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/majiayu000/spellbook/ask-openclinpx skills add majiayu000/spellbook --skill ask-opencligit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/ask-opencli)<a href="https://agentmods.dev/skills/majiayu000/spellbook/ask-opencli"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/ask-opencli.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 | $0.00095 | $0.02057 |
| Opus 5 | $0.00048 | $0.01028 |
| Sonnet 5 | $0.00019 | $0.00411 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade A, and why
ask-opencli 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 5d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask via OpenCLI (Grok / Gemini)
Use opencli to query Grok or Gemini through the user's already-logged-in Chrome session. Zero API cost, fully driven by the existing browser session.
opencli 项目：https://github.com/jackwener/opencli 安装：
npm install -g @jackwener/opencli（需要 Node ≥20） 首次运行：opencli doctor会自动引导安装 Chrome Browser Bridge 扩展 登录：用装了扩展的 Chrome profile 打开 grok.com 和 gemini.google.com 登录一次 必须环境变量：export OPENCLI_BROWSER_COMMAND_TIMEOUT=300（写进 shell rc） 更深度的多 AI 并行调研工作流：use themulti-ai-researchskill instead
When to trigger:
- User explicitly asks to query Grok or Gemini ("问一下 grok", "用 gemini 查", "让 grok 看看")
- User wants a second opinion / external advisor from Grok or Gemini
- User says "ask grok"/"ask gemini" or mentions these two as the information source
When NOT to trigger:
- User wants to use native Gemini CLI (
gemini -p) → useask-geminiskill instead - User wants Claude's own opinion → answer directly
- User wants other AI (Doubao, Yuanbao, ChatGPT, etc.) → use other tools
Model selection
If the user doesn't specify which model, default to Grok for real-time / social / news / tech-trend questions, and Gemini for long-form reasoning, research, coding, and document analysis.
If still ambiguous, ask the user which one to use before sending.
⚠️ 常见错误命令（直接 fail fast）
| ❌ 错误 | ✅ 正确 | 原因 |
|---|---|---|
opencli gemini chat "..." |
opencli gemini ask "..." |
没有 chat 子命令 |
opencli grok chat "..." |
opencli grok ask "..." |
只有 ask 子命令 |
opencli grok new |
opencli grok ask "..." --new true |
grok 的"新对话"是 ask 的参数 |
opencli gemini query "..." |
opencli gemini ask "..." |
没有 query 子命令 |
完整子命令速查（运行 opencli grok --help 或 opencli gemini --help 查看）：
Grok:
ask <prompt> # 唯一命令
Gemini:
ask <prompt> # 最常用
new # 开新对话
deep-research <prompt> # Deep Research 模式
deep-research-result [query] # 取 Deep Research 结果
image <prompt> # 图片生成
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.
- 5d ago First seen · 175 lines · 95 tokens per session scan A 690f661fb314
ask-opencli is a skill published in the GitHub repository majiayu000/spellbook (265 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,057 once invoked, about $0.0005 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
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
Interceptor
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…
cli-anything-macrocli
Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes macro run and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).
BrightData
4-tier progressive web scraping that auto-escalates WebFetch to curl to Interceptor to Bright Data proxy for bot detection and CAPTCHAs, with single-URL and multi-page crawl modes, output as markdown. USE WHEN Bright Data, scrape URL, web scraping, bot detection, crawl site, CAPTCHA, can't access, site blocking…
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.