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 attaxr/attaxr-seo-pipeline --skill seo-pipeline-llmgit clone --depth 1 https://github.com/attaxr/attaxr-seo-pipelineWrote 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/attaxr/attaxr-seo-pipeline/seo-pipeline-llm)<a href="https://agentmods.dev/skills/attaxr/attaxr-seo-pipeline/seo-pipeline-llm"><img src="https://agentmods.dev/badge/skills/attaxr/attaxr-seo-pipeline/seo-pipeline-llm/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/attaxr/attaxr-seo-pipeline/seo-pipeline-llm"><img src="https://agentmods.dev/badge/skills/attaxr/attaxr-seo-pipeline/seo-pipeline-llm.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 | $0.00033 | $0.00633 |
| Opus 5 | $0.00016 | $0.00316 |
| Sonnet 5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
seo-pipeline-llm 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Content Pipeline (LLM)
How to Run
- Say it — "run the SEO pipeline for [keyword]"
- Schedule it — as a recurring cron job
- Script it —
python -m seo_pipelinefor the scraping portion
Skills to Load
browser-use— for web research and article scraping- Research priority: browser-use MCP → browser-use CLI → web_search API
Configuration
export SEO_PIPELINE_DIR=./pipeline_data
Stage 1 — Keyword Research
Search for domain-relevant keywords. Capture phrase, volume, relevance, intent, cluster. Save to keywords.json.
Stage 2 — Content Collection
For each keyword: search SERP, extract competitor articles. Save to articles/.
Fallback
If browser tools unavailable: python -m seo_pipeline --from-json keywords.json
DuckDuckGo search is used for URL discovery only — set BROWSER_USE_API_KEY for full article extraction.
If zero articles extracted
Stop. Do not proceed.
Stage 3 — SEO Analysis
Analyze each article for keyword usage, gaps, depth, readability, structure, improvements.
Critical: Identify the unique angle none of the competitors cover.
Stage 4 — Content Creation
Per cluster: 1,500+ words, unique angle, H2/H3 hierarchy, lists, case studies, CTA, image suggestions, humanization pass. Save to drafts/.
Post-Creation — Humanization
Read the draft, strip AI-isms, adjust tone, vary rhythm. Sound like an expert explaining to a colleague.
Output
pipeline_data/
├── articles/ # Scraped competitor content
├── analysis/ # SEO metadata
└── drafts/ # Generated articles
Quality Checklist
- All 4 stages completed
- Each article ≥ 1,500 words
- Unique angle vs top 3 competitors
- SEO metadata complete
- ≥ 2 image suggestions per article
- Humanization pass applied
- Run report written
Error Handling
- Fail-stop pipeline:
set -euo pipefailin shell scripts - Empty keywords: broaden search, try once, then report
- All scrapers fail: Stop
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.
- 12d ago First seen · 91 lines · 33 tokens per session scan A f6b648817ecb
seo-pipeline-llm is a skill published in the GitHub repository attaxr/attaxr-seo-pipeline (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 633 once invoked, about $0.0002 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.
Other skills, from other repositories
marketing-seo
SEO keyword research, content planning, and competitor analysis with anti-hallucination gates.
blog
Full-lifecycle blog engine with 31 sub-skills, 12 content templates, 5-category 100-point scoring, and 5 specialized agents. Routes user requests to the right sub-skill: writing, rewriting, analysis, outlines, audits, schema, charts, images, repurposing, AI citation SEO, FLOW framework prompts, topic-cluster…
blog-cluster
Semantic topic cluster planning and automated execution engine for claude-blog. Performs SERP-based keyword research, groups keywords by search intent and SERP overlap, builds a hub-and-spoke cluster architecture, generates an interactive SVG cluster map, and executes the full cluster by orchestrating blog-write calls…
blog-rewrite
Rewrite and optimize existing blog posts for Google SEO (May 2026 Core Update, March 2026 core/spam context, June 2026 spam context, E-E-A-T) and AI citation visibility as one SEO discipline. Full rewrite for both Google rankings AND AI citations. For AI-citation-only audit (no Google work), use blog-geo instead.…
blog-write
Write new blog articles from scratch optimized for Google rankings and AI citations. Generates full articles with template selection, answer-first formatting, Key Takeaways summary box, information gain markers, citation capsules, sourced statistics, Pixabay/Unsplash images, built-in SVG chart generation, optional FAQ…
blog-analyze
Audit and score blog posts on a 5-category 100-point scoring system covering content quality, SEO optimization, E-E-A-T signals, technical elements, and AI citation readiness. Includes AI content detection (burstiness, phrase flagging, vocabulary diversity). Supports export formats (markdown, JSON, table) and batch…