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 PavloSEO/seohead-seotools --skill article-writergit clone --depth 1 https://github.com/PavloSEO/seohead-seotoolsWrote 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/pavloseo/seohead-seotools/article-writer)<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/article-writer"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/article-writer/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/pavloseo/seohead-seotools/article-writer"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/article-writer.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 | $0.00149 | $0.02431 |
| Opus 5 | $0.00075 | $0.01215 |
| Sonnet 5 | $0.00030 | $0.00486 |
| Haiku 4.5 | $0.00015 | $0.00243 |
Grade A, and why
article-writer 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 9d 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.
"code": "// app.ts\nconst result = await fetch(url);\nconsole.log(result);" How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Writer — Expert Bilingual Articles
Workflow: Research → Plan (optional) → Write RU+EN → JSON output
Step 0 — Gather Context
If the request lacks essential information, ask one clarifying question before starting, and no more than one:
| Information needed | How to obtain it |
|---|---|
| Article topic | Extract it from the request or ask |
| Author | Use author details supplied by the user or project; otherwise keep the neutral configurable author placeholders |
| Starting format | Ask: "Would you like to review the outline first, or should I start writing immediately?" |
| Tag/category | Infer it from the topic or ask |
| relatedSlugs | Suggest relevant entries and let the user revise them |
Step 1 — Research (Required)
Always conduct research before writing. Use every available source of evidence:
1A — Web Search
- Find 3–5 authoritative sources on the topic, such as official documentation, MDN, Google, W3C, research papers, or industry reports
- Find current statistics with dates and sources
- Verify that technical details are current, including APIs, versions, and changes
- Find real case studies and examples
1B — Model Knowledge
- Apply relevant subject-matter knowledge
- Apply best practices and established patterns
- Account for technical details and nuances
1C — Operator/Author Knowledge
- Use all context provided about the author's experience, case studies, and opinions
- Highlight the author's position when one is available
Research Output (Internal; Do Not Show the User)
- Topic: [topic]
- Key sources: [list with URLs]
- Key facts: [3–7 verifiable claims with sources]
- Statistics: [specific figures + year + source]
- Examples: [real case studies]
- SEO angle: [keyword and intent]
Step 2 — Outline (If the User Selected It)
If the user wants to review an outline first, show it and wait for confirmation before writing.
Outline format:
## [Article title]
**Tag:** [tag] **readTime:** ~N min **Keyword:** [keyword]
### Structure:
1. Intro — [what it resolves]
2. H2: [section] — [what it contains and which blocks it uses]
3. H2: [section] — ...
...
N. Outro + CTA
### Sources to include:
- [URL 1] — for section N
- [URL 2] — for section M
Proceed with writing? (yes / revisions: ...)
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.
- 9d ago First seen · 300 lines · 149 tokens per session scan A a6d915bbaa99
article-writer is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 5d ago), licensed MIT. It adds 149 tokens to every session and 2,431 once invoked, about $0.0007 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
fire-your-seo-agency
A procedure for improving how a website appears in search engines and how AI answer systems find and cite it. It covers search, answer-engine, generative-AI, and Naver visibility.
geo-loop
Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
content-scoring
Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.
validation-doctor
Check Brave Search and Chrome DevTools MCP availability and provide exact setup snippets. Use when validation dependencies are missing or uncertain.
geo-content-research
Researches what prompts people ask AI engines (ChatGPT, Gemini, Perplexity, Claude) about a product category and produces a prompts.csv artifact — a prioritized, strictly-schema'd list of the queries where the brand should be cited. Feeds the monitor workflow.