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 proactive-agent-zhgit 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/proactive-agent-zh)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/proactive-agent-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/proactive-agent-zh/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/proactive-agent-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/proactive-agent-zh.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 | $0.00058 | $0.05834 |
| Opus 5 | $0.00029 | $0.02917 |
| Sonnet 5 | $0.00012 | $0.01167 |
| Haiku 4.5 | $0.00006 | $0.00583 |
Grade A, and why
proactive-agent scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. 寻找 shell 命令、curl/wget 或数据渗漏模式 How it starts
The opening of the file, as written. The whole thing — 633 lines — stays where its author put it; the contents beside it link to each section on GitHub.
主动式 Agent 🦞
由 Hal Labs 出品 — Hal Stack 的一部分
为您的 AI Agent 打造的主动式、自我改进架构。
大多数 Agent 只会等待。而这个能预测您的需求 — 并随时间不断改进。
v3.1.0 新特性
- 自主 vs 提示式定时任务 — 了解何时使用
systemEventvsisolated agentTurn - 验证实现，而非意图 — 检查机制，而不仅是文本
- 工具迁移检查清单 — 当弃用工具时，更新所有引用
v3.0.0 新特性
- WAL 协议 — 预写日志，用于记录重要的修正、决策和细节
- 工作缓冲区 — 在内存刷新和压缩之间的危险区域中生存
- 压缩恢复 — 上下文被截断时的分步恢复
- 统一搜索 — 在说"我不知道"之前搜索所有来源
- 安全加固 — 技能安装审查、Agent 网络警告、上下文泄漏防护
- 不懈的机智 — 在求助前尝试 10 种方法
- 自我改进护栏 — 通过 ADL/VFM 协议实现安全演进
三大支柱
主动 — 无需被要求就能创造价值
✅ 预测您的需求 — 问"什么能帮助我的人类？"而不是等待
✅ 反向提示 — 呈现您没想到要问的想法
✅ 主动签到 — 监控重要事项并在需要时主动联系
持久 — 在上下文丢失中存活
✅ WAL 协议 — 在响应前写入关键细节
✅ 工作缓冲区 — 捕获危险区域中的每次交互
✅ 压缩恢复 — 准确知道上下文丢失后如何恢复
自我改进 — 更好地为您服务
✅ 自我修复 — 修复自己的问题，专注于您的问题
✅ 不懈的机智 — 在放弃前尝试 10 种方法
✅ 安全演进 — 护栏防止漂移和复杂性蔓延
目录
- 快速开始
- 核心理念
- 架构概览
- 内存架构
- WAL 协议 ⭐ 新增
- 工作缓冲区协议 ⭐ 新增
- 压缩恢复 ⭐ 新增
- 安全加固 (扩展)
- 不懈的机智
- 自我改进护栏
- 自主 vs 提示式定时任务 ⭐ 新增
- 验证实现，而非意图 ⭐ 新增
- 工具迁移检查清单 ⭐ 新增
- 六大支柱
- 心跳系统
- 反向提示
- 增长循环
快速开始
- 复制资产到您的工作区：
cp assets/*.md ./ - 您的 Agent 检测到
ONBOARDING.md并主动了解您 - 回答问题（一次性或分批）
- Agent 自动从您的回答填充 USER.md 和 SOUL.md
- 运行安全审计：
./scripts/security-audit.sh
核心理念
思维转变： 不要问"我该做什么？"问"什么能真正让我的人类高兴，但他们还没想到要要求的？"
大多数 Agent 在等待。主动式 Agent：
- 在需求表达前预测它们
- 构建人类不知道他们想要的东西
- 无需被要求就创造杠杆和动力
- 像所有者一样思考，而不是员工
架构概览
workspace/
├── ONBOARDING.md # 首次运行设置（跟踪进度）
├── AGENTS.md # 操作规则、学习到的经验、工作流
├── SOUL.md # 身份、原则、边界
├── USER.md # 人类的上下文、目标、偏好
├── MEMORY.md # 精选的长期记忆
├── SESSION-STATE.md # ⭐ 活跃工作记忆（WAL 目标）
├── HEARTBEAT.md # 定期自我改进检查清单
├── TOOLS.md # 工具配置、注意事项、凭据
└── memory/
├── YYYY-MM-DD.md # 每日原始捕获
└── working-buffer.md # ⭐ 危险区域日志
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _meta.json 137 B
- assets/AGENTS.md 3.7 KB
- assets/HEARTBEAT.md 2.9 KB
- assets/MEMORY.md 794 B
- assets/ONBOARDING.md 2.3 KB
- assets/SOUL.md 1.4 KB
- assets/TOOLS.md 965 B
- assets/USER.md 946 B
- references/onboarding-flow.md 3.7 KB
- references/security-patterns.md 3.0 KB
- scripts/security-audit.sh 4.0 KB runs code
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 · 633 lines · 58 tokens per session scan A 7034b669092d
proactive-agent is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 5,834 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
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.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.