open-geo: Skill for Claude Code

.agents/skills/semantic-core/SKILL.md

semantic-core is a skill for Claude Code from Pupok462/open-geo. It costs 91 tokens per session (2,514 once invoked), scanned A, original, MIT.

A workflow for measuring what people search for around a product and organising those searches by purpose. It uses keyword services and produces a JSON demand core plus a CSV of questions for visibility work.

In plain words
What is it for?
Use it for keyword and demand research, search-intent grouping, question planning, and preparing data for open-geo visibility work.
Why use it?
It replaces guesses and manually typed search-volume claims with measured data that records where, when, and how each figure was collected.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

This is Pupok462/open-geo's own configuration. It tells Claude Code how to work on open-geo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-geo configures →

Part of the open-geo plugin — 2 skills, 4 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Pupok462/open-geo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Pupok462/open-geo/main/.agents/skills/semantic-core/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Pupok462/open-geo

Made for: Claude Code.

Or install open-geo, the plugin that ships this one along with the rest of its 2 skills, 4 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 semantic-core

README.md
[![agentmods](https://agentmods.dev/badge/skills/pupok462/open-geo/semantic-core/github.svg)](https://agentmods.dev/skills/pupok462/open-geo/semantic-core)
Your own site
<a href="https://agentmods.dev/skills/pupok462/open-geo/semantic-core"><img src="https://agentmods.dev/badge/skills/pupok462/open-geo/semantic-core/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 semantic-core

Your own site · 80×15
<a href="https://agentmods.dev/skills/pupok462/open-geo/semantic-core"><img src="https://agentmods.dev/badge/skills/pupok462/open-geo/semantic-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,514 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.02514
Opus 5 $0.00046 $0.01257
Sonnet 5 $0.00018 $0.00503
Haiku 4.5 $0.00009 $0.00251

Measured 3d ago against content hash aee8fac1e4f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

semantic-core 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 3d 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/skills/semantic-core/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

semantic-core — measured demand core, then the run

You are the orchestrator for one core build: find what people actually search around a product, measure it through the platforms' own APIs, cluster it by intent, write the assistant-style questions each cluster justifies, commit the whole thing as a core.json + questions.csv, and hand that to an open-geo visibility run.

Two halves, deliberately separated:

  • Deterministic — the numbers. demand/ asks Wordstat / Google Ads / Bing / autocomplete and returns each figure with its scope (region, period, pull date). No browser, no logged-in session, no hand-typed volume. Contract: pipeline/INTERFACES.md §8, guide: demand/README.md.
  • Agentic — the judgement. Which angles the product has, how a person phrases the need to an assistant, which lines survive a skeptic. Authority: harvest/METHODOLOGY.md (§3 demand gate, §4 lens invariants, §5 segments).

Run Python from the open-geo runtime root with its venv (.venv/bin/python). Code and intermediate JSON are English; the summary you print follows --lang.


INVOCATION

/semantic-core <domain> --brand "<name>" [--market "<category>"] [--competitors "a, b"]
               [--geo ru|us|ww|<cc>[,<cc>]] [--query-lang ru|en|<code>[,<code>]]
               [--n 36] [--split 16/10/10] [--out core/<slug>/core.json]
               [--run <engine>] [--n-worker N] [--output data|dashboard|pdf|both]
               [--lang en|ru|zh|ar] [--no-run]
arg / flag required default meaning
<domain> yes The product's site. Also the target of the follow-on run.
--brand "<name>" yes Human brand name; enforces the lens/brand invariants at commit time.
--market no inferred Category in the user's words. Inferred from the homepage when absent — always echo the inference for confirmation.
--competitors no Seed list; workers extend it.
--geo no ru ISO-3166 alpha-2 lowercase, or ww for worldwide. Comma-separated for several markets — each is measured on its own ruler.
--query-lang no follows geo The language people search in — independent of --lang (the deliverable language). A distinct language is a distinct slice with its own CSV.
--n no 36 Target questions across all slices.
--split no derived general/branded/comparative, general-tilted (for 36: 16/10/10).
--out no core/<brand-slug>/core.json Where the core artifact lands. The CSV goes beside it as <brand-slug>_questions.csv.
--run <engine> no ask Engine for the follow-on open-geo run (google, chatgpt_search, yandex_neuro, …).
--n-worker no ask Capture concurrency for that run.
--no-run no off Build and commit the core, stop before the run.

Read the full file on GitHub · 180 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. 3d ago First seen · 180 lines · 91 tokens per session scan A aee8fac1e4f6

Subscribe to this mod's changes

semantic-core is a skill published in the GitHub repository Pupok462/open-geo (25 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 2,514 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 2026-09-05.

Related

Other skills, from other repositories

geo-audit

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.

techhorizonlabs/thl-open · 60 tokens

geo

GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GEO audits, citability scoring, AI crawler analysis, llms.txt generation, brand mention scanning, platform-specific…

techhorizonlabs/thl-open · 139 tokens

geo-brand-mentions

Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.

techhorizonlabs/thl-open · 49 tokens

geo-llmstxt

Analyzes and generates llms.txt files -- the emerging standard for helping AI systems understand website structure and content. Can validate existing llms.txt files or generate new ones from scratch by crawling the site.

techhorizonlabs/thl-open · 46 tokens

agent-readiness-scan

Use when a client audit, GEO/AI-visibility snapshot, or remediation re-scan needs the Cloudflare agent-readiness score from isitagentready.com — e.g. Theo client audits, "is the site agent-ready", markdown negotiation / MCP / llms.txt / Content-Signal checks, or tracking score deltas after Tier 0/1 fixes.

techhorizonlabs/thl-open · 79 tokens

found-by-ai

Measure whether AI engines actually recommend a business when buyers ask. Runs the free live scan at areyoufoundbyai.com (no auth, 60s), reads the verdict and the rivals AI names instead, hands back the fix plan, and wires monitored sites into a fix-and-re-measure loop over MCP.

techhorizonlabs/thl-open · 67 tokens