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 GYF0311/lorekit --skill wiki-removegit clone --depth 1 https://github.com/GYF0311/lorekitWrote 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/gyf0311/lorekit/wiki-remove)<a href="https://agentmods.dev/skills/gyf0311/lorekit/wiki-remove"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-remove/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/gyf0311/lorekit/wiki-remove"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-remove.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 | $0.00064 | $0.00709 |
| Opus 5.5 | $0.00026 | $0.00284 |
| Sonnet 5.5 | $0.00013 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
wiki-remove 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 1mo 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
wiki-remove
安全移除 corpus 中的一篇来源或知识页。删除语义是移动到系统回收站，不是永久删除；级联范围只按来源归因清理，不按关键词删除同主题其他知识。
When to trigger
- 用户说"删除这篇"、"移除这个知识"、"这篇过时了不要了"
- 用户说"remove"、"trash"、"丢到回收站"
- 用户给出 URL、
原料/...、知识库/摘要/...或其他 wiki 页路径并要求删除
不要触发：
- 只是标记过时、不想删除文件 → 建议改
status: archived - 要整理/合并重复页 → 先
wiki-lint或wiki-audit - 要删除外部网站内容 → lorekit 只能移除本地 corpus 内容
Workflow
1. 先生成影响报告
永远先跑 dry-run：
lorekit remove "<target>"
报告会列出：
- 将移动到系统回收站的文件/目录
- 将修改的页面（Timeline 行、frontmatter
sources、source_count） Compiled Truth中疑似依赖该来源、需要人工复核的段落
2. 向用户确认
把报告摘要给用户，明确说明：
- 删除会进入系统回收站，可恢复
- 只会移除这篇来源贡献的信息
- 同主题其他来源（例如其他 harness 文章）不会被删除
Compiled Truth不会自动改写，只报告疑似影响
3. 用户确认后执行
lorekit remove "<target>" --apply
--apply 会：
- 先创建 snapshot
- 移除明确来源贡献的登记
- 把目标文件/目录移动到系统回收站
- 刷新
index.md/_INDEX.md - 跑 lint 报告
Output format
remove 影响报告：
- 回收站：N 项
- 修改页面：N 页
- 人工复核：N 段 Compiled Truth
确认后我再执行：
lorekit remove "<target>" --apply
执行后：
已移入系统回收站：
- <path>
snapshot：<path>
sync：完成
lint：<N> issue(s)
铁律
- 不用
rm，不做永久删除。 - 不按关键词级联删除，只按明确来源 wikilink /
sources归因清理。 - 删除某篇 harness 文章时，不能删除其他 harness 来源支撑的
harness概念页。 Compiled Truth缺少精确来源标记时，只报告疑似影响，不自动改写。
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.
- 1mo ago First seen · 90 lines · 64 tokens per session scan A 05b6127769fd
wiki-remove is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 709 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
openclaw-memory-tencentdb-setup
A setup guide for installing, configuring, and checking a TencentDB memory plugin in OpenClaw, an agent environment.
kb-workflow
Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings. Teaches the token-efficient retrieval pattern and self-learning loop.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
memory-management
Two-tier memory that makes the agent a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so the agent understands requests like a colleague would. A small personal working-memory file for the hot cache, and the team's Hexis knowledge base (Glossary, People, Projects, How we…