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/meari-prototype/iftree-editor/intelligent-importnpx skills add Meari-Prototype/iftree-editor --skill intelligent-importgit clone --depth 1 https://github.com/Meari-Prototype/iftree-editorWrote 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/meari-prototype/iftree-editor/intelligent-import)<a href="https://agentmods.dev/skills/meari-prototype/iftree-editor/intelligent-import"><img src="https://agentmods.dev/badge/skills/meari-prototype/iftree-editor/intelligent-import.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 | $0.00110 | $0.02552 |
| Opus 5 | $0.00055 | $0.01276 |
| Sonnet 5 | $0.00022 | $0.00510 |
| Haiku 4.5 | $0.00011 | $0.00255 |
Grade A, and why
intelligent-import 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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能导入 / 重整目录 skill
用途
专职整理文档的目录层级结构。在简单导入或完整导入入库后,对已有节点树做结构调整——新建虚拟容器节点叠章节层、调父子边、调兄弟顺序、给虚拟容器补章节名。
本 skill 不重做简单导入已识别的结构——能用正则/AST/格式规范做的事不调用 LLM API(成本约束)。
触发
- 导入流程入口:用户在导入对话框选"智能导入",简单导入入库后自动触发本 skill;导入流程结束时弹强制审批对话框(接受全部/拒绝全部)。
- 重整目录入口:已导入文档上,用户在 LLM 协作模式对话区发起"用 LLM 重整目录"指令;产物按 15-7 路径进 LLM 对话区待审卡片,按 15-8/15-9 逐条或整批审。
输入
调用方上下文提供:
- 当前文档
docId和treeIndex(每个节点的地址、深度、子节点数、字数) - 当前权限模式(必须为
agent.mode.edit协作模式或更高) - 触发场景(
import-flow或restructure),用于决定审批 UI 走哪条路
输入产物来自完整导入(4-2)——智能导入入库阶段复用完整导入解析,不走简单导入失败拒绝。所以 treeIndex 反映的形态有三种:
- 结构识别成功:节点
1下有章节层、章节下有段落容器(虚拟节点)、段落下有句子节点 - 结构识别失败:节点
1下平铺段落容器(虚拟节点)、段落下有句子节点;无章节层 - 极端兜底:节点
1单节点(全文塞节点 1 正文),无子节点
skill 按需通过 db read <docId> <地址> 拉取节点正文;不拿原始源文件,因为节点已经反映了规则解析的产物。
输出
调用 database_mutation 产生 entry kinds 序列,写入 owner=llm 影子分支。允许的 entry kinds:
| kind | 用途 |
|---|---|
node.insert |
新建虚拟容器节点 |
node.update |
给虚拟容器节点写 node_title 字段 |
node.reparent |
调节点父子边 |
node.moveBefore / node.moveAfter |
调兄弟顺序 |
node.delete |
删除已没有子节点的空虚拟容器 |
其余 entry kinds(node.split、node.mergeInto、axiom.*、ref.* 等)本 skill 不调用。
虚拟容器节点形态(强约束)
新建节点必须严格按 9-1-1 虚拟节点形态:
text为空node_type用TEXT,role标记为容器类型(如paragraph)source_position取该容器所有子节点最早source_position减 0.5(半步偏移避免位置冲突)skipVector为 truenode_title可写(章节名);node_note留空
未按此形态创建的节点会破坏 9-1 渲染规则,被判定为违规。
职责范围("该/不该",非系统级"能/不能")
skill 做
- 新建虚拟容器节点做分组归类
- 给虚拟容器节点的
node_title写章节名 - 调父子边把散落的同类节点归到一起
- 调兄弟顺序把章节按合理顺序排
- 删除已空的虚拟容器(其子节点全部被移走后)
skill 不涉及
- 正文编辑:
text字段修改归 LLM 系统级编辑能力(别的 skill 或人类编辑模式负责)。本 skill 不动任何节点正文。 - 节点摘要:给真实内容节点(有正文的)写
node_title当摘要属于节点摘要 skill 范围。本 skill 只给虚拟容器写章节名。 - 段落切分/合并:段落容器和句子节点的粒度由
4-2完整导入锁定(智能导入入库走完整导入解析)。本 skill 不动段落正文边界。 - 删带正文的真实内容节点:本 skill 只删自己创建的空虚拟容器。
- 事实前提:
axiom.*全部归9-8单独编辑路径。
工作流
- 读 treeIndex 看当前结构,按上面三种输入产物形态分类。
- 判断是否需要调整——保守原则,不为了"做点什么"而强行调整:
- 结构识别成功 + 章节顺序合理 + 层级合理 → 返回空 entries
- 结构识别成功 + 章节顺序乱(按
source_position序号看不连续)或层级误划 → 重排或调层 - 结构识别失败(节点
1下平铺段落容器)→ 按段落正文聚类,新建章节虚拟容器作为段落容器的父节点 - 极端兜底(节点
1单节点)→ 返回空 entries 并在对话区说明"短文档/单句备忘无需结构化"
- 必要时按
db read拉节点正文 判断聚类——不要一次性拉所有正文,按 treeIndex 字数评估,只读相关节点。 - 决定调整方案,生成 entry 序列。每个 entry 必须可在影子分支投影中合法应用(参考
edit-branch-projection.mjs)。 - 保持节点集合恒等——真实内容节点不增不减,只调关系;只增删虚拟容器。
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.
- 4d ago First seen · 135 lines · 110 tokens per session scan A 93d5f7720891
intelligent-import is a skill published in the GitHub repository Meari-Prototype/iftree-editor (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 2,552 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
openkb-deck-neon
Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black…
openkb-deck-editorial
Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content. Generates a polished single-file HTML deck in the Editorial Monocle visual direction (warm cream background, serif type, brick-red accent) — designed to be opened in a browser…
wiki-knowledge-agent
Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base. When a user pastes a link or text (in ANY channel — Discord, Slack, CLI, etc.), fetch+verify it, classify it (useful vs ad), translate+summarize it into the target language, save it to the wiki, and optionally alert on…
ingest
Turn messy source notes into structured wiki pages (frontmatter, wikilinks, one folder per type) and update the vault's index, log and hot cache. Use when the user drops files into inbox/ and asks to process them, points at a note or URL to ingest, or pastes raw content to file. Triggers on: "ingest", "ingesta"…
save
File the current conversation's valuable content (analysis, decision, session summary) as a structured wiki note so it isn't lost in chat history. Triggers on: "save this", "guarda esto", "guárdalo en el wiki", "/save", "$save", "file this", "apunta esto", "guarda esta conversación", "save this session".
second-reader
Build and run a source-verified Markdown knowledge vault (opens as an Obsidian vault). Ingests books, PDFs, transcripts, and articles into atomic, cross-linked, cited notes, then gates every note and every answer behind an independent verification pass that re-reads the source cold and loops until a round finds…