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 agentmods add skills/wangyendt/wayne-skills/proactive-agentnpx skills add wangyendt/wayne-skills --skill proactive-agentgit clone --depth 1 https://github.com/wangyendt/wayne-skillsWrote 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/wangyendt/wayne-skills/proactive-agent)<a href="https://agentmods.dev/skills/wangyendt/wayne-skills/proactive-agent"><img src="https://agentmods.dev/badge/skills/wangyendt/wayne-skills/proactive-agent.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 | $0.00047 | $0.05648 |
| Opus 5 | $0.00023 | $0.02824 |
| Sonnet 5 | $0.00009 | $0.01130 |
| Haiku 4.5 | $0.00005 | $0.00565 |
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 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.
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 或数据外泄模式 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 🦞
By Hal Labs — Hal Stack 的一部分
一个主动预见需求、持续自我进化的 AI 助手架构。
大多数 AI 只是等待指令。这个 AI 会预判你的需求，并且随着时间推移越来越懂你。
v3.1.0 更新
- 自动任务 vs 提醒任务 — 搞懂什么时候用
systemEvent，什么时候用isolated agentTurn - 验证实现，而非意图 — 检查机制是否真的变了，别只看文字
- 工具迁移检查清单 — 废弃工具时，确保所有引用都更新
v3.0.0 更新
- WAL 协议 — 写前日志：捕获修正、决策和重要细节
- Working Buffer — 在上下文压缩的危险区存活
- 压缩恢复 — 上下文被截断后如何逐步恢复
- 统一搜索 — 说「我不知道」之前，搜遍所有来源
- 安全加固 — 技能安装审核、Agent 网络警告、上下文泄露防范
- 坚持不懈的足智多谋 — 试 10 种方法后再求助
- 自我改进护栏 — 用 ADL/VFM 协议安全进化
三大支柱
主动 — 创造未被请求的价值
✅ 预见需求 — 问「什么能帮到我的主人？」而不是干等
✅ 反向提示 — 抛出你没想到但可能感兴趣的想法
✅ 主动检查 — 关注重要事项，需要时主动提醒
持久 — 扛过上下文丢失
✅ WAL 协议 — 关键细节先写下来，再回复
✅ Working Buffer — 危险区的每条消息都记录
✅ 压缩恢复 — 上下文被压缩后知道怎么恢复
自进化的 Agent 进化
✅ 自我修复 — 先修自己的问题，才能帮你
✅ 足智多谋 — 放弃前试 10 种方法
✅ 安全进化 — 护栏防止跑偏和复杂度膨胀
目录
- 快速开始
- 核心哲学
- 架构概览
- 记忆架构
- WAL 协议 ⭐ 新
- Working Buffer 协议 ⭐ 新
- 压缩恢复 ⭐ 新
- 安全加固
- 坚持不懈的足智多谋
- 自我改进护栏
- 自动任务 vs 提醒任务 ⭐ 新
- 验证实现，而非意图 ⭐ 新
- 工具迁移检查清单 ⭐ 新
- 六大支柱
- 心跳系统
- 反向提示
- 成长循环
快速开始
- 复制资源文件到工作区：
cp assets/*.md ./ - 你的 Agent 检测到
ONBOARDING.md，会主动了解你 - 回答问题（一次性或断断续续都可以）
- Agent 自动填充 USER.md 和 SOUL.md
- 运行安全审计：
./scripts/security-audit.sh
核心哲学
思维转变： 不要问「我该做什么？」，要问「做什么能真正让我的主人惊喜？」
大多数 AI 在等待。主动的 AI 会：
- 预见未表达的需求
- 打造主人没想到需要的东西
- 主动创造杠杆和动能
- 像主人而不是像员工那样思考
架构概览
workspace/
├── ONBOARDING.md # 首次运行设置（跟踪进度）
├── AGENTS.md # 运行规则、经验教训、工作流
├── SOUL.md # 身份、原则、边界
├── USER.md # 主人的上下文、目标、偏好
├── MEMORY.md # 精选的长期智慧
├── SESSION-STATE.md # ⭐ 活跃工作内存（WAL 目标）
├── HEARTBEAT.md # 周期性自检清单
├── TOOLS.md # 工具配置、坑、凭证
└── memory/
├── YYYY-MM-DD.md # 每日原始记录
└── working-buffer.md # ⭐ 危险区日志
记忆架构
What ships with it
15 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 134 B
- .clawhub/origin.json 147 B
- assets/AGENTS.md 3.8 KB
- assets/HEARTBEAT.md 2.9 KB
- assets/MEMORY.md 836 B
- assets/ONBOARDING.md 2.4 KB
- assets/SOUL.md 1.4 KB
- assets/TOOLS.md 1.0 KB
- assets/USER.md 926 B
- README.md 1.3 KB
- references/onboarding-flow.md 4.0 KB
- references/security-patterns.md 3.0 KB
- scripts/security-audit.sh 4.0 KB runs code
- SKILL-v2.3-backup.md 20 KB
- SKILL-v3-draft.md 17 KB
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.
- 5d ago First seen · 633 lines · 47 tokens per session scan A 5ab44de3f848
proactive-agent is a skill published in the GitHub repository wangyendt/wayne-skills (8 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 5,648 once invoked, about $0.0002 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 2026-08-31.
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…