OpenSEO is an open-source SEO platform for keyword research, rank tracking, competitor analysis, backlink analysis, site audits, and AI visibility work. It connects SEO data to AI agents through an MCP server and reusable agent skills, while allowing users to supply their own DataForSEO API key and self-host the tool. Catalogue add-ons guide agents through OpenSEO's SEO workflows.
Borrowing it
Nothing to install: this file belongs to every-app/open-seo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/every-app/open-seo/main/.agents/skills/openseo-review-web-content/SKILL.mdgit clone --depth 1 https://github.com/every-app/open-seoWrote 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/every-app/open-seo/openseo-review-web-content)<a href="https://agentmods.dev/skills/every-app/open-seo/openseo-review-web-content"><img src="https://agentmods.dev/badge/skills/every-app/open-seo/openseo-review-web-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.
<a href="https://agentmods.dev/skills/every-app/open-seo/openseo-review-web-content"><img src="https://agentmods.dev/badge/skills/every-app/open-seo/openseo-review-web-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00446 |
| Opus 5.5 | $0.00023 | $0.00178 |
| Sonnet 5.5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
openseo-review-web-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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- upgradeseo-review-web-content — 97% identical, 44 lines differ
What it actually says
OpenSEO Web Content
Every page is for a specific reader. A blog post should leave them better at SEO. A product page should help them decide whether OpenSEO solves their problem. Judge every edit by one question: is this better for that reader? We are not writing to pass a review.
Write for the reader
- Say up front what the reader will get, in their terms.
- Organize around their job, not the source material. Interviews become a plan, not a roundup of quotes.
- Carry one real example through, with real numbers.
- Use lists instead of dense paragraphs: bullet points for things the reader needs to do or check, and numbered lists for steps in order.
- Give practical advice, even when it's messier than the official rules.
- Answer straight. "No" and "it costs money" are complete answers.
Cut what isn't for them
- Notes for whoever checks the draft: method footers, "verbatim" assurances, tool or API names, "re-checked on" dates.
- Hedges that protect the writer, and links or asides that interrupt.
- Anything that reads like an ad. A company used as an example is there to teach.
Don't make things up
That's the whole accuracy bar. Product capabilities, prices, quotes, and data must be real, so check product claims against the code. Framing, figures of speech, and opinions are the writer's call. Don't ask for disclosures or a source for every number. Never call OpenSEO simply "free."
Voice
Use the deslop skill for AI tells. When editing someone else's post, keep their voice and examples. In the playbook library, an approach is a "strategy," never a "play."
Run prettier on the files you touch.
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.
- 13d ago Changed · +58 tokens per session 64af84b49ee6
- 21d ago Changed · -2 lines · -58 tokens per session bbd69189011f
- 1mo ago First seen · 38 lines · 58 tokens per session scan A 52dc4858851d
openseo-review-web-content is a skill published in the GitHub repository every-app/open-seo (25,345 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 446 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
altorank
Run AltoRank through its hosted MCP server: readiness audits, Search Console, keyword research, and SEO drafts into a review queue.
setup-svelte-vitals
Set up svelte-vitals in a SvelteKit project: inspect what the project already uses, derive a svelte-vitals.config from its markuplint / eslint-plugin-check-file config and its actual directory conventions, measure each candidate rule before adopting it, and hand the remaining targets to svelte-vitals install. Use when…
wordstat-collector
A tool that collects search statistics from Yandex Wordstat, the Yandex service for researching what people search for. It returns search phrases and their frequencies for Russian-language market research.
improve-svelte
Survey a whole SvelteKit codebase as a senior Svelte/SvelteKit engineer, using svelte-vitals' scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when…
seo-pipeline-llm
4-stage SEO content pipeline: keyword research → competitor scraping → SEO analysis → content creation. Outputs local files, no CMS integration.
seo-pipeline-bash
One-shot SEO content pipeline: scrape keywords from SERP and produce article markdown files via Browser Use SDK or DuckDuckGo fallback.