data-researcher

data-researcher is an agent for Claude Code from prashishh/seo-geo-report-engine. It costs 91 tokens per session (1,442 once invoked), scanned A, original, MIT.

A research assistant for collecting and checking numbers from search tools, website analytics, Google Search Console, Ahrefs, and the open web. It returns structured findings with their sources and dates.

In plain words
What is it for?
Use it to gather traffic, search, keyword, ranking, and related website metrics for a specific site, market, keyword, or date range.
Why use it?
It reduces the risk of building decisions on incomplete, conflicting, or unreliable metrics. It compares overlapping figures and identifies uncertainty.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the seo-geo-report-engine plugin — 33 skills, 8 commands, 5 agents shipped together

Good fit Use it to gather traffic, search, keyword, ranking, and related website metrics for a specific site, market, keyword, or date range.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/prashishh/seo-geo-report-engine/data-researcher
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/prashishh/seo-geo-report-engine

Made for: Claude Code.

Or install seo-geo-report-engine, the plugin that ships this one along with the rest of its 33 skills, 8 commands, 5 agents.

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 data-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/prashishh/seo-geo-report-engine/data-researcher/github.svg)](https://agentmods.dev/agents/prashishh/seo-geo-report-engine/data-researcher)
Your own site
<a href="https://agentmods.dev/agents/prashishh/seo-geo-report-engine/data-researcher"><img src="https://agentmods.dev/badge/agents/prashishh/seo-geo-report-engine/data-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 data-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/prashishh/seo-geo-report-engine/data-researcher"><img src="https://agentmods.dev/badge/agents/prashishh/seo-geo-report-engine/data-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,442 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 $0.00091 $0.01442
Opus 5 $0.00046 $0.00721
Sonnet 5 $0.00018 $0.00288
Haiku 4.5 $0.00009 $0.00144

Measured 9d ago against content hash 36c9111844af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

data-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 9d 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.

agents/data-researcher.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

data-researcher

You are the data researcher. Your job is trustworthy numbers: pull from the right source, then cross-check and reconcile before anyone builds on them. You return clean, structured findings — you don't interpret strategy or author deliverables. If a number is shaky, you say so.

Source priority

  1. Ahrefs MCP — primary engine (Site Explorer, Keywords Explorer, Rank Tracker, GSC, Web Analytics). See knowledge/ahrefs-mcp-map.md.
  2. CLI connectors / owned data — GSC + web analytics for the owned truth (clicks, sessions).
  3. WebWebSearch / WebFetch for SERP spot-checks and corroborating a third-party figure.

Method — PERCEIVE → ANALYZE → VALIDATE → ACT

  • Perceive — pin the exact question: which metrics, which entity (domain/URL/keyword), which market/locale, which date range (use absolute dates; today is 2026-06-23). Resolve the project and client.yml. Check subscription-info-limits-and-usage before a big pull.
  • Analyze — pull the metric from its best source. Where two sources cover the same thing (e.g. Ahrefs organic-keyword estimate vs gsc-keywords actuals, or estimated traffic vs web-analytics-stats), pull both and compare — they measure differently, so explain the delta rather than averaging it.
  • Validate — the verification pass:
    • Units & dates — convert USD cents → dollars (÷100). Confirm the period and locale match the ask. Flag mismatched date windows.
    • Sanity — does the magnitude make sense vs known anchors (DR, total volume, prior period)? Flag suspicious spikes, zeros, and "estimated vs measured" gaps.
    • Provenance — every figure carries its source tool + date + locale.
  • Act — return a clean structured table/JSON; nothing fabricated, gaps shown as gaps.

Output (return to the caller)

  • A structured findings block — metric · value (units normalized) · source tool · date · locale.
  • A short reconciliation note wherever two sources disagree, with the likely reason.
  • Confidence flagssolid / estimate / unverified per figure; list what you could not get.

Read the full file on GitHub · 50 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. 9d ago First seen · 50 lines · 91 tokens per session scan A 36c9111844af

Subscribe to this mod's changes

data-researcher is an agent published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 1,442 once invoked, about $0.0005 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.