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 zhangxiaoqiang1991/luopan --skill industrygit clone --depth 1 https://github.com/zhangxiaoqiang1991/luopanWrote 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/zhangxiaoqiang1991/luopan/industry)<a href="https://agentmods.dev/skills/zhangxiaoqiang1991/luopan/industry"><img src="https://agentmods.dev/badge/skills/zhangxiaoqiang1991/luopan/industry/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/zhangxiaoqiang1991/luopan/industry"><img src="https://agentmods.dev/badge/skills/zhangxiaoqiang1991/luopan/industry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.02249 |
| Opus 5 | $0.00019 | $0.01125 |
| Sonnet 5 | $0.00008 | $0.00450 |
| Haiku 4.5 | $0.00004 | $0.00225 |
Grade A, and why
luopan-industry 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 13d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
罗盘 · 行业研究模式
不输出百科，输出判断。
本文件负责行业研究的执行顺序和门控。完整指标、搜索策略、HTML/Markdown 模板及检查清单位于 references/full-methodology.md。
强制加载规则
开始行业研究后，必须完整读取一次 references/full-methodology.md，再执行搜索和写作。不得只凭本文件的摘要生成报告。
具体读取时机：
| 阶段 | 何时读取参考文件 | 使用内容 |
|---|---|---|
| 开始研究前 | 确认对象是行业或赛道后立即读取 | 使用说明、信源分级、行业类型矩阵、搜索策略 |
| 建立公司清单时 | Phase 3 开始前回看相应章节 | 权力分层八项指标、Top 10 规则、竞争格局五步法 |
| 生成报告前 | Phase 5 完成后回看模板章节 | HTML 与 Markdown 双格式模板、判断式标题规范 |
| 交付前 | 初稿完成后回看末尾章节 | 对抗验证、自检、红线、失败模式 |
参考文件是强制规则，不是可选资料；其中所有门控、红线和诚实原则均有效。
适用范围
以下意图进入本模式：
- 了解或研究某个行业、赛道、产业链；
- 判断行业结构、市场规模、商业模式或竞争格局；
- 判断某行业是否值得求职、创业或进入；
- 比较行业中的上中下游权力与代表公司。
具体公司、品牌、股票、Offer 或岗位研究应返回根路由，改用 ../company/SKILL.md，不得套用行业 Top 30 流程。
交付目标
报告必须同时回答：
- 这个行业究竟是做什么的？
- 钱怎么挣、谁在挣、谁有话语权？
- 行业值不值得进入，应该从哪里进入？
输出顺序：
- 3–5 条核心判断，答案先行；
- 最少必要知识；
- 公司商业模式与竞争格局；
- 行业前景、风险与行动建议；
- 数据来源与信息局限。
同时输出 HTML 和 Markdown。两份报告必须来自同一组事实与来源，内容一致，仅呈现方式不同。
所有标题必须是完整判断，不能只是“市场规模”“竞争格局”等主题标签。
三项底层机制
1. 信源分级
- A 级：公司财报、招股书、官方公告等一手资料；
- B 级：权威行业研究机构或媒体的一手报告；
- C 级：多家媒体交叉验证但未经官方确认的信息。
C 级来源必须明确写“未经官方证实”。所有数字和关键事实必须附原始链接，禁止使用模糊的“业内人士称”。详细口径以参考文件为准。
2. 对抗验证
初稿完成后，以挑刺者视角检查：
- 是否存在没有数据支撑的断言；
- 是否把相关性写成因果关系；
- 是否使用不对等口径比较；
- 三个最重要数字的来源是否足够可靠；
- 删除任何核心判断后，报告逻辑是否仍然成立。
3. 诚实原则
- 假设发生变化必须交代；
- 搜不到的信息写“公开信息有限”，不得补造；
- 数据冲突时保留双方口径并解释可信度；
- 估算必须写明方法、假设和误差边界。
执行流程
Phase 0：确认对象与用户视角
确认研究对象是行业而非具体公司。根据已有语境识别用户偏向求职、创业或通用研究；只有该差异会显著改变报告且上下文无法判断时，才问一个简短问题。
Phase 0.5：识别行业类型
将行业识别为消费/内容型、科技/制造型、平台/交易型、服务/人力型或政策/监管型。依据参考文件的矩阵分配政策、资本、产业链、技术、需求和人才视角权重。
搜索至少覆盖四个视角。某视角没有结果时，要更换关键词重试；仍无结果才标注公开信息有限。
Phase 1：热身搜索
至少搜索市场规模、产业链与商业模式、关键公司与最新动态；再补充代表公司、市场份额和集中度。前三组搜索合计少于五个有效结果时，提示行业名称或边界可能不准确。
Phase 2：建立 Day-1 假设
用一至两句话写初始判断。该假设用于指导验证，不是预设结论；后续事实推翻它时必须在报告中说明。
Phase 3：公司与竞争格局深挖
按“议价能力、定价权、发展空间”划分上中下游，不按传统产业链位置机械分类。
公司权力判断必须使用参考文件中的八项指标：毛利率及弹性、应收应付、预收预付、客户与供应商集中度、转换成本、经营现金流质量，并考虑研发强度。数据不足时可以定性，但必须标注。
目标是每层识别十家代表公司，但“搜到多少写多少”优先，不能为了凑数补造。资本、技术、需求、人才等不同视角发现的公司都必须汇总进统一清单。
每家公司至少说明：
What ships with it
2 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.
- 13d ago First seen · 192 lines · 39 tokens per session scan A 214e864514f7
luopan-industry is a skill published in the GitHub repository zhangxiaoqiang1991/luopan (385 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 2,249 once invoked, about $0.0002 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
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
industry-research-method
A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.
tcx-strategy
Author and manage standalone Codex strategy skills named strategy- when the user wants an agent-readable investment strategy, library entry, entry or exit criteria, sizing rule, evidence standard, or decision-ready procedure. Start tool-using management with $tcx-strategy on the first meaningful line of a root turn…
tcx-brain
Author and manage TradingCodex Investment Brains. Use when the user asks to put principles or a Wiki insight into a Brain; create, inspect, revise, or validate a user-owned investment-brain- source; or install, update, activate, deactivate, roll back, or remove a managed Brain. Natural-language source authoring is…
tcx-memory
Review past investment decisions, run point-in-time historical replays, compare resolved forecasts and forward outcomes, and validate lesson candidates. Use when the user asks what happened before, why a thesis changed, whether a strategy lesson held out of sample, or what prior evidence is relevant to a current…
tcx-wiki
Query, lint, ingest, author, and manage TradingCodex Knowledge Wikis. Use for company, product, technology, material, process, scientific, industry, or value-chain background knowledge; requests such as ‘put this in the Wiki’ or ‘promote reusable knowledge from the recent Artifact’; Obsidian-compatible Wiki…