Borrowing it
Nothing to install: this file belongs to u9401066/med-paper-assistant. 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/med-paper-assistant/master/.claude/skills/memory-checkpoint/SKILL.mdgit clone --depth 1 https://github.com/u9401066/med-paper-assistantWrote 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/med-paper-assistant/memory-checkpoint)<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/memory-checkpoint"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/memory-checkpoint/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/u9401066/med-paper-assistant/memory-checkpoint"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/memory-checkpoint.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 | $0.00037 | $0.00457 |
| Opus 5 | $0.00018 | $0.00229 |
| Sonnet 5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
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 9d 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.
What it actually says
Memory Checkpoint 技能
在對話被 Summarize 前，主動將關鍵記憶寫入 memory-bank/，避免上下文遺失。
觸發時機
| 自動 | 手動 |
|---|---|
| 對話 >10 輪 | 「checkpoint」「存檔」 |
| 修改 >5 檔案 | 「先記一下」「要離開」 |
| 完成重要功能 | 「sync memory」 |
| 從設計轉實作 |
更新檔案
| 檔案 | 必要 | 內容 |
|---|---|---|
activeContext.md |
✅ | 焦點、變更檔案、待解決、決策、下一步 |
progress.md |
✅ | Done / Doing / Next |
decisionLog.md |
⚪ | 新決策（背景→選項→決定→原因） |
architect.md |
⚪ | 架構變更（如有） |
品質要求
| 必須 | 說明 |
|---|---|
| ✅ | 當前焦點（一句話） |
| ✅ | 變更檔案列表（完整路徑 + 簡述） |
| ✅ | 待解決事項 |
| ✅ | 下一步 |
| ✅ | 時間戳記 |
| ⚪ | 重要決策（如有） |
整合
- git-precommit：commit 前 → checkpoint → 同步 → commit
- memory-updater：checkpoint = 批次更新，updater = 增量更新
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.
- 9d ago First seen · 49 lines · 37 tokens per session scan A 200c7e08d5cc
memory-checkpoint is a skill published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 8d ago), licensed Apache-2.0. It adds 37 tokens to every session and 457 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
nav-graph
Query project knowledge graph. Search across tasks, SOPs, memories, and concepts. Use when user asks "what do we know about X?", "show everything related to X", or "remember this pattern/pitfall/decision".
nav-marker
Create context save points to preserve conversation state before breaks, risky changes, or compaction. Use when user says "save my progress", "create checkpoint", "mark this point", or before clearing context.
nav-profile
Manage user preferences and corrections for bilateral modeling. Auto-learns from session corrections. Use when user says "save my preferences", "remember I like...", or auto-triggers after corrections.
nav-diagnose
Detect quality drops in AI output and prompt re-anchoring. Auto-triggers after repeated corrections, context confusion, or when user says "something seems off", "you're not getting this".
session-logs
Search, browse, and analyze session history to recall past conversations, decisions, and completed work.
memory-manager
Store, recall, and organize persistent context, preferences, and knowledge across sessions.