xmind

xmind is a skill for Claude Code from levi-qiao/sherlock-claude. It costs 82 tokens per session (1,484 once invoked), scanned A, original, MIT.

A tool for opening, reading, creating, and updating XMind mind-map files. It also converts mind-map content to Markdown, a plain-text format commonly used for notes and documentation.

In plain words
What is it for?
It helps parse existing mind maps, create new ones, edit them, and convert them to Markdown for continued work.
Why use it?
It keeps mind-map content available in a form the assistant can inspect and use across follow-up edits, including both newer and older XMind file formats.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the anthropics-file-generation plugin — 9 skills shipped together

Good fit It helps parse existing mind maps, create new ones, edit them, and convert them to Markdown for continued work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/levi-qiao/sherlock-claude/xmind
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 levi-qiao/sherlock-claude --skill xmind
Clone the repo
git clone --depth 1 https://github.com/levi-qiao/sherlock-claude

Made for: Claude Code.

Or install anthropics-file-generation, the plugin that ships this one along with the rest of its 9 skills.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/levi-qiao/sherlock-claude/xmind/github.svg)](https://agentmods.dev/skills/levi-qiao/sherlock-claude/xmind)
Your own site
<a href="https://agentmods.dev/skills/levi-qiao/sherlock-claude/xmind"><img src="https://agentmods.dev/badge/skills/levi-qiao/sherlock-claude/xmind/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/levi-qiao/sherlock-claude/xmind"><img src="https://agentmods.dev/badge/skills/levi-qiao/sherlock-claude/xmind.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,484 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 $0.00082 $0.01484
Opus 5 $0.00041 $0.00742
Sonnet 5 $0.00016 $0.00297
Haiku 4.5 $0.00008 $0.00148

Measured 10d ago against content hash 1b1fe93bac79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xmind 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/xmind_tool.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/anthropics-file-generation/skills/xmind/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XMind Mind Map Skill

This skill provides full handling of XMind files (.xmind): parse, create, and update. A companion Python script performs file operations and converts mind map content to Markdown as session-level memory so the user and model can keep iterating.

Tool script

This skill depends on scripts/xmind_tool.py (relative to this skill directory), using only the Python standard library (no third-party dependencies). Run it as:

python skills/xmind/scripts/xmind_tool.py --session <session-id> <command> [args...]

Session management

All commands require --session <id> to isolate memory files per conversation.

How to obtain a session ID (in order):

  1. From context: if the thread already has a session ID from a prior use of this skill, reuse it.
  2. Otherwise: before the first call, generate a UUID v4 string (e.g. f47ac10b-58cc-4372-a567-0e02b2c3d479) and reuse it on later calls.
  • Memory file path: /tmp/skills-xmind-parsed/<session-id>/<filename>.md

Supported formats

Format Version Internal layout Detection
Zen XMind Zen / 2020+ ZIP containing content.json Automatic
Legacy XMind 8 ZIP containing content.xml Automatic

New files default to Zen; when updating an existing file, keep its original format.

Markdown representation

Parsed Markdown uses an indented list structure, for example:

# Sheet: Sheet title

## Central topic

> Labels: label1, label2
> Link: https://example.com
> Markers: priority-1
> Notes for the central topic

- Branch one  {labels: important}  {link: https://example.com}
  > Notes for branch one
  > Notes can span multiple lines
  - Child 1.1  {markers: task-done, priority-1}
    - Grandchild 1.1.1
  - Child 1.2
- Branch two
  - Child 2.1
  - Child 2.2

Format notes:

  • # Sheet: title — sheet title (separate multiple sheets with ---)
  • ## title — central topic
  • - content — node; two-space indent per level
  • {labels: ...} — inline label metadata
  • {link: ...} — inline link metadata
  • {markers: ...} — inline marker / icon metadata
  • > content — node notes (blockquote, directly under the node)
  • Central-topic metadata uses top-level blockquotes (> Labels:, > Link:, > Markers:)

Read the full file on GitHub · 165 lines

Files

What ships with it

1 file 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.

  1. 10d ago First seen · 165 lines · 82 tokens per session scan A 1b1fe93bac79

Subscribe to this mod's changes

xmind is a skill published in the GitHub repository levi-qiao/sherlock-claude (6 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 1,484 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.