Company Researcher

Company Researcher is an agent for Claude Code from stripe/ai. It costs 18 tokens per session (1,783 once invoked), scanned A, original, MIT.

A research role that studies a company and maps its business and payment flows to Stripe Connect, Stripe's system for payments between platforms, sellers, and buyers. It can use a website or company description to identify the likely integration shape.

In plain words
What is it for?
Use it to research a company, examine its website and pricing or workflow pages, identify sellers and buyers, and inform Stripe Connect integration decisions.
Why use it?
It helps clarify who receives money, who pays fees, and whether the business is a marketplace, platform, or software service before choosing a payment setup.

Agent for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter.

Part of the stripe plugin — 2 commands, 1 agent, 1 MCP server shipped together

Good fit Use it to research a company, examine its website and pricing or workflow pages, identify sellers and buyers, and inform Stripe Connect integration decisions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stripe/ai/company-researcher
About the project

Stripe AI is a collection of SDKs, tools, an MCP server, and agent skills for building AI products and businesses with Stripe's billing infrastructure. Developers use it to connect Stripe payments and metering to language models and agent frameworks, while the catalogue entries provide Stripe-specific skills, commands, plugins, and agent integrations.

stripe/ai · 1,795 stars · on GitHub · docs.stripe.com

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.

Clone the repo
git clone --depth 1 https://github.com/stripe/ai

Made for: Claude Code.

Or install stripe, the plugin that ships this one along with the rest of its 2 commands, 1 agent, 1 MCP server.

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 Company Researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/stripe/ai/company-researcher/github.svg)](https://agentmods.dev/agents/stripe/ai/company-researcher)
Your own site
<a href="https://agentmods.dev/agents/stripe/ai/company-researcher"><img src="https://agentmods.dev/badge/agents/stripe/ai/company-researcher/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.

agentmods 80×15 button for Company Researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/stripe/ai/company-researcher"><img src="https://agentmods.dev/badge/agents/stripe/ai/company-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,783 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.01783
Opus 5 $0.00009 $0.00892
Sonnet 5 $0.00004 $0.00357
Haiku 4.5 $0.00002 $0.00178

Measured 10d ago against content hash c7a14f4fb6c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Company Researcher 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.

providers/claude/plugin/agents/company-researcher.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Company Researcher Agent

Research a company using its website URL or a text description, then map findings to the Stripe Connect decision matrix. Produces a structured analysis with confidence levels that the calling skill uses to auto-fill discovery questions.

Inputs

You will receive one or both of:

  • Company URL — a website to fetch and analyze
  • Company description — freeform text about what the business does

Instructions

Step 1 — Gather company information from the web

If a URL is provided:

  1. WebFetch the homepage. Prompt: "Extract: what this company does, who the sellers/providers are, who the buyers/customers are, how payments and money flow between parties, any pricing or fee information, and whether this is a marketplace, platform, or SaaS product."

  2. Attempt to fetch deeper pages for additional signals. Try these URL suffixes in parallel and use whatever succeeds:

    • /about, /about-us, /how-it-works — for business model clarity
    • /pricing, /plans — for fee structure
  3. If the homepage fetch fails (403, 404, timeout, empty content), fall back to WebSearch using the domain name plus "business model how it works".

If only a description is provided (no URL):

  1. WebSearch for the company name (if identifiable) plus "business model" and "pricing".
  2. If the description is generic (e.g. "I'm building a marketplace"), skip web search — classify directly from the description text. Maximum confidence for description-only inferences is MEDIUM.

If both WebFetch and WebSearch are unavailable or fail:

If no description text is available (URL-only input and web research failed), return the early-exit output from Step 4 with all dimensions set to LOW confidence and the note: "Web research unavailable and no description provided. Cannot perform research."

Otherwise, classify directly from the provided description text and codebase signals (Step 2). Cap all web-derived dimensions at LOW confidence and note: "Web research unavailable — classification based on description and codebase signals only."

Read the full file on GitHub · 117 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. 10d ago First seen · 117 lines · 18 tokens per session scan A c7a14f4fb6c9

Subscribe to this mod's changes

Company Researcher is an agent published in the GitHub repository stripe/ai (1,795 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 1,783 once invoked, about $0.0001 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.

Related

Other agents, from other repositories