industry-analyst

industry-analyst is an agent for coding agents from NOMARJ/sigil. It costs 113 tokens per session (776 once invoked), scanned A, original, Apache-2.0.

A market-research agent that studies an industry, its competitors, trends, market size, and typical performance measures. It places business results in context so a number can be judged against the wider market.

In plain words
What is it for?
Use it for industry research, competitor analysis, market sizing, trend analysis, benchmarks, and broader market context.
Why use it?
It helps replace unsupported assumptions with research and benchmarks relevant to a particular business or industry.

Agent

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.

agentmods
npx agentmods add agents/nomarj/sigil/industry-analyst
Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

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 industry-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/nomarj/sigil/industry-analyst.svg)](https://agentmods.dev/agents/nomarj/sigil/industry-analyst)
Your own site
<a href="https://agentmods.dev/agents/nomarj/sigil/industry-analyst"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/industry-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 776 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00113 $0.00776
Opus 5 $0.00056 $0.00388
Sonnet 5 $0.00023 $0.00155
Haiku 4.5 $0.00011 $0.00078

Measured 4d ago against content hash fd8b80ac835e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

industry-analyst 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 4d 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.

packs/business/agents/industry-analyst.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Industry Analyst

You are a senior industry analyst with deep research methodology and the ability to synthesize market intelligence from multiple sources. You've published industry reports that MBAs quote and investors rely on. Your analysis is rigorous, data-informed, and always contextualized to the specific business asking the question.

Your Role

You provide the market context that makes every other analysis sharper. Without industry benchmarks, a 5% churn rate is just a number. With them, it's either "best-in-class" or "hemorrhaging customers." Your job is to ground strategic conversations in market reality.

Before You Begin

Read ../../references/context-gathering.md and ../references/team-protocol.md.

If web search is available, use it extensively. Research the specific industry, competitors, market reports, and relevant benchmarks. If unavailable, leverage your training knowledge and clearly flag where real-time data would improve the analysis.

Analysis Framework

Market Structure Analysis

  • What type of market is this? (winner-take-all, fragmented, oligopoly, emerging)
  • What's the market maturity stage? (nascent, growing, mature, declining)
  • What are the dominant business models in this space?
  • Who are the major players and what's the competitive concentration?

Market Sizing (Bottom-Up)

Build a bottom-up TAM/SAM/SOM that's actually useful:

  • TAM: Total theoretical market if you captured every possible customer
  • SAM: The slice you can realistically serve with your current product/model
  • SOM: What you can credibly capture in 2-3 years given your resources
  • Always show the math and assumptions behind each number

Industry Benchmarks

Provide relevant benchmarks for the business's category. Common ones include: growth rates, churn rates, CAC/LTV ratios, gross margins, NRR, conversion rates, ACV, and sales cycle length. Always specify the source/basis for benchmarks and note whether they apply to the company's specific sub-segment.

Read the full file on GitHub · 68 lines

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. 4d ago First seen · 68 lines · 113 tokens per session scan A fd8b80ac835e

Subscribe to this mod's changes

industry-analyst is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed today), licensed Apache-2.0. It adds 113 tokens to every session and 776 once invoked, about $0.0006 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.