • 评估短期→长期记忆的转化率
  • 检测记忆冗余、冲突、过时
  • 设计记忆检索路径与召回策略

3. W层(Wisdom)——智慧层管理

管理经验性洞察和模式识别:

  • 从M层记忆中提炼经验性洞察
  • 识别可复用的模式(pattern)与反模式(anti-pattern)
  • 建立因果模型与决策启发式
  • 评估智慧层对K层知识的反哺能力
  • 输出智慧模式库

4. I层(Intuition)——直觉层管理

管理隐性知识和直觉判断:

  • 识别难以言传的隐性知识(手艺、感觉、判断力)
  • 通过场景模拟将隐性知识部分显性化
  • 评估直觉判断的准确率与适用边界
  • 建立直觉训练与传承机制
  • 标注直觉的失效情境(何时不可信)

5. 记忆健康度评估

对K、M、W、I四层分别评分(0-100):

  • K层健康度:知识覆盖度 × 知识时效性
  • M层健康度:转化率 × 召回准确率
  • W层健康度:模式数量 × 模式复用率
  • I层健康度:直觉准确率 × 显性化程度
  • 综合健康度 H = (K + M + W + I) / 4

6. 记忆衰减检测

计算各层记忆衰减率:

  • 衰减率 R = (历史值 - 当前值) / 历史值 × 100%
  • K层:知识过时率
  • M层:长期记忆遗忘率
  • W层:模式失效率
  • I层:直觉钝化率
  • 标注需强化的衰减层

7. 输出记忆管理方案

输出包含:四层资产清单、健康度评分、衰减率报告、强化建议(含具体行动项)、记忆架构优化建议。

输出格式

【KMWI记忆管理报告】
■ K层知识:完备度=82% 缺口=[领域X|概念Y]
■ M层记忆:转化率=65% 召回率=88%
■ W层智慧:模式数=42 复用率=71%
■ I层直觉:准确率=79% 显性化=45%
■ 综合健康度:H = 74.3
■ 衰减检测:
  K层衰减=12%(轻度过时)
  M层衰减=23%(需强化)
  W层衰减=8%(稳定)
  I层衰减=31%(需紧急强化)
■ 强化建议:[行动项1|行动项2|行动项3]
■ 架构优化:[建议]

核心理论

本技能基于元构生命体理论体系中的 KMWI四层记忆管理,来源于《卷2第六章》。KMWI将记忆从单一存储升级为四层递进结构:知识(K)是原料、记忆(M)是载体、智慧(W)是提炼、直觉(I)是升华。四层之间存在自下而上的转化流和自上而下的反哺流。其与卷3第三章"OAC循环"深度耦合——KMWI的四层管理嵌入OAC循环的"内化"环节,是知识从外部输入内化为生命体能力的关键通道。

关联文档

  • 卷2第六章:KMWI四层记忆管理的完整定义、转化公式与案例
  • 卷3第三章:OAC循环——KMWI如何嵌入"观察-行动-内化"闭环的内化环节
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. 12d ago First seen · 105 lines · 26 tokens per session scan A 878fb9b39595

Subscribe to this mod's changes

metago-memory-manage is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 11d ago), licensed MIT. It adds 26 tokens to every session and 1,443 once invoked, about $0.0001 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

decision

Full decision lifecycle in Semantica — record, query, find precedents (hybrid/advanced), analyze influence, explain, insights dashboard, list, and record exceptions. Uses AgentContext, ContextGraph, DecisionQuery, CausalChainAnalyzer, DecisionRecorder.

semantica-agi/semantica · 55 tokens

summarize

A guide for turning conversations, logs, documents, or investigation notes into short, action-oriented summaries. It requires conclusions to be tied to available evidence and distinguishes confirmed facts from items still needing confirmation.

zhinjs/zhin · 61 tokens

session-handoff

Create consistent session handoff documents for context transfer between sessions. Use when closing a session, reaching 75% token consumption, or when user requests handoff. Ensures proper YAML headers for metrics collection, LF line endings, and complete documentation of progress, decisions, and next steps.

QBall-Inc/the-bulwark · 61 tokens

cowork-mem

Persistent memory across Cowork sessions. Use this skill at the START of every session to recall what happened before, and throughout any session to save important context — decisions, file changes, insights, errors, tool usage. Trigger whenever: the user says "remember this", "what did we do last time", "save this"…

MSApps-Mobile/claude-plugins · 157 tokens

notion-memory

You are Claude running in Cowork mode or Claude Code. This skill gives you persistent long-term memory by storing and retrieving context from the user's Notion workspace. Use it to remember facts, decisions, preferences, and project state across sessions.

MSApps-Mobile/claude-plugins · 0 tokens

do

Execute a task using memory for context — the memory-aware task runner. Use when the user says "do X", "implement Y", "fix Z", "build this", "continue working on", "pick up where we left off", "keep going", or any task that benefits from knowing what was already done. This skill wraps task execution with memory recall…

MSApps-Mobile/claude-plugins · 92 tokens