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 PascaleBeier/hitkeep --skill hitkeep-ecommerce-analystgit clone --depth 1 https://github.com/PascaleBeier/hitkeepWrote 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/pascalebeier/hitkeep/hitkeep-ecommerce-analyst)<a href="https://agentmods.dev/skills/pascalebeier/hitkeep/hitkeep-ecommerce-analyst"><img src="https://agentmods.dev/badge/skills/pascalebeier/hitkeep/hitkeep-ecommerce-analyst.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.00153 |
| Opus 5 | $0.00026 | $0.00077 |
| Sonnet 5 | $0.00011 | $0.00031 |
| Haiku 4.5 | $0.00005 | $0.00015 |
Grade A, and why
hitkeep-ecommerce-analyst 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 7d 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
HitKeep Ecommerce Analyst
Read procedure.md and follow it as the canonical conversion-analysis procedure.
Use production HitKeep MCP for scoped aggregate reports and official docs. Inspect live tool schemas rather than copying tool names, dimensions, or limits here. If MCP is unavailable, state which observations cannot be verified.
Keep the analysis aggregate-only. Route customer-level orders or raw-event needs to supported exports or takeout instead of expanding assistant access.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 13 lines · 53 tokens per session scan A c114457301cd
hitkeep-ecommerce-analyst is a skill published in the GitHub repository PascaleBeier/hitkeep (85 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 153 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ecommerce-geo-auditor
Diagnose an ecommerce page or listing for GEO, AI-search, AI-citation, and AI-shopping readiness using inspected page evidence, supplied content, or crawl data. Use when the user asks for a GEO audit, AI visibility readiness check, AI search audit, citation-readiness review, or why a product is hard for AI systems to…
ecommerce-seo-auditor
Audit ecommerce websites, product pages, collection pages, and marketplace listings for technical SEO, crawlability, indexability, on-page relevance, content, internal linking, product data, images, and Core Web Vitals. Use when the user asks for an ecommerce SEO audit, store SEO checkup, product-page review…
buyer-intent-writer
Write or rewrite ecommerce product descriptions, bullets, buying-guide sections, and landing-page copy around verified buyer needs, objections, comparisons, and purchase intent. Use when the user asks for buyer-intent copy, product copy, conversion copy, or a clearer product description. Do not use for technical…
competitor-seo-analyzer
Compare observable ecommerce competitor SEO, content, structured-data, trust, and buyer-intent signals. Use when the user asks for competitor SEO analysis, an SEO comparison, content gaps, or a comparison of supplied pages, listings, exports, or search evidence. Do not infer live rankings, traffic, backlinks, or AI…
ecommerce-geo-optimizer
Turn verified ecommerce GEO, AI-search, or AI-citation readiness gaps into a prioritized implementation plan covering content, product facts, technical access, structured data, trust, and measurement. Use when the user asks to improve GEO, optimize for AI search, fix a GEO audit, or create an AI visibility readiness…
faq-content-generator
Generate accurate ecommerce FAQs from verified product facts, buyer questions, reviews, policies, and support evidence. Use when the user asks to write product FAQs, store FAQs, buyer questions, support content, or optional matching FAQPage JSON-LD. Do not promise rich results or invent answers.