Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sergekostenchuk/seo-llm-skill-clusternpx agentmods add skills/sergekostenchuk/seo-llm-skill-cluster/semantic-core-architectWrote 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/skills/sergekostenchuk/seo-llm-skill-cluster/semantic-core-architect)<a href="https://agentmods.dev/skills/sergekostenchuk/seo-llm-skill-cluster/semantic-core-architect"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/seo-llm-skill-cluster/semantic-core-architect/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/skills/sergekostenchuk/seo-llm-skill-cluster/semantic-core-architect"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/seo-llm-skill-cluster/semantic-core-architect.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 | $0.00093 | $0.00839 |
| Opus 5 | $0.00046 | $0.00419 |
| Sonnet 5 | $0.00019 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
semantic-core-architect 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- semantic-core-architect — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Core Architect
Use this skill before URL architecture, internal linking, schema, content planning, or LLM-friendly page design. It turns a site goal into reusable semantic artifacts.
Read references/semantic-core-rubric.md before producing a full semantic core.
Owns
- query clusters;
- user/search intents;
- audience and job-to-be-done mapping;
- entity and topic mapping;
- language and locale priority;
- evidence labels and data gaps;
- handoff to information architecture.
Does Not Own
- final URL/canonical policy;
- internal link graph;
- schema implementation;
- page copywriting;
- rank guarantees;
- external link placement.
Workflow
- Capture the goal, audience, markets, languages, content model, constraints, and forbidden areas.
- Separate observed facts, user-provided facts, inferred assumptions, and unknowns.
- Build query clusters by intent, not by keyword volume alone.
- Map entities and topics to likely canonical page candidates without deciding final URLs.
- Assign priority from strategic value, page feasibility, audience fit, and evidence strength.
- Mark volume, difficulty, competitive strength, and rank opportunity as
unknownunless verified from an approved source. - Produce
semantic-core.yamlandentity-topic-map.yamlusing the templates in assets/. - Hand off to
information-architecture-seowith gaps and assumptions explicit.
Evidence Rules
- Search volume, difficulty, traffic, ranking, and assistant citation claims require current evidence.
- If keyword tools, Search Console, rank trackers, logs, or assistant-monitoring data are unavailable, use
unknown. - Current facts about search engines, AI crawlers, rich results, or platforms must follow the cluster freshness policy.
- Do not use competitor pages as proof of volume unless they come with a measured source.
Priority Model
Use P0 only when a cluster is both central to the site's identity and needed by downstream architecture. Use P1 for important supporting clusters. Use P2 for useful expansion. Use P3 for backlog or speculative ideas.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 93 lines · 93 tokens per session scan A 75fd96e945ce
semantic-core-architect is a skill published in the GitHub repository sergekostenchuk/seo-llm-skill-cluster (39 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 839 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 2026-08-30.
Other skills, from other repositories
technocore-chat
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
dialectical-paper-writing
Analyze, design, write, revise, translate, and review empirical or technical research papers through an evidence-bounded dialectical workflow. Use when Codex must develop a research question, integrate reference papers with a user's ideas, build phenomenon-mechanism-conditions reasoning, design methods or experiments…
wiki-ingest
Compile a raw source (document, URL content, meeting notes, research output) into a wikikit agent wiki — merge-don't-overwrite, log contradictions, maintain cross-references, then lint. Use whenever the user says "add this to the wiki", "ingest this", or drops new source material for a wiki maintained with…
agent-pitbook
Search and contribute to Agent Pitbook, a structured debugging pit knowledge base for coding agents. Use when Codex is diagnosing recurring local-development failures, sandbox issues, dependency installation errors, Docker or port problems, MCP/tool quirks, browser automation failures, or when a verified debugging…
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.