multi-ai-research

multi-ai-research is a skill for Claude Code, Codex from majiayu000/spellbook. It costs 134 tokens per session (3,681 once invoked), scanned A, original, MIT.

A research workflow that sends one question to several AI systems and internal agents, then compares their findings. It groups results by agreement, disagreement, and confidence.

In plain words
What is it for?
Use it for deep research, cross-checking technical or industry claims, testing assumptions, and producing ranked conclusions and follow-up actions.
Why use it?
It reduces reliance on one answer when a topic is complex, current, or uncertain. Conflicting evidence is surfaced instead of being silently merged.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for deep research, cross-checking technical or industry claims, testing assumptions, and producing ranked conclusions and follow-up actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/spellbook/multi-ai-research
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 majiayu000/spellbook --skill multi-ai-research
Clone the repo
git clone --depth 1 https://github.com/majiayu000/spellbook

Made for: Claude Code, Codex.

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 multi-ai-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/spellbook/multi-ai-research/github.svg)](https://agentmods.dev/skills/majiayu000/spellbook/multi-ai-research)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/spellbook/multi-ai-research"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/multi-ai-research/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 multi-ai-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/spellbook/multi-ai-research"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/multi-ai-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,681 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 317
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00134 $0.03681
Opus 5 $0.00067 $0.01840
Sonnet 5 $0.00027 $0.00736
Haiku 4.5 $0.00013 $0.00368

Measured 7d ago against content hash 506476bf538d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

multi-ai-research 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 7d 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.

skills/multi-ai-research/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-AI Research(并行多 AI 交叉验证)

核心价值:能力乘法,不是加法。Claude(主脑)+ grok(X 社区/实时)+ gemini(Google 生态/结构化)+ N 个内部 sub-agent = N+3 个 agent 并行处理同一个研究问题。

关键洞察(2026-04-08 实战验证):两个独立外部 AI 的共识信号 强于 任何单个 AI 的深度。"更深度" < "更少错"。

和 ask-opencli 的关系

  • ask-opencli = 单次 grok 或 gemini 调用(日常 second opinion)
  • multi-ai-research = 完整调研工作流,并行多 AI + 内部数据 + 交叉验证 + 自动仲裁

如果用户只是想"问 grok 一个问题",用 ask-opencli。如果用户要做"深度调研"或"交叉验证多个维度",用这个 skill。


何时触发

✅ 适合

  • 深度研究任务(手动做 >30 分钟)
  • 行业机制问题(算法规则、产品决策、社区共识)
  • 需要外部共识加权的内部数据推断
  • 时效性问题(grok 有实时 X 数据,gemini 有最新 web 索引)
  • 反转既有假设(数据 vs 理论冲突时仲裁)
  • 新工具/新做法的可行性调研

❌ 不适合

  • 纯代码推理(单个 Claude 足够)
  • 需要深度项目 context 的任务(外部 AI 不了解你的代码库)
  • 快速事实问答(<30 秒能解决,并行开销不值)
  • 创意生成(单家强模型即可)

工作流(7 Phase)

Phase 1:问题分解(Claude 自动 + 用户可覆盖)

从用户的一个研究问题,自动拆分成:

  1. 内部数据查询(1-5 个 sub-agent 并行)

    • 数据分布/量化分析
    • 内容对比/质性分析
    • 多维度切分
    • 时序/趋势分析
    • (按需增加)
  2. 外部理论查询(2 个 Bash 并行)

    • grok:侧重实时/社区/X 信号
    • gemini:侧重结构化/框架/长推理

默认分解策略

  • 3 个内部 agent + 2 个外部 AI = 5 个并行任务
  • 如果用户问题偏理论 → 减少内部 agent 到 1-2 个,加大外部 AI 权重
  • 如果用户问题偏数据 → 加到 4-5 个内部 agent,只跑 2 个外部 AI 做交叉

用户可覆盖:用户明确说"只问 grok 和 gemini"或"只派内部 agent"时按用户指令。

Phase 2:Prompt 自动生成

对每个并行任务,自动生成具体 prompt:

内部 agent prompt 模板
你的任务是**只读数据分析**,不要修改任何文件。

## 背景
{{研究问题的 2-3 句背景描述}}

## 数据源
{{数据库路径或文件列表}}

## 任务
{{具体要查的维度,1-5 个 task}}

## 输出格式
- 结构化 markdown 报告
- 每个结论标注 n(样本数)和 置信度
- 3 屏幕内
- 纯文本返回,不要尝试写文件
grok / gemini prompt 模板
{{研究问题的精简描述,≤300 字}}

具体问:
(1) {{子问题 1}}
(2) {{子问题 2}}
...

请基于 2026 年上半年真实情况/最新数据回答,要具体可引用。

关键要求:问 grok 和 gemini 的 prompt 必须一致(独立对比的前提)。

Phase 3:并行派发(一条消息多个工具调用)

Tool 1: Agent (general-purpose)  run_in_background=true  [内部数据 agent A]
Tool 2: Agent (general-purpose)  run_in_background=true  [内部数据 agent B]
Tool 3: Agent (general-purpose)  run_in_background=true  [内部数据 agent C]
Tool 4: Bash run_in_background=true  [OPENCLI_BROWSER_COMMAND_TIMEOUT=300 opencli grok ask "..." --timeout 300 -f json]
Tool 5: Bash run_in_background=true  [opencli gemini ask "..." --format plain]

Read the full file on GitHub · 337 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. 7d ago First seen · 337 lines · 134 tokens per session scan A 506476bf538d

Subscribe to this mod's changes

multi-ai-research is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 3,681 once invoked, about $0.0007 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 2026-09-03.

Related

Other skills, from other repositories

pneuma-session

Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.

pandazki/pneuma-skills · 127 tokens

session-handoff

Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…

will-pagane/claude-superdev-harness · 91 tokens

aenv

Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…

Blevene/aenv · 176 tokens

cao-session-management

Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.

awslabs/cli-agent-orchestrator · 49 tokens

mulmoterminal-keys

Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…

receptron/mulmoterminal · 289 tokens

tokf-discover

Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.

mpecan/tokf · 24 tokens