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 chengkj99/kj-skills --skill wiki-doc-sinkgit clone --depth 1 https://github.com/chengkj99/kj-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/chengkj99/kj-skills/wiki-doc-sink)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/wiki-doc-sink"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/wiki-doc-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/chengkj99/kj-skills/wiki-doc-sink"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/wiki-doc-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 | $0.00141 | $0.01543 |
| Opus 5 | $0.00071 | $0.00772 |
| Sonnet 5 | $0.00028 | $0.00309 |
| Haiku 4.5 | $0.00014 | $0.00154 |
Grade A, and why
wiki-doc-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 12d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki 文档沉淀（个人知识库）
范围边界
- 本 skill 仅处理个人
<WIKI_ROOT>，不处理组织/公司业务专用 Wiki。 - 若用户要沉淀的是业务域 Wiki，停止并按其本机已配置的业务 Wiki 规则执行（常见位置：
~/.claude/rules/）。
Fork 与路径配置（必读）
本 skill 的知识库根目录须由你自行指定（下称 <WIKI_ROOT>）。将下文所有 <WIKI_ROOT> 替换为你的 Wiki 仓库在本机的绝对路径。
维护者示例曾使用路径 .../kj-llm-wiki；开源使用者请改为自己的目录。
执行前必读（按顺序 Read）
- 本 skill 目录下：
references/personal-wiki-bridge.mdreferences/routing-notes.md
- 用户环境（若存在）：
~/.claude/CLAUDE.md（全局WIKI_ROOT等）
- Wiki 仓库（以磁盘为准）：
<WIKI_ROOT>/SCHEMA.md<WIKI_ROOT>/CLAUDE.md
何时写入 Wiki（默认）
当对话出现以下或同义表述，且意图为个人知识库 / Wiki（不是当前项目的 README、不是用户明确说的「就写在这个 repo」）时：
- 「沉淀内容到文档」
- 「沉淀到文档」「沉淀到知识库」
- 「把内容沉淀成文档」
- 「个人 wiki」「个人知识库」
- 其他明确表达「要把当前讨论/结论写成可长期维护的文档」且指向个人 Wiki
默认应执行：按 <WIKI_ROOT> 仓库规范写入知识库，不要默认写当前打开项目的 docs/ 或随意新建说明文件。
落点含糊时，按 references/routing-notes.md 先问一句（个人 Wiki vs 当前项目 docs/）。
何时写入当前项目
仅当用户同时或随后明确指定例如：「写在当前项目」「放在本仓库 docs/...」「只更新 README」等——按用户最后一次明确指定的落点执行。
查询流程（检索个人 Wiki 时）
- 读取
<WIKI_ROOT>/wiki/index.md定位条目。 - 打开对应
wiki/concepts/、wiki/analysis/、wiki/synthesis/等页面。 - 综合多页作答；可用
[[wiki-link]]标明关联。 - 不要修改
raw/（例外以<WIKI_ROOT>/CLAUDE.md为准）。
知识库根目录与必读规范
| 路径 | 用途 |
|---|---|
<WIKI_ROOT>/ |
个人 LLM Wiki 仓库根目录 |
<WIKI_ROOT>/SCHEMA.md |
目录结构、页面格式、raw/wiki 边界 |
<WIKI_ROOT>/CLAUDE.md |
Ingest / Analysis / Synthesis / Query / Lint 步骤与硬性约束 |
执行要点（摘要）
raw/只读：不得擅自编辑、删除、移动raw/内已有文件；例外以该仓库CLAUDE.md与.cursor/rules/为准。- 可写主战场为
wiki/：按素材类型在wiki/sources/、wiki/concepts/、wiki/entities/、wiki/analysis/、wiki/synthesis/等路径创建或更新页面，格式遵循SCHEMA.md。 - 索引与日志：新建或重要更新后，按需更新
wiki/index.md；在wiki/log.md仅追加记录。 - 语言与日期：摘要与解析以中文为主；日期使用用户环境中的当前日期，不臆造。
对 Agent 的操作顺序（写入）
- Read
references/两篇 +SCHEMA.md+CLAUDE.md，确定页面类型与路径命名。 - 在
wiki/下创建或更新页面；不触碰raw/除非该仓库规则允许。 - 按需更新
wiki/index.md；向wiki/log.md追加一行说明。 - 若用户其实要的是项目内文档，停止并按用户指定路径写入。
- 写入后在回复中注明：实际写入的绝对路径与库名（个人 Wiki），便于用户核对。
What ships with it
3 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.
- 12d ago First seen · 94 lines · 141 tokens per session scan A d0f38563bdcd
wiki-doc-sink is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 141 tokens to every session and 1,543 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
obsidian
Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.
loopx-doc-registry
Use when a connected LoopX project is asked to read, remember, record, index, register, or use a durable project material such as a Lark/wiki/design doc, research note, SOP, owner packet, migration report, benchmark paper, or external material source. Use even when the user does not mention LoopX or doc registry.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
excel-author
Create and edit Excel (.xlsx) workbooks with openpyxl. Supports formulas, charts, formatting, and data analysis.
ppt-author
Create and edit PowerPoint (.pptx) presentations programmatically. Requires python-pptx.
ocr-document
Extract text from PDFs, images, and scanned documents. Uses pymupdf (local) or optional cloud OCR APIs.