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 service-landing-copygit 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/service-landing-copy)<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/service-landing-copy"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/service-landing-copy/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/service-landing-copy"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/service-landing-copy.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 | $0.00166 | $0.02093 |
| Opus 5 | $0.00083 | $0.01046 |
| Sonnet 5 | $0.00033 | $0.00419 |
| Haiku 4.5 | $0.00017 | $0.00209 |
Grade A, and why
service-landing-copy 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 11d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Landing Copy — Copy for a Service Page
Goal: write publication-ready copy for a landing page dedicated to one service. Output format: structured copy blocks, each labeled with its section — they can be inserted into the hero, timeline, gallery, features, FAQ, and CTA components without modification.
Step 0 — Assess Whether a Dedicated Page Is Appropriate
Before writing the copy, assess whether this service warrants a dedicated landing page.
Criteria for "YES, a dedicated page is warranted"
| Criterion | Evidence |
|---|---|
| Demand volume | Target queries receive ≥100–300 impressions/month, or this is a high-ticket B2B niche with low-frequency queries |
| Specific intent | The user is looking for this exact service, not an aggregator |
| Distinct ICP | The audience and pain point differ from those of adjacent services |
| Dedicated conversion path | The service has a specific CTA or funnel |
| Differentiation | You can explain how this service differs from neighboring services in the catalog |
Criteria for "NO, a catalog card is sufficient"
- Demand is zero or extremely low, with no clear B2B context
- The service is a subset of another service that already has a parent page
- There is no unique angle: the copy would duplicate an adjacent page
- The engagement format has not yet been defined, so there is nothing concrete to promise
If the answer is "NO," state this explicitly and recommend strengthening the catalog card instead of creating a page.
Step 1 — Gather Service Data
Ask these questions, or extract the answers from the available context:
- Service name and URL
- ICP — who is the customer: B2B / e-commerce / startup / local business?
- Primary pain point — what is going wrong for the customer before they purchase the service?
- Outcome — what does the customer ultimately receive, and how is it measured?
- Engagement format — audit / project / ongoing support / one-off consultation?
- Key stages — what does the delivery process look like (3–6 steps)?
- Differentiation — how does the service differ from competitors' alternatives or adjacent services?
- Proof — are there case studies, metrics, or results?
- Objections — what prevents the customer from making a decision?
- CTA — what is the target action on the page?
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.
- 11d ago First seen · 259 lines · 166 tokens per session scan A 450524602f99
service-landing-copy is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 8d ago), licensed MIT. It adds 166 tokens to every session and 2,093 once invoked, about $0.0008 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
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.
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.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
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.