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/jihe520/mindpocket/ai-elementsnpx skills add jihe520/mindpocket --skill ai-elementsgit clone --depth 1 https://github.com/jihe520/mindpocketWhat 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 | $0.00058 | $0.01593 |
| Opus 5 | $0.00029 | $0.00796 |
| Sonnet 5 | $0.00012 | $0.00319 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
ai-elements 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- references/agent.md 4.1 KB
- references/artifact.md 2.9 KB
- references/attachments.md 5.6 KB
- references/audio-player.md 5.2 KB
- references/canvas.md 1.1 KB
- references/chain-of-thought.md 3.3 KB
- references/checkpoint.md 5.4 KB
- references/code-block.md 5.4 KB
- references/commit.md 5.8 KB
- references/confirmation.md 8.2 KB
- references/connection.md 1.1 KB
- references/context.md 5.6 KB
- references/controls.md 971 B
- references/conversation.md 7.3 KB
- references/edge.md 2.1 KB
- references/environment-variables.md 3.7 KB
- references/file-tree.md 2.0 KB
- references/image.md 4.0 KB
- references/inline-citation.md 11 KB
- references/jsx-preview.md 3.2 KB
- references/message.md 11 KB
- references/mic-selector.md 7.7 KB
- references/model-selector.md 4.3 KB
- references/node.md 2.8 KB
- references/open-in-chat.md 2.7 KB
- references/package-info.md 3.2 KB
- references/panel.md 1.0 KB
- references/persona.md 4.7 KB
- references/plan.md 3.2 KB
- references/prompt-input.md 19 KB
- references/queue.md 5.4 KB
- references/reasoning.md 7.7 KB
- references/sandbox.md 4.3 KB
- references/schema-display.md 2.5 KB
- references/shimmer.md 1.6 KB
- references/snippet.md 2.2 KB
- references/sources.md 6.2 KB
- references/speech-input.md 6.5 KB
- references/stack-trace.md 7.9 KB
- references/suggestion.md 3.6 KB
- references/task.md 6.7 KB
- references/terminal.md 3.1 KB
- references/test-results.md 5.0 KB
- references/tool.md 8.5 KB
- references/toolbar.md 983 B
- references/transcription.md 4.9 KB
- references/voice-selector.md 10 KB
- references/web-preview.md 6.1 KB
- scripts/agent.tsx 1.6 KB
- scripts/artifact.tsx 2.9 KB
- scripts/attachments-inline.tsx 3.5 KB
- scripts/attachments-list.tsx 2.2 KB
- scripts/attachments.tsx 2.0 KB
- scripts/audio-player-remote.tsx 1.0 KB
- scripts/audio-player.tsx 1.8 KB
- scripts/chain-of-thought.tsx 139 KB
- scripts/checkpoint.tsx 2.8 KB
- scripts/code-block-dark.tsx 1.0 KB
- scripts/code-block.tsx 3.0 KB
- scripts/commit.tsx 2.1 KB
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.
- yesterday First seen · 171 lines · 58 tokens per session scan A 7e36e211495c
ai-elements is a skill published in the GitHub repository jihe520/mindpocket (345 stars, last pushed 1mo ago), with no licence file. It adds 58 tokens to every session and 1,593 once invoked, about $0.0003 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
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
ask-user-question
Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.
pixelbrowse
Screenshot and visually read any web page or document using pixelshot. Use instead of fetching raw HTML when you need to see what a page looks like, read visual content (charts, diagrams, infographics), check layouts, or verify UI. Triggers: "look at this page", "screenshot", "what does this site look like", "check…
memos-memory-guide
Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query…
tushare-data
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。.