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.
npx skills add Zhao961215/DIKW-Memory-System --skill brain-periodic-refactorgit clone --depth 1 https://github.com/Zhao961215/DIKW-Memory-SystemWrote 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.
[](https://agentmods.dev/skills/zhao961215/dikw-memory-system/brain-periodic-refactor)<a href="https://agentmods.dev/skills/zhao961215/dikw-memory-system/brain-periodic-refactor"><img src="https://agentmods.dev/badge/skills/zhao961215/dikw-memory-system/brain-periodic-refactor/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.
<a href="https://agentmods.dev/skills/zhao961215/dikw-memory-system/brain-periodic-refactor"><img src="https://agentmods.dev/badge/skills/zhao961215/dikw-memory-system/brain-periodic-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.05114 |
| Opus 5 | $0.00041 | $0.02557 |
| Sonnet 5 | $0.00016 | $0.01023 |
| Haiku 4.5 | $0.00008 | $0.00511 |
Grade A, and why
brain-periodic-refactor 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.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIRAAF 大脑定期整理框架
定位：大脑（Holographic fact_store）的领域级结构检查 + 重构定稿。 与已有机制的衔接详见 § 衔接设计。
流程概览
┌─────────────────────────────────────┐
│ CIRAAF 大脑定期整理 │
├─────────────────────────────────────┤
│ │
│ P — 优先级排序：这轮先整哪个领域 │
│ ↓ │
│ C — 分类：属于什么领域/性质 │
│ ↓ │
│ I — 整合：全量扫描该领域facts │
│ ↓ │
│ R — 反思：找过期/矛盾/重复/断链/遗漏 │
│ ↓ │
│ A — 完善：降权 + 更新 + 新增 + patch │
│ ↓ │
│ A — 整理：按 A/B/C/D/E 五层重构 │
│ ↓ │
│ F — 定稿：MEMORY.md + 新fact + 告知 │
│ │
└─────────────────────────────────────┘
详细步骤
P — 优先级排序（先确定这轮整哪个）
| 优先级 | 判断标准 | 例子 |
|---|---|---|
| 🔴 高 | 用户近期频繁问该领域问题，或体系刚发生过变化 | 投资逻辑（六风刚定型） |
| 🟡 中 | 距离上次整理超过4周，或者facts数量>该领域平均 | 系统知识 |
| 🟢 低 | 刚整理不久，facts数量少且稳定 | 用户偏好 |
做法：fact_store(query="领域关键词", limit=50) 查数量 → 对比上一次 source="refactored:" 的时间 → 决定优先级
C — 分类（界定领域边界）
选定的领域有哪些子话题？预先划定搜索边界：
| 领域 | 包含子话题 | 搜索关键词覆盖 |
|---|---|---|
| 投资 | 体系框架/持仓/数据源/PE/动量/止盈/潜风/探风/挖呗 | PE,仓位,动量,止盈,探风,挖呗,潜风,乘风,换风,六风 |
| 系统 | Hermes架构/记忆系统/skill/配置/cron/工具 | hermes,记忆,holographic,skill,cron,config |
| 用户 | 偏好/风格/决策特点/沟通习惯 | 用户,偏好,风格,主上 |
| 开发 | 项目/DIKW/GitHub/设计 | 项目,github,设计,插件,dikw |
| 方法 | 元方法论/思维模型/分析框架 | 框架,方法论,原则,过程,元认知 |
I — 整合（全量扫描该领域facts）
# 核心动作：多维度搜
fact_store(query="PE 动量 止盈 仓位 基金 持仓", limit=50)
fact_store(query="探风 挖呗 潜风 乘风 换风 六风", limit=30)
fact_store(query="投资 原则 框架 体系 数据源", limit=30)
输出：该领域facts的完整清单，按created_at排序，标注信任分。
R — 反思（找7类问题）
对整合结果逐条检查以下7类问题：
| 符号 | 问题类型 | 判断标准 | 处理 |
|---|---|---|---|
| 🗑️ | 过期 | 数据有明确时效（如持仓比例、净值快照），且已过有效期 | fact_feedback降权 |
| 🔄 | 逻辑矛盾 | 两条facts对同一事物做出相反断言 | 保留正确的，降权错误的 |
| 📋 | 重复 | 同一方法论/事实被记录多次 | 保留最新的，降权其余 |
| 📸 | 快照 | 临时动态快照（如"2026-05-15净值数据"），不应存在大脑里 | 降权，这类数据应走cache |
| 📦 | 被覆盖 | 旧框架/旧方法论已被新体系取代 | 降权，在新facts中写明"替代X" |
| 🕳️ | 遗漏 | 该有但没有的关键方法论 | 新写入 |
| 🔄 | 跨领域污染 | 当前领域包含明显属于其他领域的事实（如开发domain混入403条投资fact） | 改category到正确领域，tags标记cirAAF:分类修正 |
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.
- 10d ago First seen · 377 lines · 81 tokens per session scan A 700b195e7020
brain-periodic-refactor is a skill published in the GitHub repository Zhao961215/DIKW-Memory-System (5 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 5,114 once invoked, about $0.0004 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.
Other skills, from other repositories
agent-dreaming-agnostic
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
obsidian-memory-wiki
Use when operating an Obsidian-backed agent memory wiki: safe vault note operations, context-reset handoffs, optional scheduled reconciliation, and multi-agent vault rollout.
core
This skill should be used when the user says "capture memory", "save to memory", "remember this", or trigger phrases like: "I've decided", "let's use", "we're going with", "I learned", "turns out", "TIL", "discovered", "I'm stuck", "blocked by", "always use", "never do", "convention is". Also triggers on recall…
custodian
Memory system custodian for health checks, validation, and maintenance. Trigger phrases: "check memory health", "validate memories", "fix broken links", "update decay", "relocate memories", "audit memories", "memory maintenance", "custodian", "memory health".
format
MIF Level 3 specification, memory templates, and formatting guidelines.