extract-amazon-order

extract-amazon-order is a skill for Claude Code, Codex from markmhendrickson/ateles. It costs 0 tokens per session (736 once invoked), scanned A, original, MIT.

An email workflow that finds Amazon order messages in Gmail, extracts purchase details, and stores them as purchase records. Neotoma is the connected system used to save these records.

In plain words
What is it for?
It helps capture Amazon purchases from Gmail, including order numbers, products, amounts, dates, delivery details, addresses, and links.
Why use it?
It removes the need to search order emails and copy details such as the item, price, date, and delivery information by hand. Keeping the purchase in a record makes it easier to use later.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/markmhendrickson/ateles/extract-amazon-order
Any agent
npx skills add markmhendrickson/ateles --skill extract-amazon-order
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for extract-amazon-order

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/extract-amazon-order.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/extract-amazon-order)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/extract-amazon-order"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/extract-amazon-order.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 736 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00736
Opus 5 $0.00000 $0.00368
Sonnet 5 $0.00000 $0.00147
Haiku 4.5 $0.00000 $0.00074

Measured 4d ago against content hash 3f28d4923130, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

extract-amazon-order 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 4d 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.

.claude/skills/extract-amazon-order/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract Amazon Order

Search Gmail for Amazon order emails, extract order details, and store as a purchase in Neotoma first (then Parquet if purchases still use Parquet). Create a snapshot before any Parquet write.

When to Use

Use this skill when:

  • User says "extract Amazon order", "get order from email", "record Amazon purchase from Gmail"
  • User wants to capture an Amazon order from email (standalone or during email triage)

Required Documents (load first)

  1. Amazon order extraction: docs/workflow_specifics_rules.mdc (Amazon Order Extraction)
  2. Storage and snapshot: docs/neotoma_parquet_migration_rules.mdc (Neotoma first; snapshot before Parquet modification when required)
  3. Purchases schema: $DATA_DIR/schemas/ for purchases if needed (item_name, status, vendor, etc.)

Workflow

  1. Search Gmail: Use Gmail MCP search (e.g. search_emails) with query such as from:[email protected] OR from:[email protected] subject:"pedido", or by order number/product name as appropriate.
  2. Read message: Use Gmail MCP read (e.g. read_email) with message ID. Extract: order number, product, amount, order date, delivery date, address, URL.
  3. Store in Neotoma first: Use Neotoma MCP to store purchase entity (entity_type appropriate to schema). Include all extracted fields.
  4. If purchases still in Parquet: Use mcp_parquet_add_record(data_type="purchases", record={...}). Map to schema: item_name, status ("completed"/"in_progress"), location, vendor ("Amazon.es"/"Amazon.com"), actual_cost_usd, currency, category, created_date, completed_date, notes (order number, status), import_date, import_source_file ("gmail_email_parsing").
  5. Snapshot before Parquet write: Create timestamped snapshot $DATA_DIR/snapshots/purchases-YYYY-MM-DD-HHMMSS.parquet before modifying purchases parquet if the workflow requires it per repo rules.

Constraints

  • Store in Neotoma first; do not write only to Parquet for user/agent-captured data.
  • Create snapshot before modifying purchases parquet when Parquet is used.
  • No Amazon consumer API; use email parsing only. Multiple emails per order (confirmation, shipping, delivery) are possible.

Read the full file on GitHub · 48 lines

Changes

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.

  1. 4d ago First seen · 48 lines · 0 tokens per session scan A 3f28d4923130

Subscribe to this mod's changes

extract-amazon-order is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 736 tokens. 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.