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 rexchengm/fios-skills --skill notion-life-systemgit clone --depth 1 https://github.com/rexchengm/fios-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/rexchengm/fios-skills/notion-life-system)<a href="https://agentmods.dev/skills/rexchengm/fios-skills/notion-life-system"><img src="https://agentmods.dev/badge/skills/rexchengm/fios-skills/notion-life-system/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/rexchengm/fios-skills/notion-life-system"><img src="https://agentmods.dev/badge/skills/rexchengm/fios-skills/notion-life-system.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 | $0.00236 | $0.03484 |
| Opus 5 | $0.00118 | $0.01742 |
| Sonnet 5 | $0.00047 | $0.00697 |
| Haiku 4.5 | $0.00024 | $0.00348 |
Grade A, and why
notion-life-system 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 11d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notion 生活系统（Life System）
核心规则
把 Notion 当作一个活的个人操作系统。默认只读检查，除非用户明确要求创建、更新、移动、归档、删除或以其他方式修改 Notion 数据。
绝不从本 skill 修改数据库 schema。结构探查类任务期间绝不修改 Notion 页面。
当用户说要写入某个具体 Notion 页面，或提供了目标 Notion 页面 URL 加内容时，把这视为只对该页面的明确修改授权。除非用户明确要求替换，否则保留页面已有内容。
必备参考文件
按需加载，不一次全读：
references/notion-intake-rules.md: 处理随手输入的主路由规则，含每个数据库的场景、写入策略、可填字段、关联字段、禁填字段，以及queryDefaults（排序字段 + 展示字段）。references/notion-intake-rules.json: 入库规则的机器可读版本。创建页面、查询记录或运行数据库查询前先用它。references/notion-system-schema.md: 人类可读总览、路由表、数据库 ID、关联图、rollup 图、属性表。references/notion-system-schema.json: 精确的机器可读 schema，含所有 data source ID、数据库 page ID、属性 ID、关联目标、select/status 选项、rollup 配置和完整公式表达式。
当前快照由 数据管理 页面用 ntn CLI 生成。若用户说 Notion 结构变了，刷新它。
CLI 模式
Notion 操作用 ntn，不用浏览器自动化。
默认直连。打包脚本不再强制走代理。仅当 Notion API 调用因 TLS 或连接错误失败时，
才通过导出 NOTION_CLI_PROXY 选择走代理
（如 export NOTION_CLI_PROXY=http://127.0.0.1:1082）—— 脚本会自动识别。
ntn api v1/data_sources/<data_source_id>
数据库行查询用 data source ID：
ntn api v1/data_sources/<data_source_id>/query -d '{"page_size":10}'
页面读取或更新用 page ID：
ntn pages get <page_id>
指定页面的读写工作流，优先用打包的 helper：
~/.claude/skills/notion-life-system/scripts/notion_page_io.zsh id <page-url-or-id>
~/.claude/skills/notion-life-system/scripts/notion_page_io.zsh get <page-url-or-id> [output.md]
~/.claude/skills/notion-life-system/scripts/notion_page_io.zsh append <page-url-or-id> [content.md]
~/.claude/skills/notion-life-system/scripts/notion_page_io.zsh replace <page-url-or-id> [content.md]
append 和 replace 在调用 ntn pages update 之前，会先在 ~/.fios/notion-page-backups 下创建本地 Markdown 备份。
ntn 操作实战要点（踩过的坑，务必遵守）
- 创建页面（写记录）：
ntn api v1/pages -X POST -d '{"parent":{"type":"data_source_id","data_source_id":"<id>"},"properties":{...}}'。parent 用data_source_id（当前 API 版本 2026-03-11）；relation 填{"relation":[{"id":"<page_id>"}]}、日期带时段用{"date":{"start":"2026-06-03T14:00:00.000+08:00"}}。 - 删除/归档页面：用
ntn api v1/pages/<id> -X PATCH -d '{"in_trash":true}'。不要用ntn pages trash——非交互环境会因确认提示失败（要--yes）。 - 写入/PATCH 偶发失败要重试：ntn 偶有间歇失败（返回空/非 page，伴随 "stale cached OpenAPI spec" warning），原样重试 1–4 次通常即成功。批量写入/迁移/删除要逐项 GET 验证、失败重试——实测一批十个 PATCH 可能大半首发失败、静默漏掉。
- 解析响应前先清控制字符：ntn 返回的 JSON 常含未转义控制字符（formula 字段里的裸换行等），直接 jq/python 解析会报 "control characters must be escaped"。先
tr -d '\000-\037\177'（或 pythonre.sub(r'[\x00-\x1f\x7f]','',raw)）再解析；查询本身也偶发返回空，要重试。 - jq 后处理两个易错点：① 对象构造里中文 key 必须加引号（
{"事项":...}而非{事项:...}）；② jq 顶层不能用分号连两个表达式（会编译错）。 - select/status/multi_select 绝不臆造值：select/multi_select 塞 options 里没有的值，Notion 不报错、自动新建脏选项（污染选项库，比报错更隐蔽）；status 塞越界值则 400。一律匹配 options，匹配不到留空。
- 字段名以
intake-rules.json为准，可能含尾随空格：例如「日常打卡」指向习惯分类的 relation 字段名是习惯分类（末尾带一个空格），写错会 400「property does not exist」。
What ships with it
6 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.
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.
- 11d ago First seen · 191 lines · 236 tokens per session scan A e5b0a1d949b5
notion-life-system is a skill published in the GitHub repository rexchengm/fios-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 236 tokens to every session and 3,484 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
domain
When you want to brainstorm and check available .com domains for a new project — brand naming, aftermarket pricing (HugeDomains / Afternic / Sedo / Dan), USPTO trademark screening, and social handle availability. Built on Laura Roeder's "work backwards from availability, not from a name you fell in love with"…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
slide-deck
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
session-cleanup
Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation.…
notion-tool
Notion integration tool for searching, reading, creating, and updating pages and databases via the API. Use when: editing Notion pages, adding database rows, or searching a workspace.