scout

A market-research agent that studies competitors, industries, market size, and areas where few businesses currently compete. It turns its findings into a recommended decision, with a confidence level and a date showing when the information may become outdated.

In plain words
What is it for?
Use it to compare competitors, understand an industry, estimate market opportunity, find underserved areas, and support strategic decisions.
Why use it?
It reduces the work of collecting scattered market information and helps separate observed facts from guesses. It also makes uncertainty and potentially stale research visible.

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/nxtg-ai/forge-plugin/scout
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,932 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 $0.00000 $0.01932
Opus 5 $0.00000 $0.00966
Sonnet 5 $0.00000 $0.00386
Haiku 4.5 $0.00000 $0.00193

Measured 2d ago against content hash 4ce94e37abe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scout 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 2d 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.

docs/agents/scout.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout

The competitive intelligence specialist who turns raw market signals into strategic advantage -- every output ends with "so what should we do about it," not "here are some facts."

Level L1 Vibe Coder
Category Executive & Strategy
Model Sonnet

What It Does

The Scout produces actionable intelligence that drives decisions, not slide decks that gather dust. It tracks competitors, maps ecosystems, sizes markets, and identifies strategic whitespace -- but every analysis ends with a specific decision recommendation, a confidence level, and an expiration date.

It follows a rigorous anti-bias protocol: steel-man competitors first (if you cannot explain why a customer would choose them, you do not understand them), separate observation from interpretation, name your unknowns explicitly, apply the reversal test (would your analysis survive if competitors were analyzing you?), triangulate every claim from at least two independent sources, actively track disconfirming evidence, and time-stamp everything (market intelligence decays -- anything older than 90 days is potentially stale).

The Scout operates across ten analytical playbooks: competitor feature matrices, pricing comparison analysis, market sizing (TAM/SAM/SOM with both top-down and bottom-up), technology trend monitoring, patent and IP landscape scanning, open source ecosystem mapping, acquisition and funding tracking, SWOT analysis, Porter's Five Forces, and Blue Ocean strategy identification. Each playbook produces structured output with findings, decisions required, blind spots acknowledged, and next collection targets.

When to Use It

  • Competitive landscape mapping: When you need a detailed feature matrix comparing your product against specific competitors, with honest strengths and weaknesses on both sides.
  • Market sizing: When you need TAM/SAM/SOM estimates for a product launch or investor communication, validated with both top-down and bottom-up methods.
  • Competitor tracking: When you need to know what a specific competitor has shipped recently, how their adoption is trending, and what their hiring patterns signal.
  • Strategic whitespace identification: When you want to find the gaps in the market that no one is filling, validated by demand signals.
  • Open source ecosystem analysis: When you need to understand which technologies in your space are rising, plateauing, or declining, and what that means for your positioning.

Read the full file on GitHub · 141 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. 2d ago First seen · 141 lines · 0 tokens per session scan A 4ce94e37abe1

Subscribe to this mod's changes

scout is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,932 tokens. 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.