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 lu90/industry-research-skill --skill industry-researchgit clone --depth 1 https://github.com/lu90/industry-research-skillWrote 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/lu90/industry-research-skill/industry-research)<a href="https://agentmods.dev/skills/lu90/industry-research-skill/industry-research"><img src="https://agentmods.dev/badge/skills/lu90/industry-research-skill/industry-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.
<a href="https://agentmods.dev/skills/lu90/industry-research-skill/industry-research"><img src="https://agentmods.dev/badge/skills/lu90/industry-research-skill/industry-research.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 | $0.00064 | $0.04387 |
| Opus 5 | $0.00032 | $0.02194 |
| Sonnet 5 | $0.00013 | $0.00877 |
| Haiku 4.5 | $0.00006 | $0.00439 |
Grade A, and why
industry-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 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.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Industry Research
Use this skill to produce structured industry research like a business analyst. The default output is Markdown. Do not generate PDF, PPT, webpage, or XMind unless the user explicitly asks after the Markdown report is complete.
Core Workflow
- Classify the user request.
- Select the output language using
references/report-language.md. - Build an internal research brief that translates the user's request into a report route, template, source plan, output language, and depth contract; use visible brief or prompt mode only when triggered by
references/research-brief-builder.md. - Define the problem and research boundary.
- Decompose the problem if the user asks a specific question.
- Build a WBS research plan and run the Deep Research Engine for standard or deep reports.
- Build and show the industry map before lifecycle analysis.
- Collect, clean, classify, compress, and synthesize information.
- Judge industry lifecycle stage.
- Analyze the seven core modules.
- Create a working draft and initial v64 Claim bindings, then run the v65 Pressure Test closure by default.
- Rewrite the draft from resolved Challenges, rerun affected v64 admission and binding, and pass the v64 final fidelity audit.
- Output and register the report using the matching template and selected language only after every formal gate passes.
Request Types
Classify the request by the user's underlying intent, not by whether the wording is formal or complete.
- Industry overview: the user wants to understand an industry, market, sector, track, business category, or opportunity space, even if the industry boundary is vague.
- Industry-specific question: the user asks about a phenomenon, cause, trend, opportunity, risk, competition, price war, policy impact, profitability, lifecycle, or future direction related to an industry.
- Company/product analysis: the user asks about a company, product, project, brand, business line, or startup idea, and its position, prospects, risks, or competitiveness in an industry context.
What ships with it
46 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.
- assets/company-product-template.md 25 KB
- assets/industry-overview-template.md 11 KB
- assets/research-prompt-template.md 6.1 KB
- assets/specific-question-template.md 11 KB
- LICENSE 11 KB
- references/capital-market-question.md 3.0 KB
- references/common-report-section-contract.md 18 KB
- references/company-product-few-shot.md 11 KB
- references/company-product-output-contract.md 6.1 KB
- references/deep-research-engine.md 13 KB
- references/deep-search-protocol.md 14 KB
- references/industry-map.md 1.6 KB
- references/industry-overview-output-contract.md 3.1 KB
- references/information-sources.md 4.7 KB
- references/institutional-report-benchmarks.md 3.5 KB
- references/layered-analysis.md 2.8 KB
- references/lifecycle.md 1.5 KB
- references/output-format.md 12 KB
- references/pressure-test.md 7.9 KB
- references/primary-source-first.md 5.8 KB
- references/problem-decomposition.md 1.3 KB
- references/profitability-indicators.md 2.1 KB
- references/prosperity-indicators.md 2.3 KB
- references/report-compliance.md 9.4 KB
- references/report-depth-rubric.md 3.1 KB
- references/report-language.md 6.2 KB
- references/report-output-modes.md 4.6 KB
- references/report-regression-tests.md 20 KB
- references/research-brief-builder.md 9.6 KB
- references/research-pipeline.md 1.6 KB
- references/research-plan.md 1.2 KB
- references/routing-sanity-check.md 6.3 KB
- references/section-depth-playbook.md 4.7 KB
- references/seven-modules.md 1.7 KB
- references/source-registry-company-and-market.md 5.4 KB
- references/source-registry-official-and-industry.md 5.7 KB
- references/source-registry-research-and-technology.md 5.7 KB
- references/source-registry-schema.md 7.2 KB
- references/specific-question-output-contract.md 3.5 KB
- references/user-intake.md 1.7 KB
- references/valuation-logic.md 1.6 KB
- scripts/deep_search_contract_check.py 52 KB runs code
- scripts/report_batch_check.py 5.0 KB runs code
- scripts/report_contract_check.py 224 KB runs code
- scripts/source_contract_check.py 20 KB runs code
- scripts/truthfulness_contract_check.py 42 KB runs code
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 · 163 lines · 64 tokens per session scan A 5080b5a1ff68
industry-research is a skill published in the GitHub repository lu90/industry-research-skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 4,387 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 2026-08-31.
Other skills, from other repositories
gr-competitor
A competitor research workflow that collects information from rival websites, including landing pages, pricing, blogs, and past changes. Wayback refers to the Internet Archive’s record of older versions of websites.
mapping-markets
Map the market around any company from its domain alone — competitors, substitutes, the infrastructure it sits on, the directories that list it, the publications that cover it and the communities its buyers argue in — with a source and a reason on every entry. Use this skill whenever someone wants a competitive…
falsify
Adversarial falsification of sigint research findings. Generates disconfirming queries, executes web-only adversarial search, assigns ordinal verdicts (falsified | weakened | survived | inconclusive), and applies remediation (quarantine, confidence downgrade, follow-up queue). Invocable standalone via /sigint:falsify…
regulatory-review
This skill should be used when the user asks to "analyze regulations", "regulatory landscape", "compliance requirements", "legal considerations", "regulatory risk", "industry regulations", "compliance analysis", "regulatory trends", or needs guidance on understanding regulatory environments, compliance requirements…
augment
Deep-dive into a specific area of current research. Orchestrates a single dimension-analyst using full swarm pattern (TeamCreate, TaskCreate, SendMessage). Use when the user wants to augment current research with deeper analysis of a specific area.
market-sizing
This skill should be used when the user asks to "calculate market size", "TAM SAM SOM analysis", "estimate market opportunity", "market sizing", "total addressable market", "serviceable market", "market potential", or needs guidance on market size estimation methodologies, market opportunity calculations, or growth…