A workflow for managing WorkBuddy's shared content area, including online documents, structured tables, pages, links, and stored files. It supports content creation, organisation, sharing, collaboration, and light publishing.

Use it to write or organise documents, import CSV or Excel data, edit tables, build dashboards or report pages, manage files, and share content.

It gives different kinds of shared content a defined place and workflow instead of treating every item as a plain file. It also applies rules for choosing spaces, searching, and changing remote content.

资料库 — Skill for Claude Code and Codex by rojim666/SztuCode

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 rojim666/SztuCode --skill library

Clone the repo

git clone --depth 1 https://github.com/rojim666/SztuCode

Made for: Claude Code, Codex.

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/rojim666/sztucode/library/github.svg)](https://agentmods.dev/skills/rojim666/sztucode/library)

Your own site

<a href="https://agentmods.dev/skills/rojim666/sztucode/library"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/library/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/rojim666/sztucode/library"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/library.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,259 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	$0.00212	$0.03259
Opus 5.5	$0.00085	$0.01304
Sonnet 5.5	$0.00042	$0.00652
Haiku 4.5	$0.00021	$0.00326

Measured 1mo ago against content hash 0f1b4808d7bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

资料库 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.

packages/runtime-ts/prompts/Sztubuddy/skills/library/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

资料库使用指南

调用前置

静默读取运行环境，仅用于内部路由和鉴权；除非用户明确询问，不在过程说明、确认或成功回执中提及：

python3 "${CODEBUDDY_SKILL_DIR}/runtime_context.py"

输出 mode=sandbox：不调 connect_open_platform、不传 token；mode=client：按客户端模式鉴权。
mode=client 的鉴权调用必须严格执行：先用 ToolSearch 精确查询 {"tool_names":["connect_open_platform"]}，再用 DeferExecuteTool 调用 {"toolName":"connect_open_platform","params":{"skill_id":"library"}}。拿到 authenticated=true 且非空的 token 后，才能执行本 skill 的网络脚本。
connect_open_platform 是 deferred MCP 工具，不是 shell/CLI 命令，也不是 space_api.py 子命令。禁止通过 Bash、cbc、codebuddy、Python 或 space_api.py connect_open_platform 调用；禁止在环境变量、本地文件、凭证目录、进程、二进制或 RPC 中搜索/探测 token；禁止用空值或伪造值调用 --token-stdin。ToolSearch 未找到工具或 DeferExecuteTool 换票失败时立即停止，不改走其它凭证路径。
目标空间由所有模块按以下顺序统一决定：
1. 操作已有节点：用户给出 nodeId 或节点链接时，按该节点的实际归属执行，不套用默认空间。
2. 用户显式指定空间或目录：以该目标为准；已给出或解析出 spaceId 时传实际值，仅明确指定我的文档但未给 ID 时可省略可选 spaceId；按 parentId 新建时，先取得其所属 spaceId，确认二者匹配后同时传入。
3. 无显式目标：创建、导入、上传时省略可选的 --space-id / space_id，由后端默认落我的文档。

以脚本输出为准。脚本失败时停止，简要说明无法继续即可。

远端变更

凡创建/上传、修改、删除、移动或重命名远端资料，先静默执行 mutation.md，按其规则判定实际目标空间分类与是否需要停下确认。

检索授权

明确给出单个节点时只读取该节点，不扩展成全库搜索。“写报告”“做方案”等泛化创作不触发检索。写入目标不等于检索授权。

按 kind 直取入口

访问/处理任一资料库节点前，先归一化为 nodeId（/space/d/{id} 或 *.Sztubuddy.link/p/{id} 直接提取 {id} 为 nodeId、搜索结果取 nodeId），再用 space.workspace.node-info 读 kind。

按下表读取对应的 entry：

kind	场景	入口
doc	在线文档读/改	`doc/entry.md`
web / page	HTML 页面	`page/entry.md`
database	结构化表	`database/entry.md`
link	网页剪藏	`link/entry.md`
drive	网盘文件	`drive/entry.md`
smh	历史媒体节点	`smh/entry.md`
目录 / 空间导航 / 全局搜索	管理	`manage/entry.md`

目标选择

说「存到资料库」且未点名外部产品时，默认且唯一是原生资料库，不反问存哪、不把外部产品拼成选择题。
只在缺文档主题时问主题。
仅写入失败/权限不足/多个同名空间/语义指向团队空间但名称不全时消歧，且只列原生空间（space.workspace.list-user-spaces）。

文件夹意图

说「建文件夹/做目录/把文档归到一起/建知识库」时，不默认建空间；先让用户在两种做法间选，措辞用「挂到下面/目录树」，不用「父/子节点」：

做法	怎么做	适合
文档目录（默认）	新建一篇文档当目录页，其余文档挂到它下面成目录树	灵活聚合
独立空间	单独建空间统一管理；长期+多人协同推荐团队空间	长期沉淀

Read the full file on GitHub · 138 lines

Files

What ships with it

37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · +4 tokens per session 0f1b4808d7bf
1mo ago First seen · 138 lines · 208 tokens per session scan A a15b191b0d71

Subscribe to this mod's changes

资料库 is a skill published in the GitHub repository rojim666/SztuCode (109 stars, last pushed 6d ago), licensed MIT. It adds 212 tokens to every session and 3,259 once invoked, about $0.0008 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 2026-09-12.

Documents Project management Spreadsheets agentic-ai ai-agents ai-coding-agent coding-agent developer-tools json-rpc

xlsx-official

Builds, edits, cleans, and inspects spreadsheet files (.xlsx, .xltx, .csv, .tsv) when the file is the deliverable or the record being changed: financial and operating models with live formulas, formula-driven summaries, template fills, cell and row patches, messy-data repair, sheet-to-CSV or PDF export, formula…

evoelsewhere/evoflux · 151 tokens

google-workspace-ops

Operate across Google Workspace tools with reusable patterns for docs, sheets, calendar, drive, and gmail.

aaronnat23/disp8ch · 0 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

xlsx

Create/edit/analyze/verify spreadsheet workbooks including XLSX/CSV/TSV.

Hmbown/CodeWhale · 20 tokens

spreadsheets

Compatibility alias for the xlsx skill. Prefer loading xlsx.

Hmbown/CodeWhale · 17 tokens

browser4-web-miner

Groups similar web pages together and produces an interactive HTML report with clusters of related pages, plus Excel spreadsheets for analysis. Use when the user wants to cluster downloaded HTML files, convert detail web pages into interactive views, or analyze a folder of web pages locally.

platonai/Browser4 · 57 tokens