What is archive-import?

A document-import tool that copies outside files into a project archive. It can either turn specs and reports into dated records with summaries, or organize technical references and wiki exports into reusable knowledge files.

Use it to import files or folders containing specs, meeting notes, reports, wiki exports, or technical references into the appropriate archive area.

It avoids manually copying, summarizing, labeling, and sorting imported documents. It also helps reduce duplicate or overlapping knowledge entries.

archive-import — Skill for Claude Code and Codex by grasscaograss

Install

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.

Any agent

npx skills add grasscaograss/AwesomeWeldoneSkills --skill archive-import

Clone the repo

git clone --depth 1 https://github.com/grasscaograss/AwesomeWeldoneSkills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin archive-import — /plugin install archive-import after adding the marketplace above.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/grasscaograss/awesomeweldoneskills/archive-import/github.svg)](https://agentmods.dev/skills/grasscaograss/awesomeweldoneskills/archive-import)

Your own site

<a href="https://agentmods.dev/skills/grasscaograss/awesomeweldoneskills/archive-import"><img src="https://agentmods.dev/badge/skills/grasscaograss/awesomeweldoneskills/archive-import/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/grasscaograss/awesomeweldoneskills/archive-import"><img src="https://agentmods.dev/badge/skills/grasscaograss/awesomeweldoneskills/archive-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,901 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00073	$0.01901
Opus 5	$0.00036	$0.00950
Sonnet 5	$0.00015	$0.00380
Haiku 4.5	$0.00007	$0.00190

Measured 10d ago against content hash f1f2b027a9be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

archive-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 10d 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.

archive-import/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Archive Import — 文档导入

Quick start

/archive-import docs/specs/ → records       ← spec 文档 → records
/archive-import .zread/wiki/ → knowledge    ← wiki 输出 → 知识库

第一个参数：源文档路径（文件或目录）。第二个参数：目标模式（records 或 knowledge）。

两种模式

目标	处理方式	适用场景
→ records	格式转换：添加 TL;DR，套用模板，保留内容	Spec 文档、会议记录、外部报告、一次性文档
→ knowledge	深度整理：重叠分析、领域分组、并行 agent 读写、合并/拆分	技术参考资料、wiki 导出、可复用领域知识

Records 模式

处理每份文档

读取源文档
提取：标题、日期（来自文件名或内容）、要点
生成 TL;DR 行和关键词标签
套用标准 record 模板（参见 /archive-session 的模板）
写入 archive/records/YYYY-MM-DD-<slug>.md

更新 INDEX.md

在 archive/INDEX.md 的 ## Records 下添加每条导入记录，附关键词标签。每行不超过 150 字符。

Knowledge 模式

Knowledge 模式采用三步工作流：分析设计 → 并行写入 → 验证更新。核心区别在于使用 TaskCreate 为每个领域启动独立 Agent 并行执行，而非串行处理。

领域文件夹参考

archive/knowledge/
├── dual-arm/          ← 双臂系统
├── weld-template/     ← 焊接模板
├── weld-seam/         ← 焊缝规划
├── coarse-positioning/ ← 粗定位
├── scanning/          ← 精定位与扫描
├── capacity/          ← 产能统计
├── weld-tracking/     ← 焊接跟踪
├── coordinate/        ← 坐标与矩阵
├── workflow/          ← 状态机与工作流
├── frontend/          ← 前端界面
├── device-robot/      ← 设备与机器人
├── tools/             ← 工具与其他

第一步：分析源文档，设计领域结构

读取所有源文档 — 用 Glob 找到所有文件，逐个 Read
提取关键概念、事实、规则、模式 — 从每份文档中抽取出独立的知识单元
与现有知识对比重叠 — Read archive/knowledge/ 下所有现有文件，标记：
- new：全新知识，无重叠
- merge：与现有文件有重叠，需要合并
- skip：已被现有文件完全覆盖
按领域分组 — 将知识单元归入上述领域文件夹，确定每个文件的：
- 源文件归属（哪些源文档的内容合并到此文件）
- 与现有知识文件的合并关系
向用户展示结构方案 — 输出分组表，等待用户确认：

| 领域文件夹 | 新文件 | 合并到已有文件 | 跳过 |
|-----------|--------|--------------|------|
| dual-arm/ | arc-safety.md | pipeline.md (追加§3) | — |
| scanning/ | laser-calib.md | — | vision.md 已覆盖 |

用户确认后进入第二步。

第二步：创建目录，并行启动 Agent

创建目标文件夹（如尚未存在）
为每个领域文件夹启动一个独立 Agent（通过 TaskCreate），每个 agent 接收以下信息：
- 领域名称和文件夹路径（如 archive/knowledge/dual-arm/）
- 要读取的源文件列表（绝对路径）
- 已有知识文件的迁移需求（如需合并，列出目标文件和合并策略）
- 知识文件格式规范（见下方）
- 合并/拆分指导原则

Read the full file on GitHub · 206 lines

Changes

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.

10d ago First seen · 206 lines · 73 tokens per session scan A f1f2b027a9be

Subscribe to this mod's changes

archive-import is a skill published in the GitHub repository grasscaograss/AwesomeWeldoneSkills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,901 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.

Documents Memory and context

obsidian

Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.

steipete/agent-scripts · 19 tokens

loopx-doc-registry

Use when a connected LoopX project is asked to read, remember, record, index, register, or use a durable project material such as a Lark/wiki/design doc, research note, SOP, owner packet, migration report, benchmark paper, or external material source. Use even when the user does not mention LoopX or doc registry.

huangruiteng/loopx · 74 tokens

archive-import