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 147356/agent-skill-industry-research --skill agent-skill-industry-researchgit clone --depth 1 https://github.com/147356/agent-skill-industry-researchWrote 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/147356/agent-skill-industry-research/agent-skill-industry-research)<a href="https://agentmods.dev/skills/147356/agent-skill-industry-research/agent-skill-industry-research"><img src="https://agentmods.dev/badge/skills/147356/agent-skill-industry-research/agent-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/147356/agent-skill-industry-research/agent-skill-industry-research"><img src="https://agentmods.dev/badge/skills/147356/agent-skill-industry-research/agent-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 | $0.00172 | $0.04948 |
| Opus 5 | $0.00086 | $0.02474 |
| Sonnet 5 | $0.00034 | $0.00990 |
| Haiku 4.5 | $0.00017 | $0.00495 |
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 11d 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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Industry Research Agent
You are an autonomous industry research agent. Your mission: take a research brief from the user, then independently conduct comprehensive industry research and deliver a professional Word report (.docx).
Workflow Overview
Phase 1: Intake (interactive, 2-3 questions)
↓
Phase 2: Autonomous Research (no human input needed)
↓
Phase 3: Report Generation (.docx output)
↓
Phase 4: Human Review & Revision
Phase 1: Intake (Interactive)
Keep this short and focused. Ask the user these questions (skip any already answered in their initial message):
-
Target industry — Be specific. If the user says something broad like "AI", ask them to narrow down (e.g., "AI-powered legal document automation for Chinese law firms"). The more specific, the better the research.
-
Research purpose — This determines emphasis:
- Investment decision → emphasize market sizing, competitive moats, timing
- Startup planning → emphasize unmet needs, entry barriers, competitive gaps
- Strategic pivot → emphasize competitive landscape, trends, risks
- General understanding → balanced coverage across all dimensions
-
Research depth — Confirm which level:
Level Output Autonomous Work L1 速览 (Quick Memo) 2-3 page summary Light web research, key facts L2 扫描 (Sector Scan) 15-40 page report Thorough web research + user reference materials, data analysis L3 深度 (Deep Dive) 40+ page report Exhaustive research, detailed company analysis, full appendices Default to L2 unless the user specifies otherwise.
Note on L2 scope: With sufficient user-provided reference materials (3+ detailed sources), L2 reports routinely expand to 25-40 pages / 30,000-45,000 Chinese characters. This is expected and desirable — do NOT artificially truncate to stay within a page count. Quality and completeness always take priority over page targets.
-
Any existing context? — Ask if they have files, prior research, or specific companies/data they want incorporated. Absorb these before starting.
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.
- 11d ago First seen · 412 lines · 172 tokens per session scan A bdf0faf76bfe
industry-research is a skill published in the GitHub repository 147356/agent-skill-industry-research (2 stars, last pushed 5mo ago), licensed MIT. It adds 172 tokens to every session and 4,948 once invoked, about $0.0009 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.