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 malue-ai/dazee-small --skill screenpipegit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote 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/malue-ai/dazee-small/screenpipe)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/screenpipe"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/screenpipe/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/malue-ai/dazee-small/screenpipe"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/screenpipe.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 | $0.00038 | $0.01061 |
| Opus 5 | $0.00019 | $0.00531 |
| Sonnet 5 | $0.00008 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
screenpipe 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.
curl "http://localhost:3030/search?q=关键词&content_type=ocr&limit=10" What it actually says
Screenpipe — AI 屏幕记忆
24/7 记录屏幕内容和音频，让 AI 拥有「记忆」。用户可以回溯任何看过的内容、说过的话、用过的应用。所有数据本地存储，隐私优先。
使用场景
- 用户说「我昨天在哪个网页上看到那篇关于…的文章？」
- 用户说「上周开会时谁说了什么？」
- 用户说「今天我在电脑上花了多少时间在哪些应用上？」
- 用户说「帮我找一下之前看到的那个代码片段」
- 用户说「我这周总共写了多少代码？看了多少邮件？」
- 结合每日简报类 Skill（如已启用）自动生成基于真实屏幕活动的每日回顾
前置条件
- 安装 Screenpipe：https://screenpi.pe/ （macOS / Windows / Linux）
- 启动 Screenpipe 后，本地 API 运行在
http://localhost:3030 - Screenpipe 内置 MCP Server，通过 MCP 协议自动连接
执行方式
通过 MCP 工具调用
Screenpipe MCP 提供以下核心能力：
搜索屏幕内容（OCR 文字）
工具: search_screen_content
参数:
query: "搜索关键词"
start_time: "2026-02-25T00:00:00Z" # 可选，时间范围
end_time: "2026-02-26T00:00:00Z"
app_name: "Chrome" # 可选，限定应用
limit: 10
搜索音频转录
工具: search_audio_transcripts
参数:
query: "会议讨论内容"
start_time: "2026-02-25T09:00:00Z"
limit: 5
获取应用使用统计
工具: get_app_usage
参数:
start_time: "2026-02-25T00:00:00Z"
end_time: "2026-02-26T00:00:00Z"
直接 API 调用（备选）
如果 MCP 不可用，可通过 HTTP API 访问：
# 搜索屏幕 OCR 内容
curl "http://localhost:3030/search?q=关键词&content_type=ocr&limit=10"
# 搜索音频转录
curl "http://localhost:3030/search?q=关键词&content_type=audio&limit=5"
# 获取最近活动
curl "http://localhost:3030/search?limit=20&start_time=2026-02-25T00:00:00Z"
典型工作流
回溯查找：
用户：我昨天下午看到一个很好的 Python 库，名字里有 pipe
→ 搜索 OCR 内容，时间限定为昨天下午
→ 返回匹配的屏幕截图和上下文
→ 告诉用户：你在 Chrome 中浏览了 GitHub 上的 xxx 项目（14:32）
会议回顾：
用户：今天上午的会议讨论了什么？
→ 搜索音频转录，时间限定为今天上午
→ 提取关键讨论点和行动项
→ 结构化输出会议摘要
时间追踪：
用户：我今天在各个应用上花了多少时间？
→ 获取应用使用统计
→ 生成时间分布报告（可结合图表生成类 Skill 生成图表）
与其他 Skills 的协作
| 组合 | 效果 |
|---|---|
| screenpipe + 每日简报类 Skill（如已启用） | 基于真实屏幕活动生成每日回顾 |
| screenpipe + meeting-insights-analyzer | 自动回顾会议录音和屏幕共享内容 |
| screenpipe + habit-tracker | 基于真实应用使用数据追踪习惯 |
| screenpipe + pomodoro | 回顾专注时段内的实际工作内容 |
输出规范
- 搜索结果附上时间戳和来源应用
- 涉及屏幕内容时描述上下文（哪个应用、哪个页面）
- 音频转录标注说话人（如果 Screenpipe 提供了说话人标签）
- 时间统计使用表格/图表呈现
- 尊重隐私：不主动提及用户未询问的敏感内容
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 · 124 lines · 38 tokens per session scan A e128704f42ac
screenpipe is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,061 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 2026-09-03.
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.