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 agentmods add skills/gyf0311/lorekit/wiki-filebacknpx skills add GYF0311/lorekit --skill wiki-filebackgit 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-fileback)<a href="https://agentmods.dev/skills/gyf0311/lorekit/wiki-fileback"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-fileback.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.01767 |
| Opus 5 | $0.00030 | $0.00883 |
| Sonnet 5 | $0.00012 | $0.00353 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
wiki-fileback 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 3d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-fileback
把对话里产生的新洞察、新决定、新事实按主语写回 corpus。和 wiki-ingest 的关键区别:输入不是外部资料,而是当前对话的对话记录/结论。
项目/domain skill 可以把已确认的研究结论、候选摘要或对话洞察路由到这里;完整外部材料、finished package 和来源归档仍走 wiki-ingest。
When to trigger
- 用户说"这个记一下"、"存下来"、"做个笔记"、"把刚才那个放进去"
- 用户说"fileback"、"存回知识库"、"归档到 wiki"
wiki-query返回结果后,用户说"好,把今天聊到的这点补到这个页上"- 对话里刚得出一个决定 / 结论 / 事实,用户示意要留痕
不要触发:
- 输入是 URL / 文件 / 外部资料 → 那是
wiki-ingest - 只是随口说,用户没明确要存 → 不要自作主张
Decision tree
- 识别待存内容:用户指向"刚才那段"、"今天聊的 X",明确边界
- 识别主语(按
系统/filing-rules.md)- 谁/哪个项目/哪个概念 是这条内容的"主角"?
- 一条内容可以有多个主语 → 每个主语都要处理
- 定位目标页:
lorekit search "<主语>"- 命中 → update 分支
- 未命中 → 过 Notability gate,决定新建还是挂到最近相关页
- 写入格式(严格):
- 只追加到
## Timeline段落,永不改写 compiled truth - 条目格式:
- YYYY-MM-DD HH:mm — <一句话事实/决定/洞察>(来源:对话) - 如涉及其他实体,用
[[wikilink]]引用
- 只追加到
- 反向链接:如果这条 timeline 提到别的主语页,对方也要追加一条反向条目
- 同步文本档案(
lorekit sync):- 如果本次 fileback 新建了页面或修改了
corpus/index.md:必须跑 - 如果只是往已有页面追加 timeline 一行:可选(目录 summary 通常不变)
- 一条命令刷新
_INDEX.md、合并 rootindex.md,再跑 doctor
- 如果本次 fileback 新建了页面或修改了
- 自检:
lorekit lint --quick - 汇报
Tools to use
lorekit search "<主语>"— 定位目标页lorekit sync— 同步_INDEX.md/ rootindex.md并跑 doctor(新建页面或改 index.md 后必跑)lorekit lint --quick— 写完自检- 底层:Read / Edit(追加 timeline,不要 Write 覆盖)
Output format
本次 fileback:
- 内容:<一句话摘要>
- 主语:<人物/项目/概念>
- 目标:[[页面名]](追加 timeline 1 条)
- 反向链接:[[另一页]] 已追加
lint:PASS
铁律:
- 只追加,不改写 compiled truth(那是 wiki-ingest 或人工 review 的职责)
- 每条都要带时间戳和"来源:对话"标记
- 不确定主语时先问用户,不要猜
价值判断:建 synthesis 页的阈值
fileback 的常规路径是"追加 Timeline"。但当本次 fileback 的内容同时满足以下任一条件时,主动向先生提议升级为 synthesis 页(知识库/专题/<slug>.md):
- 跨源 ≥ 3 个 source — fileback 内容综合了 3 个及以上
知识库/摘要/的观点 - 有新综合见解 — 内容不是单源复述,而是对多源的新组合、新结论、新模型
- 先生明确立场 — 对话中先生说过"我认为..."、"我的立场是..."、"综合来看..."
提议话术:
本次 fileback 涉及多源综合(或:"先生的明确立场")。
这个答案建议升级为 `知识库/专题/<slug>.md`,作为独立的 synthesis 页留存,便于下次引用。
建不建?(Y/N)
Y → 走"建 synthesis 页"流程(见下节),先做反向检验再建
N → 只追加 Timeline,结束
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.
- 3d ago First seen · 119 lines · 59 tokens per session scan A 6005e885919b
wiki-fileback is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,767 once invoked, about $0.0003 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
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).
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 an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
wiki-ingest
Process source files into synthesised wiki pages. Always use this skill when the user says /wiki-ingest, 'import these files', 'process my clippings', 'ingest this article', 'I have new articles to add', 'turn this PDF into a wiki page', 'what's in my raw/ folder', or 'what have I ingested'. Also use when the user…
wiki-config
Set up, validate, and reconfigure the llm-wiki skill suite. Always use this skill when the user says /wiki-config, asks to 'set up my wiki', 'configure wiki', 'initialize wiki config', mentions 'page structure problems', 'schema issues', 'missing templates', 'wiki help', 'how does the wiki work', or when any wiki…
wiki-lint
Health-check the wiki: scan all pages for broken wikilinks, orphaned pages, stale index entries, missing connections, em-dash violations, orphaned assets, and schema errors. Produces a dated lint report. Always use this skill when the user says /wiki-lint, mentions broken links, dead wikilinks, orphaned pages, 'what's…