xmind-mcp-server: Skill for Claude Code

.claude/skills/xmind-format/SKILL.md

xmind-format is a skill for Claude Code from GarryWhite109909/xmind-mcp-server. It costs 52 tokens per session (1,115 once invoked), scanned A, original, MIT.

A technical guide to the XMind file format, whose files are ZIP archives containing JSON that describes mind-map sheets, topics, styles, links, and images. It also documents how to read, change, save, and validate those files safely.

In plain words
What is it for?
Use it when parsing or editing XMind files, changing topic trees or styles, handling images and attachments, or writing files back for validation.
Why use it?
It reduces the risk of corrupting an XMind file or losing its structure when editing the underlying data. It also clarifies which files and fields are authoritative.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is GarryWhite109909/xmind-mcp-server's own configuration. It tells Claude Code how to work on xmind-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything xmind-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GarryWhite109909/xmind-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GarryWhite109909/xmind-mcp-server/main/.claude/skills/xmind-format/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GarryWhite109909/xmind-mcp-server

Made for: Claude Code.

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.

agentmods badge for xmind-format

README.md
[![agentmods](https://agentmods.dev/badge/skills/garrywhite109909/xmind-mcp-server/xmind-format/github.svg)](https://agentmods.dev/skills/garrywhite109909/xmind-mcp-server/xmind-format)
Your own site
<a href="https://agentmods.dev/skills/garrywhite109909/xmind-mcp-server/xmind-format"><img src="https://agentmods.dev/badge/skills/garrywhite109909/xmind-mcp-server/xmind-format/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.

agentmods 80×15 button for xmind-format

Your own site · 80×15
<a href="https://agentmods.dev/skills/garrywhite109909/xmind-mcp-server/xmind-format"><img src="https://agentmods.dev/badge/skills/garrywhite109909/xmind-mcp-server/xmind-format.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,115 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01115
Opus 5.5 $0.00021 $0.00446
Sonnet 5.5 $0.00010 $0.00223
Haiku 4.5 $0.00005 $0.00112

Measured yesterday against content hash da58a3e1047b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xmind-format 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 yesterday.

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.

.claude/skills/xmind-format/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XMind 文件格式与安全写回

先看事实

.xmind 是 ZIP,新版(XMind Zen / 2020+)以 content.json 为准:

content.json       主题树(唯一真相)
metadata.json      dataStructureVersion / layoutEngineVersion / creator
manifest.json      file-entries 清单
content.xml        旧版兼容占位(XMind 26 仍会带)
cache.json         缓存占位
attachments/       图片/附件(可被 xap: 引用)
resources/         本工具插入图片时使用
Thumbnails/        保存时生成的整图缩略图

图片引用:"src": "xap:resources/xxx.png" → zip 内 resources/xxx.png。 也兼容 data:image/...;base64,...。

节点树:

{
  "id": "sheet-id",
  "title": "工作表",
  "rootTopic": {
    "id": "root",
    "title": "中心主题",
    "children": {
      "attached": [],
      "detached": [],
      "summary": [],
      "callout": []
    },
    "notes": {"text": "..."},
    "markers": [{"markerId": "priority-1"}],
    "labels": ["标签"],
    "image": {"src": "xap:resources/x.png"},
    "style": {"id": "...", "properties": {...}},
    "summaries": [{"id": "...", "range": "(0,2)", "topicId": "..."}],
    "boundaries": [{"id": "...", "range": "(0,1)"}]
  },
  "relationships": [{"end1Id": "...", "end2Id": "..."}],
  "theme": {...}
}

读写流程

读:parse_xmind(path) → XMindFile(sheets / raw_content / _topic_index)。 改:只改 writer.xm.raw_content 里的 dict,然后调用 self.xm.refresh_from_raw() 重建节点树和 ID 索引。 存:writer.save(output_path);不要自己写 zip。

save() 已经负责:

  • 覆盖前备份到 ~/.xmind-mcp/backups/(每个文件保留 20 份);
  • 磁盘摘要与 xm.source_digest 不一致时抛 FileChangedError;
  • 移除过期 Thumbnails/thumbnail.png;
  • 补 metadata.json / content.xml / cache.json,同步 manifest.json;
  • 临时文件 + os.replace 原子替换。

官方校验硬规则

非根主题不能带 class: "topic";每个 style 必须有 id; markers 必须是 [{"markerId": "..."}],不能是字符串数组。 这些规则由 tests/test_golden.py 和官方 CLI 共同守住。

如果本机装有 XMind 官方 CLI:

xmind auth status
xmind validate path/to/file.xmind

CLI 要求登录,validate 也不例外;没有登录时先 xmind auth login cn (或 global),回调等待约 180 秒。

结构变更的连锁影响

  • children.attached 顺序变化(插入 / 删除 / 移动)会让 summaries / boundaries 的字符串区间 "(i,j)" 错位: 必须先记录旧 ID 列表,再调用 _remap_visual_ranges(parent, old_ids)。
  • 删除子树时用 topic_ids_in_subtree(),再 _cleanup_dangling_refs() 清理 relationships / summaries / boundaries。
  • 移动/复制节点前用 _is_descendant() 阻止移到自己或后代下。
  • summary / callout 不是普通主题,不能挂子节点、不能移动/复制。

Read the full file on GitHub · 111 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.

  1. yesterday First seen · 111 lines · 52 tokens per session scan A da58a3e1047b

Subscribe to this mod's changes

xmind-format is a skill published in the GitHub repository GarryWhite109909/xmind-mcp-server (0 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,115 once invoked, about $0.0002 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 2026-11-09.

Related

xmind-format compared with skills from other repositories

xmind-format next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
xmind-formatGarryWhite109909/xmind-mcp-serverSkill02d agoMITA52Claude Code
orbit-notionnexu-io/open-designSkill107ktodayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k3d agoApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49ktodayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill10.0k2d agoApache-2.0A68Claude Code
report-to-pdfasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A17Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A54Claude Code, Codex