Borrowing it
Nothing to install: this file belongs to u9401066/rootcause-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/u9401066/rootcause-mcp/master/.claude/skills/memory-updater/SKILL.mdgit clone --depth 1 https://github.com/u9401066/rootcause-mcpWrote 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/u9401066/rootcause-mcp/memory-updater)<a href="https://agentmods.dev/skills/u9401066/rootcause-mcp/memory-updater"><img src="https://agentmods.dev/badge/skills/u9401066/rootcause-mcp/memory-updater.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01335 |
| Opus 5 | $0.00000 | $0.00668 |
| Sonnet 5 | $0.00000 | $0.00267 |
| Haiku 4.5 | $0.00000 | $0.00134 |
Grade A, and why
memory-updater 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 7d 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.
This is a copy
100% identical to memory-updater — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Bank 更新技能
描述
維護和更新專案的 Memory Bank 記憶系統,確保專案狀態在對話間持久化。
觸發條件
- 「更新 memory bank」「MB」「記錄進度」
- 「更新上下文」「sync」「同步」
- 工作階段結束時
- 完成重要任務後
📁 Memory Bank 檔案結構
memory-bank/
├── activeContext.md # 當前工作焦點(最常更新)
├── progress.md # 進度追蹤 Done/Doing/Next
├── decisionLog.md # 重要決策記錄
├── architect.md # 架構文檔
├── productContext.md # 專案上下文
├── projectBrief.md # 專案簡介
└── systemPatterns.md # 系統模式
🔧 操作步驟
Step 1: 讀取現有內容
使用 read_file 工具讀取要更新的檔案:
read_file("memory-bank/activeContext.md")
read_file("memory-bank/progress.md")
Step 2: 判斷更新類型
| 情況 | 更新檔案 | 更新方式 |
|---|---|---|
| 開始新任務 | activeContext.md, progress.md | 新增 Doing |
| 完成任務 | progress.md | Doing → Done |
| 做出決策 | decisionLog.md | 新增條目 |
| 架構變更 | architect.md | 更新相關區塊 |
Step 3: 執行更新
使用 replace_string_in_file 進行精確更新(推薦):
replace_string_in_file(
filePath="memory-bank/progress.md",
oldString="## Doing\n\n- [ ] 任務 A",
newString="## Doing\n\n- [ ] 任務 A\n- [ ] 新任務 B"
)
或使用 write_file 完整覆寫(適合大幅修改)。
📝 檔案格式規範
activeContext.md
# Active Context
> Last updated: 2026-01-15
## 🎯 當前焦點
[一句話描述正在處理的主要任務]
## 📁 相關檔案
- `path/to/file1.py` - [用途說明]
- `path/to/file2.ts` - [用途說明]
## ⚠️ 待解決問題
- [ ] 問題 1
- [ ] 問題 2
## 💡 備註
[其他需要記住的事項]
progress.md
# Progress
## Done ✅
- [x] 已完成任務 1 (2026-01-15)
- [x] 已完成任務 2 (2026-01-14)
## Doing 🚧
- [ ] 進行中任務 1
- [ ] 進行中任務 2
## Next 📋
- [ ] 計劃任務 1
- [ ] 計劃任務 2
decisionLog.md
# Decision Log
## 2026-01-15
### 決策:選擇 React 作為前端框架
- **背景**:需要選擇前端框架
- **選項**:React, Vue, Svelte
- **決定**:React
- **原因**:團隊熟悉度高,生態系完整
---
## 2026-01-14
### 決策:...
⚡ 更新原則
1. 增量更新
✅ 正確:只修改相關區塊
❌ 錯誤:每次都覆寫整個檔案
2. 保持簡潔
✅ 正確:「完成用戶認證模組」
❌ 錯誤:「今天我們完成了用戶認證模組的開發工作,包括...」
3. 時間標記
✅ 正確:- [x] 完成功能 A (2026-01-15)
❌ 錯誤:- [x] 完成功能 A
4. 檔案路徑完整
✅ 正確:`src/domain/entities/User.py`
❌ 錯誤:`User.py`
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.
- 7d ago First seen · 213 lines · 0 tokens per session scan A bc4113554951
memory-updater is a skill published in the GitHub repository u9401066/rootcause-mcp (0 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,335 tokens. A static security scan graded it A with 0 findings. It is 100% identical to memory-updater, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
vault-summarize
Use when the user asks to summarize, digest, or get an overview of a folder, project, or set of notes in their markdown vault — runs the vault's batched map-reduce recipe so note bodies stay out of the retained conversation context.
vault-workflow
Use when the user asks you to search, read, or reason about notes in their markdown vault — guides when to use which vault tool and how to chain them for good results.
second-brain-reflection
Systematically extract lessons from tasks, compress them into reusable rules, and store them in the appropriate memory tier (Local, Global, or Private). Use this skill at the end of every major mission or experiment to build your 'Second Brain'.
memory-checkpoint
A checkpoint process that copies important project context into Memory Bank files before a conversation is summarized. It records current work, completed and upcoming tasks, decisions, and architecture changes.
memory-updater
A method for maintaining project notes in a set of Memory Bank files, including current context, progress, and important decisions. The notes preserve project state between conversations.
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.…