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 coracoo/zspace_skill --skill label-managergit clone --depth 1 https://github.com/coracoo/zspace_skillWrote 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/coracoo/zspace_skill/label-manager)<a href="https://agentmods.dev/skills/coracoo/zspace_skill/label-manager"><img src="https://agentmods.dev/badge/skills/coracoo/zspace_skill/label-manager/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/coracoo/zspace_skill/label-manager"><img src="https://agentmods.dev/badge/skills/coracoo/zspace_skill/label-manager.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 | $0.00150 | $0.02835 |
| Opus 5.5 | $0.00060 | $0.01134 |
| Sonnet 5.5 | $0.00030 | $0.00567 |
| Haiku 4.5 | $0.00015 | $0.00283 |
Grade A, and why
label-manager 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 2mo 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Label Manager — NAS 标签全生命周期
概述
NAS 标签的全生命周期管理——两种发现方式,同一入口:
| 发现方式 | 用哪个命令 | 适合 |
|---|---|---|
| 按文件名/扩展名 | label_manager.py scan + find-by-label |
目录递归、批量、精确匹配 |
| 按文件内容(RAG 语义) | 纯 LLM 编排,semantic_search → save_file_label |
自然语言描述、不靠文件名 |
最终都走 save_file_label MCP tool 落盘。
前置:nas-setup skill(验证 NAS 登录)。RAG 场景额外需要 rag-manager(门控)。
MCP tool 依赖
| list_file_labels | 列出所有标签 |
| save_file_label(label_names, paths) | 打标签(覆盖式,会自动创建新标签名) |
| delete_label(label_names) | 删除标签(从所有文件上彻底移除) |
| notebook_updatelabel(id, label) | 笔记标签 |
| label_manager.py 命令(机械活) | 用途 |
|---|---|
list-labels |
同 MCP,但走脚本(批量友好) |
scan --root X --ext Y |
BFS 扫目录找文件(LLM 决策前先用) |
find-by-label --label X |
反向查询带某标签的文件 |
5 个标准场景
场景 1:给单个/多个文件打标签
用户说:"给 /sata14/my/data/docker-compose.yml 打 docker 标签"
步骤:
- 调
save_file_label(label_names="docker", paths="/sata14/my/data/docker-compose.yml") - 返回结果(返回 200 即可)
注意:
paths多个用英文逗号分隔,最多 50 个/次(NAS 限速)- 如果
label_names里有不存在的标签名,NAS 会自动创建
场景 2:批量打标(目录递归 + LLM 决策)
用户说:"把 /sata14/my/data/ 下所有 .yml 文件打 docker 标签"
步骤:
- exec
python skills/label-manager/label_manager.py scan --root /sata14/my/data/ --ext yml --max-depth 5 --output /tmp/scan.json - 读
/tmp/scan.json,得到items数组(含 path/name/labels) - LLM 自己判断哪些真该打(README.yml 不该打),过滤后分批(每批 50 个)
- LLM 调
save_file_label(label_names="docker", paths="path1,path2,...")分批执行
为什么 LLM 决策:不是所有 .yml 都是 docker 配置。LLM 看 path/name 决定。
场景 3:按标签找文件(反向查询)
用户说:"找所有带 docker 标签的文件"
步骤:
- exec
python skills/label-manager/label_manager.py find-by-label --label docker --root /sata14/my/data/ --max-depth 5 --output /tmp/docker.json - 读
/tmp/docker.json,得到matches数组(含 path/name/is_dir/labels) - 格式化返回给用户
已知 gap:
- 受
--max-depth限制,深度外文件找不到 - 用户只能扫
/<pool>/my/<子目录>/,跨池越权 N001411 - 脚本内部走 BFS + 串行,sleep 0.1s/层,100 个目录约 10s
What ships with it
4 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.
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.
- 2mo ago First seen · 214 lines · 150 tokens per session scan A df3bbf1464b0
label-manager is a skill published in the GitHub repository coracoo/zspace_skill (36 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 2,835 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.