Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/luna-jmy/thinkdokit-skillsnpx agentmods add skills/luna-jmy/thinkdokit-skills/llmwiki-ingestWrote 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/luna-jmy/thinkdokit-skills/llmwiki-ingest)<a href="https://agentmods.dev/skills/luna-jmy/thinkdokit-skills/llmwiki-ingest"><img src="https://agentmods.dev/badge/skills/luna-jmy/thinkdokit-skills/llmwiki-ingest/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/luna-jmy/thinkdokit-skills/llmwiki-ingest"><img src="https://agentmods.dev/badge/skills/luna-jmy/thinkdokit-skills/llmwiki-ingest.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 | $0.00077 | $0.02216 |
| Opus 5 | $0.00039 | $0.01108 |
| Sonnet 5 | $0.00015 | $0.00443 |
| Haiku 4.5 | $0.00008 | $0.00222 |
Grade A, and why
llmwiki-ingest 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki 摄取
把原始来源中的新信息编译进 wiki/,让知识库持续积累,而不是每次查询都重新从原文开始。
目标
- 发现新增、变更、删除的来源文件
- 为来源创建摘要页
- 更新相关实体页、概念页、案例页
- 对
Books/默认按“每个正文章节 = 一个 source”摄取,而不是整本书一个 source - 维护
[[wikilinks]]和反向链接 - 更新
wiki/index.md、wiki/.manifest.json、wiki/log.md
输入范围
默认扫描这些来源目录:
300 Resources/Books/200 Areas/
如果用户明确指定文件或子目录,就只处理指定范围。
工作原则
- 原始来源只读,不修改
- 优先增量更新,而不是重建整个 wiki
manifest负责追踪来源哈希和已影响的 wiki 页面- 只保留有信息密度的摘要,不把原文无差别复制进 wiki
- 当多个来源谈到同一实体或概念时,优先合并进已有页面
#llmwiki只放在 frontmattertags里,不出现在正文;是否保留该标签优先按原始来源目录决定- 对书籍来源,先读取书籍
moc,按目录识别正文章节;跳过致谢、目录、附录、索引、参考文献等非正文块 - 书籍来源的抽取粒度为章节级:每个正文章节单独提取
stories、entities、concepts
清单格式建议
wiki/.manifest.json 可使用这种结构:
{
"300 Resources/example.md": {
"md5": "a1b2c3...",
"ingested": "2026-04-08",
"wiki_pages": [
"sources/example.md",
"entities/some-entity.md",
"concepts/some-concept.md"
]
}
}
执行步骤
1. 找出需要处理的来源
- 读取
wiki/.manifest.json - 扫描候选来源目录
- 计算文件哈希
- 分出四类状态:
- 新增
- 已修改
- 未变化
- 已删除
如果用户给了明确路径,可以跳过自动检测,直接强制重摄取目标范围。
2. 读取当前 wiki 状态
在处理来源前,先了解已有知识结构:
- 读取
wiki/index.md - 按需搜索可能受影响的现有页面
- 找出应复用或更新的实体页、概念页、案例页
3. 处理单个来源
对每个来源执行:
3.1 读取与分析
- 如果来源在
Books/:- 先读取该书
moc,确定章节顺序和章节边界 - 仅处理正文章节;跳过致谢、目录、附录、索引、参考文献等非正文内容(以及语义上等价的章节)
- 按“每章节一个 source”处理,不把整本书合并成一个 source
- 先读取该书
- 读取来源正文
- 识别关键实体、概念、案例、数据点、结论、矛盾、关系
- 如来源包含图片,默认不要求解析图片具体内容
- 对
Books/来源,图片链接本身属于重要上下文:即使当前只用纯语言模型,也应把图片链接保留到 source 页面 - 如果当前环境支持多模态,可再按需把这些图片作为额外上下文;如果不支持,也不要因为无法看图而跳过图片链接
3.2 创建或更新 source 页面
写入 wiki/sources/<source-name>.md,建议包含:
- 来源路径
- 摄取日期
- 2 到 4 段高密度摘要
- 要点列表
- 提及的实体
- 相关概念
- 相关案例
- 如原始来源含重要图片,增加“相关图片”或等价小节,保留图片链接或嵌入链接
- frontmatter
tags中按需要保留llmwiki
对于 Books/,<source-name> 应体现“书名 + 章节名”或等价唯一标识,确保每章可独立追踪、回链和增量重摄取。
3.3 创建或更新 entity 页面
放在 wiki/entities/,用于人物、公司、产品、工具、组织、地点等相对稳定对象。
页面如需进入复习池,应在 frontmatter tags 中包含 llmwiki,正文不要出现 #llmwiki。
3.4 创建或更新 concept 页面
放在 wiki/concepts/,用于原理、方法、范式、框架、模型、主题。
页面如需进入复习池,应在 frontmatter tags 中包含 llmwiki,正文不要出现 #llmwiki。
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 · 255 lines · 77 tokens per session scan A d9d07667b660
llmwiki-ingest is a skill published in the GitHub repository luna-jmy/thinkdokit-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 2,216 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.