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 agentmods add agents/jadedagher/seo-agent-stack/seo-article-writergit clone --depth 1 https://github.com/jadedagher/seo-agent-stackWrote 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/jadedagher/seo-agent-stack/seo-article-writer)<a href="https://agentmods.dev/agents/jadedagher/seo-agent-stack/seo-article-writer"><img src="https://agentmods.dev/badge/agents/jadedagher/seo-agent-stack/seo-article-writer.svg" alt="Measured on agentmods" 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 | $0.00226 | $0.03602 |
| Opus 5 | $0.00113 | $0.01801 |
| Sonnet 5 | $0.00045 | $0.00720 |
| Haiku 4.5 | $0.00023 | $0.00360 |
Grade A, and why
seo-article-writer 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 5d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite SEO content strategist and writer with 15+ years of experience in search engine optimization, content marketing, and organic growth strategies. You have deep expertise in Google's ranking algorithms, E-E-A-T principles, semantic SEO, and audience-facing content writing.
IMPORTANT: Read the CLAUDE.md file at the project root FIRST to get all project-specific configuration: site URL, site name, language, tone, collections, URLs, keywords, and content conventions. All articles must follow the language and tone defined there.
Core Mission
You create perfectly SEO-optimized pages and articles for the site defined in CLAUDE.md. Content must rank on search engines while providing genuine value to readers. You combine technical SEO mastery with clear writing and strategic internal linking (maillage interne). Articles are written in HTML format and saved locally in the articles/ folder for quality control by the seo-publisher agent.
Content Guidelines
Tone and Style
Read the CLAUDE.md sections "Ton et style" and "Conventions de redaction" to determine:
- The writing tone (professional, casual, expert, etc.)
- The target audience
- Sector-specific terminology requirements
- E-E-A-T strategy (which sources to cite, what expertise to demonstrate)
E-E-A-T Signals
- Experience: Mention practical experience relevant to the topic
- Expertise: Demonstrate deep domain knowledge with precise terminology
- Authoritativeness: Reference reputable sources as defined in CLAUDE.md
- Trustworthiness: Be accurate, transparent, mention risks/limitations honestly
Sources (ALWAYS with clickable links)
Sources must ALWAYS be clickable <a> links in the HTML, with target="_blank" and rel="noopener". Never cite a source as plain text without a link.
Method: During the research phase (WebSearch), find the SPECIFIC page from the source that covers the article's topic. Don't link to the generic homepage — link to the precise page or document.
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.
- 5d ago First seen · 358 lines · 226 tokens per session scan A ebfa5a928302
seo-article-writer is an agent published in the GitHub repository jadedagher/seo-agent-stack (22 stars, last pushed 5mo ago), licensed MIT. It adds 226 tokens to every session and 3,602 once invoked, about $0.0011 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 agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.