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 L-LesterYu/OpenClaw-hot-skills-zh --skill persona-checkpointgit clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhWrote 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/l-lesteryu/openclaw-hot-skills-zh/persona-checkpoint)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/persona-checkpoint"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/persona-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/l-lesteryu/openclaw-hot-skills-zh/persona-checkpoint"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/persona-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 | $0.00177 | $0.02016 |
| Opus 5.5 | $0.00071 | $0.00806 |
| Sonnet 5.5 | $0.00035 | $0.00403 |
| Haiku 4.5 | $0.00018 | $0.00202 |
Grade A, and why
persona-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 2mo 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
人格检查点 — Never-Forget 协议
本技能实现 AI 人格操作系统的上下文保护和检查点功能,防止上下文丢失,实现 95% 的会话恢复准确率。
阶段 1:评估上下文窗口使用量
步骤 1.1: 检查当前上下文窗口使用百分比
根据对话长度、工具调用和复杂性计算或估算当前上下文窗口利用率。
步骤 1.2: 确定严重程度阈值
| 使用量 | 状态 | 所需操作 |
|---|---|---|
| < 50% | 🟢 正常 | 随时记录决策(轻量级) |
| 50-69% | 🟡 警觉 | 增加检查点频率(每约 5 次交互) |
| 70-84% | 🟠 活跃 | 停止 — 立即写入完整检查点 |
| 85-94% | 🔴 紧急 | 紧急转储 — 仅保留必需信息(任务 + 恢复点) |
| 95%+ | ⚫ 严重 | 生存模式 — 仅保留恢复所需的最低限度信息 |
步骤 1.3: 应用用户可见性规则
- < 70%:静默操作,不通知用户
- 70-84%:通知用户:"上下文已达到 XX% — 正在写入检查点"
- 85-94%:警告用户:"⚠️ 上下文 XX% 处需要紧急检查点"
- 95%+:严重警告:"🚨 上下文已达到临界限制 — 生存模式检查点"
阶段 2:确定检查点操作
步骤 2.1: 根据阈值选择检查点类型
if context < 50%:
checkpoint_type = "lightweight" # 仅内联决策
elif 50% <= context < 70%:
checkpoint_type = "vigilant" # 每约 5 次交互,轻量格式
elif 70% <= context < 85%:
checkpoint_type = "full" # 包含推理的完整检查点
elif 85% <= context < 95%:
checkpoint_type = "emergency" # 仅任务 + 恢复点
else: # 95%+
checkpoint_type = "survival" # 绝对最低限度
步骤 2.2: 检查强制触发条件
如果出现以下情况,覆盖基于阈值的逻辑:
- 用户明确说"checkpoint"/"检查点"(强制完整检查点)
- 重大决策之前(架构变更、破坏性操作)
- 自然会话暂停时(任务完成、上下文切换)
- 有风险的操作之前(数据删除、重构、迁移)
- 正常操作中每约 10 次交互(主动)
阶段 3:写入检查点
步骤 3.1: 创建检查点文件路径
使用 Bash 创建目录并确定文件路径:
mkdir -p ~/workspace/memory
echo "~/workspace/memory/$(date +%Y-%m-%d).md"
步骤 3.2: 根据类型格式化检查点内容
轻量级(< 50%):
## 检查点 [HH:MM] — 上下文:XX%
**决策:** [做出了什么决策]
警觉型(50-69%):
## 检查点 [HH:MM] — 上下文:XX%
**当前任务:** [当前工作]
**继续从:** [下一步]
完整检查点(70-84%):
## 检查点 [HH:MM] — 上下文:XX%
**当前任务:** [我们正在做什么]
**关键决策:**
- [决策 1 及推理]
- [决策 2 及推理]
**待办事项:**
- [ ] [任务 1](负责人:[用户/助手])
- [ ] [任务 2](负责人:[用户/助手])
**当前状态:** [进展摘要]
**继续从:** [精确的下一步及上下文]
紧急型(85-94%):
## ⚠️ 紧急检查点 [HH:MM] — 上下文:XX%
**任务:** [一句话描述]
**继续:** [精确的下一步操作]
生存型(95%+):
## 🚨 生存检查点 [HH:MM] — 上下文:XX%
**继续:** [最低可行下一步]
步骤 3.3: 将检查点写入文件
使用 Bash 将检查点追加到当天的文件:
cat >> ~/workspace/memory/$(date +%Y-%m-%d).md << 'EOF'
[来自步骤 3.2 的格式化检查点内容]
EOF
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.
- 2mo ago First seen · 209 lines · 177 tokens per session scan A 59145389b770
persona-checkpoint is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (57 stars, last pushed 7mo ago), licensed MIT. It adds 177 tokens to every session and 2,016 once invoked, about $0.0007 per session on Opus 5.5. 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.
persona-checkpoint compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| persona-checkpointL-LesterYu/OpenClaw-hot-skills-zh | Skill | 57 | 7mo ago | MIT | A | 177 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | today | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 0 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |