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.
npx skills add oyusypenko/creo --skill creo-seogit clone --depth 1 https://github.com/oyusypenko/creoWrote 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/oyusypenko/creo/creo-seo)<a href="https://agentmods.dev/skills/oyusypenko/creo/creo-seo"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-seo/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/oyusypenko/creo/creo-seo"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-seo.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 | $0.00185 | $0.02911 |
| Opus 5 | $0.00093 | $0.01456 |
| Sonnet 5 | $0.00037 | $0.00582 |
| Haiku 4.5 | $0.00018 | $0.00291 |
Grade A, and why
creo-seo scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the skill reads exported CSVs, runs curl-based verification, and produces the How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
creo-seo — Next.js SEO + GEO specialist
Elite SEO specialist for Next.js applications. Covers technical SEO auditing, AI search optimization (LLMO/GEO), content E-E-A-T compliance, Core Web Vitals, schema deprecation awareness, citability scoring, and llms.txt generation.
Commands
| Command | What it does |
|---|---|
/creo seo onboard <url> |
Main lifecycle command — audit, implementation plan, guided GSC/Bing configuration, monitoring + autofix scaffold, standing cadence. See references/seo-onboarding.md. |
/creo seo plan <url> |
Analyze + produce a prioritized implementation plan (Problem/Fix/Verify, DEV/YOU tags, phased forecast) without the setup stages |
/creo seo init |
Scan codebase and write cached project profile to .claude/skills/creo-seo/creo-seo-{project_id}.md. Run this first. |
/creo seo audit <url> |
Main full-site audit — runs all 7 phases, produces markdown + JSON report |
/creo seo audit --brief <url> |
Fast audit: Technical + Build + Live + Scoring only |
/creo seo technical <url> |
Phase 1 + 3 + 4 — codebase/build/live tech checks |
/creo seo content <url> |
Phase 2 — content quality, E-E-A-T, AI-pattern detection |
/creo seo schema [<url>] |
Schema audit: generation, deprecation, validation |
/creo seo sitemap |
Sitemap audit + generation recommendations |
/creo seo citability <url> |
Passage-level AI citability score + rewrite priorities |
/creo seo llms-txt [--generate] |
Validate existing /llms.txt or generate new one |
/creo seo crawlers [--fix] |
Audit robots.txt for 14 AI crawlers; optionally rewrite |
/creo seo compare <old.md> <new.md> |
Delta between two prior audits |
/creo seo autofix [--dry-run] |
Closed-loop GSC remediation: detect, allowlisted fix, verify, notify, ledger (needs gsc-analyzer extension) |
/creo seo triage <bucket> |
Triage a GSC coverage bucket: expected vs concern, direction over level |
/creo seo semantic-core |
Build/refresh the focused query core with noise filtering and P0-P3 priorities |
/creo seo freshness |
Audit freshness signals: lastmod/dateModified divergence, year-staleness |
/creo seo offpage |
Off-page authority plan: directories, LLM citation slots, trust-killer sweep |
/creo seo weekly [--setup] |
Read the latest weekly snapshot, or scaffold the weekly monitoring workflow |
/creo seo page-rules |
Generate a project-scoped .claude/rules/seo-page-rule.md for page-creation-time enforcement |
What ships with it
22 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.
- references/ai-crawlers.md 6.0 KB
- references/ai-pattern-detection.md 6.3 KB
- references/audit-report-template.md 7.0 KB
- references/content-quality-rubric.md 5.0 KB
- references/coverage-triage.md 5.2 KB
- references/deploy-verification.md 4.4 KB
- references/freshness-signals.md 4.4 KB
- references/geo-citability.md 7.0 KB
- references/gsc-autofix-loop.md 5.7 KB
- references/indexation-runbook.md 4.4 KB
- references/internal-linking-recipe.md 7.4 KB
- references/llms-txt-generator.md 7.0 KB
- references/offpage-authority.md 5.5 KB
- references/page-seo-rules.md 5.8 KB
- references/project-profile-template.md 6.6 KB
- references/schema-templates.md 15 KB
- references/schema-validation-checklist.md 6.4 KB
- references/scoring-rubric.md 6.9 KB
- references/semantic-core.md 5.0 KB
- references/seo-onboarding.md 5.3 KB
- references/seo-program-conventions.md 5.4 KB
- references/sitemap-patterns.md 8.8 KB
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 · 209 lines · 185 tokens per session scan A c8602963f62e
creo-seo is a skill published in the GitHub repository oyusypenko/creo (4 stars, last pushed 3d ago), licensed MIT. It adds 185 tokens to every session and 2,911 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. Use when building or reviewing React or Next.js components, state, or render performance.
react-testing
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
design-sync
Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says "sync my design system to Claude Design".