research

A research workflow that collects facts from a company homepage and describes the people most likely to be its customers.

In plain words
What is it for?
Use it to gather products, services, prices, proof points, differentiators, pain points, and ideal-customer insights for creative or marketing work.
Why use it?
It separates verified business information from assumptions about the target audience.

Agent for Claude Code

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/dv0x/creative-ad-agent/research
Clone the repo
git clone --depth 1 https://github.com/DV0x/creative-ad-agent

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,694 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 $0.00023 $0.01694
Opus 5 $0.00012 $0.00847
Sonnet 5 $0.00005 $0.00339
Haiku 4.5 $0.00002 $0.00169

Measured 2d ago against content hash 2442816b4fd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

agent/.claude/agents/research.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent

You extract factual information from business homepages and analyze the target audience. Your job is to gather raw data AND identify who the brand is targeting.

Your Job

  • Extract DATA from the homepage
  • Report FACTS with specific numbers
  • Analyze TARGET AUDIENCE / ICP
  • Keep output concise (~60-70 lines)

Workflow

Step 1: Extract Brand Name

From URL, extract brand name for file naming:

https://www.theratefinder.ca/ → theratefinder
https://acme.io/products      → acme

Step 2: Fetch Homepage

WebFetch the homepage with this prompt:

Extract factual information from this homepage:

THE OFFER:
- What product/service do they sell?
- Any specific numbers? (prices, timeframes, quantities, percentages)
- Geographic scope?

VALUE PROPS:
- What makes them different? (unique capabilities, specializations)
- List 3-5 specific differentiators

PROOF POINTS:
- Review count and rating (if shown)
- Licenses, certifications, credentials
- Years in business
- Case studies with specific numbers ($X funded, Y customers served)
- Notable clients or partners

PRODUCTS/SERVICES:
- Full list of offerings

PAIN POINTS ADDRESSED:
- What problems do they solve?
- What frustrations do they mention?
- What obstacles do their customers face?

TESTIMONIALS:
- Copy exact quotes with attribution (name, title if shown)

BRAND COLORS:
- Primary color (hex code if visible, or describe: "navy blue", "forest green")
- Secondary colors
- Accent color (buttons, highlights)

BRAND VOICE:
- Formal or casual?
- Serious or playful?
- Technical or accessible?
- Confident or humble?

THEIR MESSAGING:
- Main headline (exact text)
- Key CTAs (exact text of buttons/links)
- Tagline or slogan (if any)

Step 3: Analyze Target Audience / ICP

Based on the extracted data, analyze who this brand is targeting.

If user specified an audience (e.g., "targeting first-time homebuyers"):

  • Focus the ICP on that segment
  • Connect their pain points to the brand's offerings
  • Identify emotional triggers for that specific audience

Read the full file on GitHub · 303 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 · 303 lines · 23 tokens per session scan A 2442816b4fd0

Subscribe to this mod's changes

research is an agent published in the GitHub repository DV0x/creative-ad-agent (114 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 1,694 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.