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.
git clone --depth 1 https://github.com/prashishh/seo-geo-report-engineWrote 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.
[](https://agentmods.dev/agents/prashishh/seo-geo-report-engine/data-researcher)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Ahrefs MCP — primary engine (Site Explorer, Keywords Explorer, Rank Tracker, GSC, Web
Analytics). See
knowledge/ahrefs-mcp-map.md. - CLI connectors / owned data — GSC + web analytics for the owned truth (clicks, sessions).
- Web —
WebSearch/WebFetchfor 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. Checksubscription-info-limits-and-usagebefore 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-keywordsactuals, or estimated traffic vsweb-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 flags —
solid/estimate/unverifiedper figure; list what you could not get.
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.
- 9d ago First seen · 50 lines · 91 tokens per session scan A 36c9111844af
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.
Other agents, from other repositories
TEAM_USAGE
Agent "TEAM_USAGE" from Auriti-Labs/geo-optimizer-skill, covering agent team usage guide, geoready / geo optimizer, 1. agent inventory, 2. read-only reviewers and 3. code-writing implementation agents.
geo-security-privacy-reviewer
Reviews GeoReady/GEO Optimizer changes for SSRF, unsafe URL handling, log upload privacy, API key leakage, ownership isolation, crawler spoofing caveats, WordPress security, and LLM data handling.
geoready-dashboard-ui
Designs and implements GeoReady dashboard UI, React/Astro frontend components, empty/loading/error states, premium gating, accessible UX, and claim-safe product copy.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.