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 luna-jmy/thinkdokit-skills --skill llmwiki-searchgit clone --depth 1 https://github.com/luna-jmy/thinkdokit-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/luna-jmy/thinkdokit-skills/llmwiki-search)<a href="https://agentmods.dev/skills/luna-jmy/thinkdokit-skills/llmwiki-search"><img src="https://agentmods.dev/badge/skills/luna-jmy/thinkdokit-skills/llmwiki-search/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-search"><img src="https://agentmods.dev/badge/skills/luna-jmy/thinkdokit-skills/llmwiki-search.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 | $0.00078 | $0.01054 |
| Opus 5 | $0.00039 | $0.00527 |
| Sonnet 5 | $0.00016 | $0.00211 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
llmwiki-search 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.
What it actually says
LLM Wiki 检索
围绕已经沉淀到 wiki/ 的知识库回答问题，让答案建立在“已整理的知识”上，而不是每次重新从原始来源开始。
目标
- 找到与问题最相关的 wiki 页面
- 综合多个页面里的信息并直接回答问题
- 标出引用来源和覆盖盲区
- 当答案本身很有价值时，建议沉淀回 wiki
检索优先级
1. qmd 搜索
如果 qmd 可用，优先使用：
- 词法搜索，适合精确术语
- 向量搜索，适合自然语言问题和语义相近概念
- 必要时增加一个假设性答案查询，帮助召回更隐含的内容
2. wiki/index.md
把索引当作导航层：
- 扫描标题
- 扫描一行描述
- 识别相关页面簇
3. 精确文本检索
当问题带有具体名字、缩写、标识符、年份或专有名词时：
- 在
wiki/下做精确匹配 - 把结果页作为补充证据
执行步骤
1. 解析问题
提取：
- 核心主题
- 关键术语和同义表达
- 时间范围
- 对比维度
- 目标输出形式
2. 选出候选页面
通常先选 3 到 10 个最相关页面：
- 直接匹配问题的页面
- 问题主题的上位概念页
- 关键实体页
- 最近更新过的相关页面
3. 深读并跟链
阅读候选页面时关注：
- 核心结论
- 使用了哪些来源
- 对
Books/派生页面，如页面保留了图片链接，要把这些链接视为有效上下文而不是噪音 - 默认不要求解析图片具体内容；如果当前环境支持多模态，可再按需把图片作为额外证据
- 是否存在互相印证或矛盾
- 是否通过
[[wikilinks]]指向一个必须继续读的页面
必要时沿链接追加一层深度，避免只看表面页。
4. 综合回答
回答至少要包括：
- 直接结论
- 关键依据
- 引用的 wiki 页面
- 覆盖是否充分
- 缺失了哪些信息
5. 评估是否值得沉淀
如果本次输出已经形成较稳定、复用价值高的分析，可以建议用户保存为：
wiki/comparisons/wiki/synthesis/
保存后记得更新索引和日志。所有回存的新页面如需进入复习池，只在 frontmatter tags 中保留 llmwiki；正文不要出现 #llmwiki。index.md 和 log.md 仍然例外。
输出风格
- 先给结论，再给证据
- 使用
[[页面标题]]作为 wiki 内引用 - 如果来源覆盖不足，要明确说“不够确定”
- 不要把 wiki 外的猜测伪装成已知事实
- 如果将答案沉淀为
wiki/comparisons/或wiki/synthesis/页面，只在 frontmattertags中按规则保留llmwiki
回退策略
如果 qmd 不可用：
- 先读
wiki/index.md - 再做文件级扫描和精确文本检索
- 明确告诉用户当前是”非 qmd 模式”
搜索依赖
本技能及 llmwiki 系列技能默认使用 qmd 进行词法和向量检索。如果用户未安装 qmd，应自动回退到 rag-skill 进行基于文件扫描和精确文本检索的搜索，并在输出中明确告知用户当前使用的是 rag-skill 回退模式。
推荐日志格式
在 wiki/log.md 追加：
## [YYYY-MM-DD] query | 简短问题描述
- Query: 完整问题
- Pages: [[Page A]], [[Page B]]
- Archived: wiki/synthesis/example.md
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 · 125 lines · 78 tokens per session scan A 08c343583873
llmwiki-search is a skill published in the GitHub repository luna-jmy/thinkdokit-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 1,054 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.