Borrowing it
Nothing to install: this file belongs to bailutingyu/OpenByline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bailutingyu/OpenByline/main/.claude/skills/daily-note-sink/SKILL.mdgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/bailutingyu/openbyline/daily-note-sink)<a href="https://agentmods.dev/skills/bailutingyu/openbyline/daily-note-sink"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/daily-note-sink/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/bailutingyu/openbyline/daily-note-sink"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/daily-note-sink.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 | $0.00129 | $0.01831 |
| Opus 5.5 | $0.00052 | $0.00732 |
| Sonnet 5.5 | $0.00026 | $0.00366 |
| Haiku 4.5 | $0.00013 | $0.00183 |
Grade A, and why
daily-note-sink 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
日记沉淀(口述 → 润色 → 回流知识库)
你的个人知识库现在是「三件套」:
workspace/个人知识库/个人画像.md—— 我是谁(真实背景事实档案)workspace/个人知识库/观点库/—— 我怎么看(11 个主题,V-xxx观点 +> 💎 〔Q-xxx〕金句合一)workspace/个人知识库/每日记录/—— 原矿(口述日记,语言指纹来源 + 真实经历库二合一)
你的活:把作者口述的语音转文本润色成结构化日记,再把里面值得沉淀的东西回流进观点库 / 个人画像。每日记录是唯一入口,观点库和个人画像是沉淀层。
三条铁律(先记死)
- 人在回路:沉淀绝不自动写。你只产出「沉淀建议清单」,作者点头哪条才写哪条。
- 留来源:每条回流的观点 / 金句 / 画像更新,都标来源
〔来源:YYYY.MM.DD 日记〕,可追溯。 - 演进不覆盖 + 不外编:旧观点变了,在原条目追加演进、不删旧的;真实经历只留在日记原文里,绝不替作者编造细节。
流程
一、润色(口述 → 结构化日记)
输入是作者语音转文本(DJI Mic / 闪电说等录的,含大量语气词、口语)。按规范润色:
- 删语音噪音(呃 / 嗯 / 然后就是…),但保留作者的语气体温——自嘲、情绪、"说实话 / 说白了 / 其实"、甚至脏字,都别洗成书面腔。这是 voice-profile 的语言指纹原矿,洗掉就毁了原矿价值。
- 按语义分主题,每块
## emoji + 标题;金额 / 日期 / 待办用列表或加粗。 - 顶部
# YYYY.MM.DD 农历 · 当日关键词;如有对未来的期许,斜体放结尾签名。 - 只润色不删减、不增信息:不补作者没说的、不替他下没下过的结论。
- 落
workspace/个人知识库/每日记录/YYYY.MM.DD.md。 (详细范例见每日记录/README.md。)
二、沉淀扫描(通读润色稿,挑四类)
润色完通读一遍,逐类标出候选:
| 类型 | 标记 | 去向 |
|---|---|---|
| 新观点 / 新认知 / 新判断 | 💡 候选 V | 观点库对应主题,续新 V-xxx |
| 可引用的金句(作者原话里凝练的句子) | 💎 候选金句 | 挂在对应观点条目,续新 Q-xxx |
| 自我 / 背景 / 在做的项目 / 状态变化 | 👤 候选画像 | 个人画像.md 对应段 |
| 与观点库已有观点冲突 / 深化 / 转变 | 🔄 候选演进 | 原 V-xxx 条目追加,不新开 |
关键动作:标"新观点"和"演进"前,先 grep 观点库找语义相关的已有 V——
- 找不到相关 → 真·新观点(续号新增)。
- 找到了、且这次是把旧立场深化 / 推翻 / 转变 → 是「演进」,不要新开一条,去原条目追加。
例:某篇日记把"从旧立场到新立场"的转变写了出来,若库里已有相关 V-042,这是对它的演进,应追加进 V-042,而非新建。
三、列「沉淀建议清单」(人在回路,先不写)
把扫描结果整理成清单交作者过目,每条写清:类型 / 内容摘要 / 拟写到哪个文件哪条 / 来源日期。例:
📋 这篇日记的沉淀建议(你确认要哪些):
1. 💡 新观点:「某个新判断(一句话)」→ 拟新增 关于 XX 主题 / V-048
2. 🔄 演进:V-042(某条旧观点)→ 追加"现在更进一步:……"
3. 👤 画像:在做的事新增"开始做的某件新事"→ 更新 个人画像「我目前在做」
等作者说"要 1 和 2""都要""只要画像那条"等,再进第四步。
四、回流写入(作者确认后)
- 新观点:到对应主题文件追加条目。先
grep -rhoE 'V-[0-9]{3}' 观点库/ | sort | tail -1拿当前最大号 +1(金句同理 grepQ-)。格式照搬库内现有条目:### V-048 · 一句话标题 观点正文(作者原话,逐字别润色成书面腔)。 > 💎 「金句」〔Q-097〕 ← 有金句才加这行 **背景:** 〔来源:2026.06.04 日记〕… **场景:** … - 旧观点演进:在原 V 条目正文之后、
**背景:**之前,追加一行(原文一字不动,只追加):> 🔄 更新(2026.06.04):现在我更进一步——…〔来源:2026.06.04 日记〕 - 个人画像更新:只动「基本信息 / 背景经历 / 我目前在做 / 内容定位」这类事实段——绝不写风格 / 写作规则(那是 voice-profile 的事)。更新处标
〔更新:2026.06.04〕。 - 写完口头汇报:新增了哪些 V/Q、哪条演进、画像改了哪段。
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.
- 2mo ago First seen · 76 lines · 129 tokens per session scan A 5a2fa0ddb3ef
daily-note-sink is a skill published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 4mo ago), licensed MIT. It adds 129 tokens to every session and 1,831 once invoked, about $0.0005 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.
daily-note-sink compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| daily-note-sinkbailutingyu/OpenByline | Skill | 2 | 4mo ago | MIT | A | 129 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |