memory-checkpoint

memory-checkpoint is a skill for Claude Code, Codex from u9401066/HyperHierarchicalRAG. It costs 0 tokens per session (1,948 once invoked), scanned A, a copy of memory-checkpoint, Apache-2.0.

A memory-saving workflow that records important project context in files called a Memory Bank. It is intended to preserve details when a long conversation is shortened or summarized.

In plain words
What is it for?
Use it to save current work, progress, decisions, and architecture changes to files such as activeContext.md, progress.md, and decisionLog.md.
Why use it?
It reduces the risk of losing file paths, decisions, code changes, and next steps from the conversation.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/u9401066/hyperhierarchicalrag/memory-checkpoint
Any agent
npx skills add u9401066/HyperHierarchicalRAG --skill memory-checkpoint
Clone the repo
git clone --depth 1 https://github.com/u9401066/HyperHierarchicalRAG

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 memory-checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/u9401066/hyperhierarchicalrag/memory-checkpoint.svg)](https://agentmods.dev/skills/u9401066/hyperhierarchicalrag/memory-checkpoint)
Your own site
<a href="https://agentmods.dev/skills/u9401066/hyperhierarchicalrag/memory-checkpoint"><img src="https://agentmods.dev/badge/skills/u9401066/hyperhierarchicalrag/memory-checkpoint.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,948 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.01948
Opus 5 $0.00000 $0.00974
Sonnet 5 $0.00000 $0.00390
Haiku 4.5 $0.00000 $0.00195

Measured 5d ago against content hash f18f510d20c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-checkpoint 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 5d 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.

Origin

This is a copy

100% identical to memory-checkpoint — 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.

.claude/skills/memory-checkpoint/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: memory-checkpoint description: Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著.

Memory Checkpoint 技能 (記憶檢查點)

描述

在對話被 Summarize 壓縮前,主動將詳細記憶外部化到 Memory Bank,避免重要上下文遺失。

觸發條件

  • 「記憶檢查點」、「checkpoint」、「存檔」
  • 「保存記憶」、「外部化記憶」
  • 「sync memory」、「dump context」
  • 對話較長時主動觸發(建議每 10-15 輪對話或重大進展後)

⚠️ 為什麼需要這個 Skill?

當對話過長時,系統會自動 Summarize(摘要)對話歷史,可能導致:

  • 詳細的程式碼變更記錄被省略
  • 決策背後的討論脈絡遺失
  • 檔案路徑和具體實作細節模糊化
  • 需要花時間重建上下文

解決方案:在被 Summarize 前,主動將關鍵記憶寫入 memory-bank/ 目錄。


📋 Checkpoint 內容

1️⃣ activeContext.md - 當前工作焦點

## 當前工作焦點
<!-- 當前正在做什麼 -->

## 進行中的變更
<!-- 具體的檔案和修改 -->

## 待處理事項
<!-- 下一步要做什麼 -->

## 關鍵決策
<!-- 本次對話做的重要決定 -->

## 相關檔案
<!-- 涉及的檔案路徑列表 -->

2️⃣ progress.md - 進度追蹤

## Done (已完成)
- [x] 具體完成的事項(含檔案路徑)

## Doing (進行中)
- [ ] 正在進行的工作

## Next (下一步)
- [ ] 計劃要做的事項

3️⃣ decisionLog.md - 決策日誌

## YYYY-MM-DD

### 決策:[決策標題]
- **背景**:為什麼需要這個決定
- **選項**:考慮過的方案
- **決定**:最終選擇
- **原因**:選擇的理由

4️⃣ architect.md - 架構記錄(如有變更)

## 架構變更記錄

### YYYY-MM-DD: [變更標題]
- **變更內容**:
- **影響範圍**:
- **相關檔案**:

🚀 Checkpoint 執行步驟

自動執行(推薦)

當偵測到以下情況,AI 應主動執行 Checkpoint:

  1. 對話長度指標

    • 對話超過 10 輪
    • 累積修改超過 5 個檔案
    • 完成一個重要功能/修復
  2. 工作階段轉換

    • 從設計階段轉到實作
    • 完成一個 PR 或 Commit
    • 切換到不同的功能區塊
  3. 明確指標

    • 使用者說「先記一下」、「checkpoint」
    • 使用者說「等等繼續」、「我先去忙」

手動執行

使用者可隨時說:

  • 「記憶檢查點」
  • 「同步 memory bank」
  • 「存檔目前進度」

📝 Checkpoint 範本

Quick Checkpoint(快速檢查點)

更新 activeContext.md

# Active Context

> Last checkpoint: 2024-XX-XX HH:MM

## 🎯 當前焦點
[一句話描述當前在做什麼]

## 📝 本次對話摘要
1. [做了什麼 1]
2. [做了什麼 2]
3. [做了什麼 3]

## 📁 變更的檔案
- `path/to/file1.py` - [變更摘要]
- `path/to/file2.ts` - [變更摘要]

## ⚠️ 待解決
- [ ] 問題 1
- [ ] 問題 2

## 💡 重要決定
- 決定 A:[原因]
- 決定 B:[原因]

## 🔜 下一步
1. [下一步 1]
2. [下一步 2]

Full Checkpoint(完整檢查點)

更新所有相關 Memory Bank 檔案:

Read the full file on GitHub · 271 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. 5d ago First seen · 271 lines · 0 tokens per session scan A f18f510d20c6

Subscribe to this mod's changes

memory-checkpoint is a skill published in the GitHub repository u9401066/HyperHierarchicalRAG (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,948 tokens. A static security scan graded it A with 0 findings. It is 100% identical to memory-checkpoint, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

ux-ui-map-page-by-page

Produce the EdgeQuake WebUI UX/UI map one route at a time (capture screenshots, then immediately write per-page docs and per-page analysis requests). Use when asked to map UI, capture screens page-by-page, avoid agent memory saturation, or generate uxuimap artifacts.

raphaelmansuy/edgequake · 63 tokens

ux-ui-analyze-single-page

Analyze exactly one captured UI page (from uxuimap screenshots + request JSON) and immediately write/update uxuimap/pages/{page}.md in neutral descriptive language. Use when asked to analyze screenshots, rewrite corresponding analysis immediately, or avoid memory/context saturation.

raphaelmansuy/edgequake · 58 tokens

lemmalog

Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…

JordyZomer/lemmalog · 105 tokens

dbrain-processor

Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.

smixs/agent-second-brain · 60 tokens

autograph

Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…

smixs/agent-second-brain · 89 tokens

braindb

Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.

dimknaf/braindb · 36 tokens