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 ZensInk/zens-ink-seo-package --skill search-intentgit clone --depth 1 https://github.com/ZensInk/zens-ink-seo-packageWrote 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/zensink/zens-ink-seo-package/search-intent)<a href="https://agentmods.dev/skills/zensink/zens-ink-seo-package/search-intent"><img src="https://agentmods.dev/badge/skills/zensink/zens-ink-seo-package/search-intent/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/zensink/zens-ink-seo-package/search-intent"><img src="https://agentmods.dev/badge/skills/zensink/zens-ink-seo-package/search-intent.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 | $0.00099 | $0.00649 |
| Opus 5.5 | $0.00040 | $0.00260 |
| Sonnet 5.5 | $0.00020 | $0.00130 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
search-intent 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 2d 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.
What it actually says
Search intent, cross-validated
Two layers: what the words say (keyword-based) and what Google rewards (SERP-based). When they disagree, believe the SERP.
When to use
- Before writing a page for a target keyword — decides page TYPE.
- "Is 'seo audit tool' informational or transactional?"
- Batch-classifying a keyword list for a content plan.
When NOT to use
- Pure navigational brand queries ("gmail login") — classification is trivial and useless for planning.
Setup
pip install zens-ink
Keyword layer needs no keys. SERP layer needs SERPER_API_KEY
(free tier at serper.dev).
Commands
# Keyword-based, batch, no key needed
python3 -m zens_ink.search_intent "buy running shoes" "how to tie shoes" --json
python3 -m zens_ink.search_intent --file keywords.txt
# SERP-based verification (what ranks?)
python3 -m zens_ink.serp_intent "seo audit tool"
python3 -m zens_ink.serp_intent "seo 审计工具" --zh
python3 -m zens_ink.serp_intent "best crm" --cross # cross-check keyword verdict
How to read the results
- informational → guide/post format, long-form, capture with newsletter.
- commercial → comparison/best-of format, affiliate or demo CTA.
- transactional → product/landing page, pricing visible, minimal prose.
- navigational → usually not targetable; only worth it for brand terms.
When keyword verdict and SERP verdict disagree: the SERP is ground truth — Google already ran the experiment with real searchers.
Page-type mismatch is the #1 reason good content never ranks. A landing page cannot win a SERP that rewards 2,000-word guides, and vice versa.
Next steps
- Intent confirmed →
keyword-difficultyfor the go/no-go. - Building the page →
site-auditskill catches technical issues before ship.
Going deeper
ZensInk Pro adds a semantic arbitration layer (typed AI judgments with confidence scores) that resolves keyword-vs-SERP conflicts automatically: https://zens.ink/pricing/
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.
- 2d ago First seen · 79 lines · 99 tokens per session scan A d2632a1ec6e5
search-intent is a skill published in the GitHub repository ZensInk/zens-ink-seo-package (53 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 649 once invoked, about $0.0004 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 2026-10-15.
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.
content-creator
Self-configuring content creation pipeline with geo-lint validation. On first use, scans your project to learn its framework, content schema, categories, and authors, then creates SEO & GEO-optimized content matched to your brand voice. Validates every piece with geo-lint's 92 rules until zero violations. Triggers on…
geo-lint
SEO & GEO content linter — validates Markdown/MDX files for AI search visibility using 92 deterministic rules (35 GEO, 32 SEO, 14 content quality, 8 technical, 3 i18n). Runs an autonomous lint-fix loop: scan content, read structured violations, fix them, re-lint until clean. Use when optimizing content for AI…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
vs-search-tuning-specify-policy-direction
Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and…
vs-search-tuning-partial-case
Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay…