Borrowing it
Nothing to install: this file belongs to re0wiki/wiki-bot. 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/re0wiki/wiki-bot/main/.agents/skills/series-nav-sync/SKILL.mdgit clone --depth 1 https://github.com/re0wiki/wiki-botWrote 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/re0wiki/wiki-bot/series-nav-sync)<a href="https://agentmods.dev/skills/re0wiki/wiki-bot/series-nav-sync"><img src="https://agentmods.dev/badge/skills/re0wiki/wiki-bot/series-nav-sync/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/re0wiki/wiki-bot/series-nav-sync"><img src="https://agentmods.dev/badge/skills/re0wiki/wiki-bot/series-nav-sync.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 | $0.00040 | $0.01834 |
| Opus 5.5 | $0.00016 | $0.00734 |
| Sonnet 5.5 | $0.00008 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
series-nav-sync 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 13d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
系列导航(Tab/*)与 en 同步 SOP
系列跳转(前后集/前后卷/前后篇)全部由 Tab/* 页首标签条承担,信息框不声明
previous/next(约定见 docs/templates.md)。en 站用信息框 Previous/Next 字段 +
页底 navbox 双轨;zh 不跟随该方案,但 en 的 prev/next 链是系列结构的权威规格书。
不变量
- en 侧新增/合并/拆分系列内容后,zh 有两处不会自动跟随:
- 新搬运页不带 Tab——transferbot 只搬 en 内容,en 没有 Tab 体系;
- Tab 模板条目滞后——新话数/新卷要补进对应 Tab。
这两处的机械情形由 tab-sync 循环任务自动收敛(见下节);处理不了的进
报告页
User:IchiSanNi/tab_sync。
- transferbot 带入的
| previous/next =残留由 fix:para 常驻删行,无需处理。 - en 的合并/拆分调整要跟随(zh 拆分页结构与 en Part 结构一一对应)。
审计工具:src/tools/series_nav_audit.py
只读、匿名可达(≤50 titles/批 prop 查询),跑法:
uv run python src/tools/series_nav_audit.py
输出两项检查,全部干净时退出码 0,有待办则 1:
- 覆盖检查:en 每个 prev/next 目标的 zh 对应页 ∈ 该页 Tab 链接集
(分层 Tab 两跳判定:本页 Tab 链接的季/章总页自带下一层 Tab,如
动画:第50集经动画:第三季的 Tab 覆盖第51集)。未覆盖(页面无 Tab)→ 新搬运页待挂 Tab,或整个系列缺 Tab;未覆盖(目标不在 Tab 链接集)→ Tab 条目待补;N/A(zh 无对应页)→ en 已更新 zh 未搬运,正常待搬运状态,无需动作。
- 拆分对应检查:zh 前/中/后篇拆分页 vs en Part N(篇数一致、 前→Part 1、中→Part 2、后→末位 Part;单成员且 en 链接非 Part 页的视为 作品名后缀,如「蜜月背后篇」)。
实现要点(改动前必读):en→zh 映射用 zh 页源码的 [[en:…]] 建立(langlinks
派生表不可靠);参数值匹配用 [ \t]* 不用 \s*(\s 吃换行,空值行会吞
下一行)。子页(zh 标题与 en 链接均含 /)自身 en 页无 prev/next 时,
取 en 根页(主页面)的 prev/next、目标加相同子页后缀——短篇集第14卷/梗概
的链 = 短篇集卷链 + /Synopsis,邻居即邻居子页,挂载/补条目规则与主页面
同构(梗概子页挂 Tab/<系列>/Synopsis 变体);自身带 prev/next 的子页
(合集故事子页的故事链,如 亲竜之国/迷途子搜索记录①)仍以自身为准。
自动同步:tab-sync 循环任务
src/scripts/re0_tab_sync.py(python main.py tab-sync)每轮跑同一套审计,
对机械情形直接写入(链式收敛:最多 3 编辑轮 + 1 复核轮),其余进报告页
User:IchiSanNi/tab_sync(含拆分失配清单)。规则(全部满足才动手,否则报告):
- 挂载:en 链上有 Tab 且 en 标题系列键一致的邻居全票一致(系列键 =
掩末位数字段,季/章号保留:
Season 2 Episode #≠Season 3 Episode #, 跨季/跨章新页不会挂错上一季,进报告页等人工建模板);候选模板链接集须含 至少一个邻居页;页首须为独立 Init/To do 行块。 - 补条目:锚定检查发起页自身在模板中的条目行(next 插其后、previous
插其前);锚行全模板唯一;所在块无注释;目标与锚同词干同词尾(拆分篇
词尾归一后比较,目标自身非拆分篇);序号方向与链一致;块内有同词干
数字显示条目佐证显示文本可推导(
OVA1|OVA1类推导不出,转人工)。 - 激活占位:模板里整行注释包裹的占位条目(
<!--|[[…]]-->或带<!--暂未搬运-->前注),目标经重定向归一后已是现存内容页 → 自动去注释 并改指终态标题(显示文本保留原样)。 - 自身条目兜底:已挂 Tab 但不在其活链接集(剥除注释)→ 以自身检查的 链上邻居为锚、方向取反走补条目流程,机械不了进报告。覆盖挂载/既挂页 条目无人补的情形(邻居检查被全量链接集的注释占位判为已覆盖、en 链缺环等)。
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.
- 13d ago Changed · +29 lines 50d976a1fe54
- 1mo ago First seen · 63 lines · 40 tokens per session scan A 077192e9edfd
series-nav-sync is a skill published in the GitHub repository re0wiki/wiki-bot (5 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 1,834 once invoked, about $0.0002 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 2026-09-22.
series-nav-sync compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| series-nav-syncre0wiki/wiki-bot | Skill | 5 | 3d ago | MIT | A | 40 | Claude Code, Codex |
| rewrite-twKerberosClaw/kc_ai_skills | Skill | 79 | yesterday | MIT | A | 152 | Claude Code |
| docutranslateznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 119 | Claude Code, Codex |
| humanizer-vilonghang2004/vietnamese-humanizer | Skill | 60 | yesterday | MIT | A | 85 | Claude Code, Codex |
| grammar-checker-vilonghang2004/vietnamese-humanizer | Skill | 60 | yesterday | MIT | A | 87 | Claude Code, Codex |
| style-guide-vilonghang2004/vietnamese-humanizer | Skill | 60 | yesterday | MIT | A | 89 | Claude Code, Codex |
| translationese-cleaner-vilonghang2004/vietnamese-humanizer | Skill | 60 | yesterday | MIT | A | 93 | Claude Code, Codex |