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 agentmods add skills/galiacheng/mindmap-skills/mindmapnpx skills add galiacheng/mindmap-skills --skill mindmapgit clone --depth 1 https://github.com/galiacheng/mindmap-skillsWrote 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/galiacheng/mindmap-skills/mindmap)<a href="https://agentmods.dev/skills/galiacheng/mindmap-skills/mindmap"><img src="https://agentmods.dev/badge/skills/galiacheng/mindmap-skills/mindmap.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02091 |
| Opus 5 | $0.00012 | $0.01045 |
| Sonnet 5 | $0.00005 | $0.00418 |
| Haiku 4.5 | $0.00002 | $0.00209 |
Grade A, and why
mindmap 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 6d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mindmap Skill — Generate an Interactive Markmap
Trigger
/mindmap <input> [--panel] [--render] [--output <path>]
<input> is one of:
- a file path — read the file and map it
- a URL (
http://orhttps://) — fetch the page and map its content - pasted text / notes — map the text directly
- a short topic — generate a map from your own knowledge
Flags:
--panel— design the structure with a multi-agent judge panel (token-intensive; best for complex/important sources like papers). See Step 2 → Judge Panel.--render— after writing the.md, also produce a standalone interactive.html--output <path>— write the.mdto this path instead of the default
Cross-harness note: This skill uses Claude Code tool names (
Read,Write,Glob,Bash,WebFetch). On GitHub Copilot CLI, use the equivalents (view,create,glob,bash,web_fetch) — seereferences/copilot-tools.md. The workflow itself is identical on both.
Workflow
Step 1: Resolve the input
Strip the flags, then classify what remains and load the content:
- If it is a URL (starts with
http://orhttps://), fetch it with WebFetch (ask it to return the page's main text content). The fetched content is the content. Check this first, before the file/text/topic rules. - Else if it is the path of an existing file, Read it. That is the content.
- Else if it is long or multi-line prose (roughly > 12 words, or contains line breaks), treat it as raw text. That is the content.
- Else treat it as a topic: generate the content from your own knowledge.
Stop and ask the user (never silently guess) when:
- A URL fetch fails (network error, blocked, or empty page) → report it and ask: map the page's topic from your own knowledge instead, or try a different URL? Do not invent page content.
- It looks like a file path (ends in
.md/.txt, or contains/or\) but the file does not exist → reportno file at <path>and ask: map it as a topic instead, or fix the path? - It is empty or whitespace only → ask for content or a topic.
- It is genuinely ambiguous (a short phrase that could be raw text or a topic) → default to topic generation and say so in one line so the user can correct you.
What ships with it
5 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.
- 6d ago First seen · 170 lines · 24 tokens per session scan A 4c1635e4d7f6
mindmap is a skill published in the GitHub repository galiacheng/mindmap-skills (15 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 2,091 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
gpt-vis
推荐并生成合适的数据可视化图表，使用 GPT-Vis 库。支持两种输出模式：（1）语法模式——生成 Syntax 或 JSON 配置；（2）代码模式——生成完整的运行代码。支持 26 种图表类型。.
antv-x6-editor
Use this skill whenever the user wants to create, customize, or troubleshoot X6 v3 graph editor diagrams. Triggers include: any mention of 'X6', 'antv x6', '@antv/x6', 'X6 editor', 'X6 图编辑', '流程图', 'DAG', 'ER图', '实体关系图', '血缘图', '组织架构图', 'UML类图', 'flowchart', 'DAG diagram', 'ER diagram', 'lineage graph', 'org chart'…
infographic-creator
Create beautiful infographics based on given text content. Use when users request to create infographics.
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
codex-implement
Implement features via Codex exec. Use when: writing new code from specs, implementing features, Codex-driven development. Not for: code review (use codex-code-review), architecture advice (use codex-architect). Output: implemented code + review loop.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…