Borrowing it
Nothing to install: this file belongs to iyuenan3/worklog-kit. 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/iyuenan3/worklog-kit/main/.agents/skills/worklog-maintain/SKILL.mdgit clone --depth 1 https://github.com/iyuenan3/worklog-kitWrote 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/iyuenan3/worklog-kit/worklog-maintain)<a href="https://agentmods.dev/skills/iyuenan3/worklog-kit/worklog-maintain"><img src="https://agentmods.dev/badge/skills/iyuenan3/worklog-kit/worklog-maintain/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/iyuenan3/worklog-kit/worklog-maintain"><img src="https://agentmods.dev/badge/skills/iyuenan3/worklog-kit/worklog-maintain.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 | $0.00132 | $0.01679 |
| Opus 5.5 | $0.00053 | $0.00672 |
| Sonnet 5.5 | $0.00026 | $0.00336 |
| Haiku 4.5 | $0.00013 | $0.00168 |
Grade A, and why
worklog-maintain 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
worklog-maintain：vault 记忆维护
ingest 是增量编译器，只看见当晚窗口；本 skill 是批处理维护工序（GC + 碎片整理），处理跨月才显形的腐坏。与用户交互语言跟随其消息语言，写入 vault 的内容按 config
language。
授权模型（跟触发方式走，无全局开关）
- 交互触发（用户此刻发的消息，含「处理体检项」）= 明示授权：wiki / todos 类修复直接做，git 可回滚，无需逐项确认。
- 定时 / 无人值守触发（schedule / cron / headless 会话），或用户明说「报告模式」= 只跑体检出报告，不动任何文件。判不准当无人值守处理（宁可少动）。
红线
diaries/永不触碰：历史日记只读，连标点都不改（它是全系统的事实源）。- wiki 只做合并 / 归档 / 重链，删除留给人：归档 =
git mv进wiki/archive/；合并后旧名留 alias 存根（见修复配方），绝不让历史日记里的 wikilink 变幽灵。 - TODO 僵尸只标记不关闭（出厂默认）：加
#todo/stale与一句标注；打勾或删除是用户的决定。
原则
证据先行（不信旧报告与日记提醒行的数字，现场重跑体检）；每次只处理体检列出的明确问题（清单之外的「顺手优化」不做）；不为整洁删除仍有价值的内容（价值拿不准 → 归档而非删除，或留给用户并说明）。
流程
1. 现场体检
python3 .agents/skills/worklog-lint/scripts/lint.py --health
🩺 0 项待维护→ 报告「vault 健康，无需维护」，结束。- 有待维护项 → 逐项列给用户看。无人值守模式到此为止（报告即产出）；交互模式继续。
2. 按腐坏类型分批修复（每类修完立即一个 commit）
| 体检项 | 修复配方 |
|---|---|
| 状态漂移 | 读该项目页 + 最近提及它的几篇日记，把项目页现状与决策日志补到与日记一致，刷新 last_updated；页与日记冲突以日记为准（日记是事实源） |
| 孤儿页 | 先判断价值：仍有价值 → 从相关 wiki 页补一条入链；已完结 / 过时 → git mv 入 wiki/archive/（不删除）；拿不准 → 不动，小结里列出留给用户 |
| 实体分裂 | 选 canonical 名（优先已有项目页的名字），把 wiki 与 todos 里的变体 wikilink 全部重链到 canonical（diaries 一个都不改）；变体若自有页面，内容并入 canonical 后原页改为 alias 存根：frontmatter 写 alias_of: <canonical> + 正文一行指针（存根让历史日记链接仍可解析，体检也不再把它算分裂）；候选是机械归一化产物，中英别名等语义级同一性由你判断，误报直接跳过并在小结说明 |
| 膨胀 | 页面超体积 → 历史段落移入 wiki/archive/<页名>-<年份>.md，原页留一行指针；决策日志超条数 → 老条目移入 wiki/archive/<slug>-decisions.md，原段保留最近条目 + 一行指针 |
| TODO 年龄 | 判断前先挖证据：读整行原文（不信 --health 截断串）+ 该 TODO 关联项目的 git log 与项目记忆（项目页决策日志，以及项目规则指向的专用 memory 或通用 stash memory），别只按 checkbox 文字判：表面「N 周没动」的可能早已完成、或正是当前活跃焦点。已完成 → 原位勾 - [x] + 标 ✅ <date> + 列证据（commit / 文件），不移；仍有效 / 跟进类 / 含未来 📅 的 snooze 项 → 不动、不 #todo/stale；仅确无跟进意图的废弃项、先把候选列给用户确认后才加 #todo/stale + 一句标注，不关闭（已标记的体检不再重复报，等用户处置） |
commit：每类一个，格式 maintain: <类型>（<N> 项）（en vault 用 maintain: <type> (<N> items)），正文列触及文件；尾行 Co-Authored-By 约定与 ingest D.4 相同。
3. 验收 + 收尾
- 重跑
lint.py（正误节必须 0 must-fix）+lint.py --health（目标归零；因「留给用户」未归零的逐条说明） - 写作门：对本次改动的 md 跑标点门（仅 zh）与日期门（与 ingest D.4 同规）
- push 一次：前置 visibility 检测（与 ingest D.4 同规）；检测不可用则跳过检测照常 push
- 维护小结：每类修了几项 / 归档了什么 / 留给用户什么及原因 / 阈值是否建议调整（只建议，不代改 config）。维护记录不做额外记账：maintain commit 由当晚 ingest 的 vault 内部源自然收录进日记。
What ships with it
1 file 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.
- 2mo ago First seen · 60 lines · 132 tokens per session scan A c1ab3930fdd4
worklog-maintain is a skill published in the GitHub repository iyuenan3/worklog-kit (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 132 tokens to every session and 1,679 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 2026-08-30.
worklog-maintain compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| worklog-maintainiyuenan3/worklog-kit | Skill | 11 | 3mo ago | Apache-2.0 | A | 132 | Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |