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 skills add shirleyharleywiley/multi-agent-deepresearch --skill research-multi-agentgit clone --depth 1 https://github.com/shirleyharleywiley/multi-agent-deepresearchWrote 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/shirleyharleywiley/multi-agent-deepresearch/research-multi-agent)<a href="https://agentmods.dev/skills/shirleyharleywiley/multi-agent-deepresearch/research-multi-agent"><img src="https://agentmods.dev/badge/skills/shirleyharleywiley/multi-agent-deepresearch/research-multi-agent/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.
<a href="https://agentmods.dev/skills/shirleyharleywiley/multi-agent-deepresearch/research-multi-agent"><img src="https://agentmods.dev/badge/skills/shirleyharleywiley/multi-agent-deepresearch/research-multi-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00072 | $0.14092 |
| Opus 5 | $0.00036 | $0.07046 |
| Sonnet 5 | $0.00014 | $0.02818 |
| Haiku 4.5 | $0.00007 | $0.01409 |
Grade A, and why
research-multi-agent scanned grade A with 1 finding 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.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Phase A → curl 爬取(工具前置,P0,必须先于 agents 执行) How it starts
The opening of the file, as written. The whole thing — 1,113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
多角色多轮迭代深度调研方法论
六角色三层架构 × 多轮迭代 × 工具前置
Role 0:调研类型选择
调研启动时先确定调研类型,不同类型对应不同的信息源优先级、终止条件和输出格式。
| 类型 | 核心问题 | 侧重点 | 终止条件差异 |
|---|---|---|---|
| 竞品分析 | X vs Y 谁更好?为什么? | 差异点、优劣势、时机 | 核心差异是否已覆盖 |
| 技术选型 | 选 A 还是 B? | 约束、性能、社区、成本 | 技术风险是否已评估 |
| 市场研究 | 市场规模和趋势? | 规模、增速、用户画像 | 数据是否可交叉验证 |
| 人物研究 | 这人是谁?为什么成功? | 背景、动机、关系网 | 关键事件链是否完整 |
| 政策研究 | 政策如何影响行业? | 监管要点、合规风险、豁免条件 | 政策原文是否已覆盖 |
| 供应链研究 | 产业链上下游关系? | 关键环节、议价能力、替代风险 | 核心供应商是否已识别 |
| 观点论证 | 验证某个观点是否成立? | 论据质量、反驳角度、来源可信度 | 核心论据是否已覆盖正反两面 |
| 企业研究 | 这个企业是如何运作的? | 商业模式、组织架构、核心能力 | 核心机制是否已清晰描述 |
执行方式:当用户提供调研主题时,主动询问调研类型。如果用户未指定,根据主题特征自动推断并告知用户。
方法论核心架构
输入:调研主题 + 约束条件(如"面向CEO"、"只讲X自身")
↓
【快速洞察层 QuickInsight】
↓
Phase A → curl 爬取(工具前置,P0,必须先于 agents 执行)
↓
Phase B → Role 1(并行探针):将主题拆解为 N 个子方向,错峰并行搜索
输入 ← 主题 + 约束条件
输出 → 原始发现列表(每个 agent 一个子方向的结果)
↓
Phase C → Role 4(信息综合):实时合并新发现,识别已确认/有冲突/未知
输入 ← Role 1 的原始发现列表
输出 → 结构化合并发现(含:已确认N条、有冲突N条、未知N条)
↓
Phase D → Role 6(边界守卫):检查约束条件是否满足
输入 ← 合并发现 + 约束条件
输出 → 约束合规清单(每条约束:✓合规 / ⚠越界→已纠正)
↓
【元认知层 MetaInsight】
↓
Phase E → Role 2(差距分析):识别信息差距,指导下一轮搜索
输入 ← Role 4 合并结果(重点:未知条目)
输出 → 优先缺口列表(每条:缺口名称 — 预期来源 — 边际收益)
↓
Phase F → Role 3(知识整合):将多轮发现整合为完整叙事
输入 ← Role 4 合并结果 + Role 6 合规清单
输出 → 调研报告草稿(含:发现 + 缺口说明 + 参考来源)
↓
【判断层 XInsight】
↓
Phase G → Role 5(终止判断):综合所有前置输出,决定继续或终止
输入 ← Role 2 差距分析 + Role 3 草稿 + Role 6 合规清单
输出 → 终止/继续判定 + 下一步优先缺口
终止条件(必须全部满足):
① 核心问题已解决
② 高价值发现最低可信度 ≥ 中高
③ Role 6 约束合规 ✓
④ 剩余缺口属于结构性限制
→ 全部满足 → 终止迭代,进入 Phase H
→ 任一未满足 → 进入下一轮迭代
↓
【输出层 OutputInsight】
↓
Phase H → Role 7(多读者差异化输出):面向不同读者生成差异化报告版本
输入 ← 最终报告草稿 + 目标读者列表 + 原始约束条件
输出 → 面向各读者的独立报告版本(CEO版/CTO版/运营版等)
执行时机 → Phase G 终止判定后(仅执行一次)
→ 多读者场景:并行产出差异化版本
→ 单读者场景:直接输出适配版本
↓
输出:完整调研报告 + 信息缺口说明 + 参考来源 + 多读者版本(可选)
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.
- 10d ago First seen · 1,113 lines · 72 tokens per session scan A 00d34aad7200
research-multi-agent is a skill published in the GitHub repository shirleyharleywiley/multi-agent-deepresearch (11 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 14,092 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…