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 takechanman1228/claude-ecom --skill ecomgit clone --depth 1 https://github.com/takechanman1228/claude-ecomWrote 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/takechanman1228/claude-ecom/ecom)<a href="https://agentmods.dev/skills/takechanman1228/claude-ecom/ecom"><img src="https://agentmods.dev/badge/skills/takechanman1228/claude-ecom/ecom/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/takechanman1228/claude-ecom/ecom"><img src="https://agentmods.dev/badge/skills/takechanman1228/claude-ecom/ecom.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 | $0.00074 | $0.01920 |
| Opus 5 | $0.00037 | $0.00960 |
| Sonnet 5 | $0.00015 | $0.00384 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
ecom 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 9d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ecom — Ecommerce Business Review Toolkit
D2C ecommerce analytics. The bundled Python engine computes KPIs, runs health checks, and scores performance from order transaction data; you (Claude) interpret the numbers and write the human-readable report.
Key principle: Python computes the numbers. Claude interprets them. Never present raw numbers without business context.
Arguments: $ARGUMENTS (if empty, infer intent from the conversation)
Mode Selection
| Arguments / intent | Mode | Output |
|---|---|---|
empty or review |
Full Review (auto-selects periods from data) | REVIEW.md |
review 30d / 90d / 365d |
Full Review, single period | REVIEW_{PERIOD}.md |
| contains a natural-language question | Focused Query | Inline answer, no file |
Input
Order transaction CSV. Each row = one order or line item. Required columns: order ID, order date, customer ID (or email), revenue (after discounts, before tax/shipping). Optional: quantity, SKU/product, discount amount. Column names are fuzzy-matched by the loader.
If no CSV is specified, Glob for *.csv in the working directory and ask
the user if multiple plausible candidates exist.
Running the Engine
The ecom CLI is on PATH while this plugin is enabled:
ecom review orders.csv --output <output-dir>
ecom review orders.csv --period 90d --output <output-dir>
If ecom is not on PATH, use the bundled launcher with the same
arguments: "${CLAUDE_SKILL_DIR}/../../bin/ecom". The first run
bootstraps a private Python venv under ~/.local/share/claude-ecom/
and may take a minute; later runs are instant.
Output: review.json (or review_{period}.json for --period runs)
in the output directory (defaults to current directory).
Workflow
Phase 1: Compute (Python)
Run the engine (add --period per Mode Selection). It computes, per
available period: summary KPIs with prior-period comparison, a
new-vs-returning KPI tree, revenue driver decomposition (AOV / volume /
mix), and — for 365d — repeat purchase rate and a 12-month
monthly_trend. It also evaluates ~30 health checks across Revenue,
Customer, and Product; each returns pass / watch / fail and powers the
🟢/🟡/🔴 markers.
What ships with it
9 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.
- references/benchmarks.md 18 KB
- references/finding-clusters.md 9.4 KB
- references/focused-query.md 2.4 KB
- references/health-checks.md 11 KB
- references/impact-formulas.md 11 KB
- references/recommended-actions.md 16 KB
- references/report-format.md 5.7 KB
- references/review-narratives.md 13 KB
- references/review-schema.md 4.8 KB
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.
- 9d ago First seen · 186 lines · 74 tokens per session scan A 452de42a7124
ecom is a skill published in the GitHub repository takechanman1228/claude-ecom (49 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,920 once invoked, about $0.0004 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
persona
Build a persona panel, explore customer motivations through open-ended questions, and pressure-test product concepts before spending on fieldwork. Generates diverse AI persona panels, runs agent-separated interviews (qualitative ask or structured concept test), analyzes results with theme synthesis, cross-tabs, and…
paywalls
When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan…
seo-ecommerce
E-commerce SEO analysis: Google Shopping visibility, Amazon marketplace intelligence, product schema validation, competitor pricing analysis, and marketplace keyword gaps. Combines on-page product SEO with marketplace data from DataForSEO Merchant API. Use when user says "ecommerce SEO", "product SEO", "Google…
product-feed-optimizer
Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…
monetization-strategy
When the user wants to design or optimize their app's monetization — pricing, paywalls, subscriptions, or in-app purchases. Also use when the user mentions "pricing", "paywall", "subscription", "IAP", "how to monetize", "revenue optimization", "free trial", or "conversion to paid". For retention impact, see…
paywall-optimization
When the user wants to design, test, or optimize their app's paywall — layout, copy, pricing display, trial offers, plan structure, hard vs soft paywall, paywall placement, or paywall A/B tests. Use when the user mentions "paywall", "paywall design", "paywall conversion", "trial-to-paid", "soft paywall", "hard…