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-capturegit 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-capture)<a href="https://agentmods.dev/skills/rexchengm/fios-skills/notion-life-capture"><img src="https://agentmods.dev/badge/skills/rexchengm/fios-skills/notion-life-capture/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-capture"><img src="https://agentmods.dev/badge/skills/rexchengm/fios-skills/notion-life-capture.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 | $0.00214 | $0.04507 |
| Opus 5.5 | $0.00086 | $0.01803 |
| Sonnet 5.5 | $0.00043 | $0.00901 |
| Haiku 4.5 | $0.00021 | $0.00451 |
Grade A, and why
notion-life-capture 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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notion 生活记录（Life Capture）
概述
随手说一句 → 分条 → 路由到正确的 direct_write 业务库 → 智能填好「非公式」字段 → 入库。这是和 查询 / 分析 / 设定 / 复盘 并列的「记录」动词入口。
字段权威 = notion-life-system 的 references/notion-intake-rules.json（单一事实来源）。 它由 schema 刷新脚本从用户真实 Notion 生成，含每个库的可直填字段 / 类型 / options / relation。本技能内的「高频速查卡」只是加速参考，一切以 json 为准；用户改了 Notion 属性后，多数情况靠刷新 json 即自愈，无需改本技能。
REQUIRED BACKGROUND： notion-life-system —— 复用 ntn CLI、scripts/notion_query.zsh、references/notion-intake-rules.json / .md，以及 schema 刷新三件套脚本。
何时使用（动词边界）
用本技能：把一条/多条新信息记进库。触发词 记一下 / 记一笔 / 记个 / 收藏 / 存一下 / 帮我记 / 备忘，或 "今天/刚才 + 花了/吃了/读了/想到/联系了/买了/跑了…"。
不要用于（这些是负向用例，必须分流出去）：
- 查看 / 查询 / 列出 已有记录 → notion-life-system（只读查询）
- 成体系地 设定 / 拆解 目标·规划·项目·任务 → notion-life-cascade（capture 只管零散记一条事实/事件/想法，不做向下拆解）
- 写 日/周/月 复盘叙述（今日复盘 / 周报 / 月报）→ notion-life-reflection
- 跨库 分析 / 对比 / "做得怎么样" → notion-life-insights
核心流程 —— 4 步
-
分条 —— 把输入拆成 1 条或多条待记项。"今天午饭花了 35，还读完了《原则》" = 2 条（支出事项 + 书籍阅读）。
-
路由 —— 按
notion-intake-rules的场景 / 触发词，把每条匹配到一个direct_write业务库（共 31 个）。- 命中速查卡的高频库 → 直接用卡。
- 未命中 → 读
references/notion-intake-rules.json，按各库的场景与触发词匹配。 - 命中维度库（
conditional_write）的内容 → 不直接建，转「维度库」一节处理。 - 命中只读库（
avoid_manual_write）→ 拒写并提示。
-
智能默认决策（核心 —— 明确就写，含糊才问）：
- 明确无歧义 + 纯
direct_write+ 不需关联/新建维度 → 直接写完即报。 - 需解析 relation（挂到某项目/账户/人物/分类）→ 先
scripts/notion_query.zsh <目标库>查 page_id；查到就写，查不到或多义 → 一句话确认。 - 要新建维度对象（新账户/新分类/新联系人）→ 先确认再建（见「维度库」一节）。
- 库不明确 或 缺关键直填字段 → 一句话确认，只问最少必要项。
- 明确无歧义 + 纯
-
写入与回报 ——
ntn api v1/pages -X POST（带目标 data_source_id + properties）。每条记录回报：库 / 标题 / page_id / 设置的关联 / 未解析字段。批量多条时先给一行式预览再统一写。
智能填充规则
- 日期：缺省 = 今天；"明天 / 下周二 / 周末"解析成具体日期。
- 金额 / 数字：从自然语言抽取（"花了三十五" / "35 块" → 35）。
- select / status / multi_select：拿话里的词去匹配该字段的
options（取自 json）。匹配不到就用最接近的或留空 + 提示，绝不臆造新选项。⚠️实测两者行为不同：select / multi_select 塞不存在的值，Notion 不报错、自动新建该选项 → 悄悄污染选项库（比报错更隐蔽有害）；status 塞越界值则直接 400 失败。两种都 →匹配不到必须留空，仅当用户明确说"新增『X』选项"才对 select 传新值（status 选项无法这样加）。 - relation：先
notion_query.zsh查目标库拿 page_id，不编造、不写成纯文本。归类型关联（分类/账户/类型）缺省时按「关键关联兜底」兜到「其他」(无则自动建)；身份型关联（人/项目/书）查不到才留空或问。 - title：必填，从输入提炼一个短标题。
- 绝不填：
formula/rollup/button/created_time/last_edited_time/unique_id等计算或同步字段。
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.
- 1mo ago First seen · 148 lines · 214 tokens per session scan A 9ea1669b731f
notion-life-capture is a skill published in the GitHub repository rexchengm/fios-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 214 tokens to every session and 4,507 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
context-bankruptcy
Declare bankruptcy on a long-lived AI agent's accumulated memory — audit what it currently believes, separate ground truth from stale and wrong, purge deliberately, restate the truths that survive, and log what was lost. Use when an agent keeps acting on outdated facts, contradicts itself across sessions, 'remembers'…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/)…
second-brain
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Vault defaults to…
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
context-engineering-review
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and…
memory-file-maintenance
Keep your AI memory/context file (MEMORY.md, CLAUDE.md, custom instructions) healthy over time — pruning the stale, adding the new, and keeping it sharp so your AI keeps getting you right. Use when asked review my memory file, my AI context is outdated, clean up my CLAUDE.md, or maintain my AI instructions. Produces a…