creo-seo-content

creo-seo-content is an agent for Claude Code from oyusypenko/creo. It costs 80 tokens per session (1,389 once invoked), scanned A, original, MIT.

A content-quality specialist for Next.js websites that reviews how clear, specific, credible, and useful each page is. It also examines search intent, which means the information a person is trying to find when they search.

In plain words
What is it for?
Auditing page content, classifying search intent, assessing credibility and citability, finding internal-linking opportunities, and prioritizing rewrites.
Why use it?
It turns broad content problems into rewrite priorities and examples, while checking whether pages answer the questions people are likely asking. It can also identify wording patterns that may make text seem machine-written.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the creo plugin — 19 skills, 17 agents shipped together

Good fit Auditing page content, classifying search intent, assessing credibility and citability, finding internal-linking opportunities, and prioritizing rewrites.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oyusypenko/creo/creo-seo-content
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/oyusypenko/creo

Made for: Claude Code.

Or install creo, the plugin that ships this one along with the rest of its 19 skills, 17 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 creo-seo-content

README.md
[![agentmods](https://agentmods.dev/badge/agents/oyusypenko/creo/creo-seo-content/github.svg)](https://agentmods.dev/agents/oyusypenko/creo/creo-seo-content)
Your own site
<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-seo-content"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-seo-content/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 creo-seo-content

Your own site · 80×15
<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-seo-content"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-seo-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,389 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 $0.00080 $0.01389
Opus 5 $0.00040 $0.00694
Sonnet 5 $0.00016 $0.00278
Haiku 4.5 $0.00008 $0.00139

Measured 12d ago against content hash 4b68fe965978, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

creo-seo-content 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 12d 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/creo-seo-content.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

creo-seo-content — Content Quality Specialist

Deep content auditor for Next.js apps. Scores each page across 5 content dimensions, detects AI-generated patterns, maps search intent, scores opportunity, and outputs actionable rewrites with before/after examples.

Configuration load

  1. Read .claude/project-config.md for project_id, reports_path, keyword strategy
  2. Load project profile: .claude/skills/creo-seo/creo-seo-{project_id}.md (shared with creo-seo skill)
  3. If called by creo-seo as Phase 2 delegate, accept inherited context (URL list, business type, project config)

Reference library

File Purpose
skills/creo-seo-content/references/search-intent.md 4-class intent system
skills/creo-seo-content/references/opportunity-scoring.md 8-factor weighted scoring
skills/creo-seo-content/references/content-playbook.md 15 writing patterns
skills/creo-seo-content/references/rewrite-templates.md Before/after examples
skills/creo-seo/references/content-quality-rubric.md 5-dim content score
skills/creo-seo/references/ai-pattern-detection.md 26 AI phrases + 24 vague words
skills/creo-seo/references/geo-citability.md 5-dim citability + 134-167w window
skills/creo-seo/references/internal-linking-recipe.md Linking rules

Audit flow per page

1. Fetch content

  • Local MDX/TSX: Read file
  • Live URL: WebFetch and extract main content (skip nav/footer/sidebar)
  • Normalize to plain text + structure map (headings, paragraphs, lists, tables)

2. Score 5 dimensions

Apply content-quality-rubric.md:

Content_Quality =
  (Humanity        × 0.30) +
  (Specificity     × 0.25) +
  (Structure       × 0.20) +
  (SEO_Compliance  × 0.15) +
  (Readability     × 0.10)

3. AI-pattern sweep

Apply ai-pattern-detection.md:

  • Count every AI phrase occurrence (line-numbered)
  • Count every vague quantifier
  • Count specificity boosters (%, $, years, citations)
  • Count conversational boosters (contractions, questions, asides)
  • Compute per-500-word densities
  • Compute humanity score

Read the full file on GitHub · 157 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. 12d ago First seen · 157 lines · 80 tokens per session scan A 4b68fe965978

Subscribe to this mod's changes

creo-seo-content is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 1,389 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

devops-architect

DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…

closedloop-ai/claude-plugins · 95 tokens

whitepaper-coherence

Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 39 tokens

hydra-runner

🟢 Hydra's execution head — fast test runner, build executor, and validation agent. Use proactively whenever Claude needs to run tests, execute builds, check linting, verify formatting, run type checks, check git status, execute simple scripts, or validate that changes work. Runs on the cheap tier for speed — ideal…

AR6420/Hail_Hydra · 105 tokens

code-reviewer

An AI code-review assistant that checks changed code for architecture, quality, type safety, error handling, security, and project-rule compliance. Its instructions and output format are written in Chinese.

xiaobei930/cc-best · 74 tokens

security-auditor

Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…

HermeticOrmus/LibreUIUX-Claude-Code · 85 tokens

devops-engineer

CI/CD, deployment, infrastructure specialist. Invoked by /setup-repo and infra tasks.

firatcand/forge · 24 tokens