amazon-returns-recovery

amazon-returns-recovery is a skill for Claude Code, Codex from JasonColapietro/suede-creator-skills. It costs 138 tokens per session (2,463 once invoked), scanned A, original, MIT.

An audit workflow for finding possible money owed by Amazon after restocking fees, incomplete or denied refunds, or forgotten paid subscriptions.

In plain words
What is it for?
Use it to investigate eligible orders and subscriptions and prepare a refund dispute, with the account owner's confirmation required before any action.
Why use it?
These charges and refund errors can remain hidden in an Amazon account unless someone checks the order and subscription history.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: positional $N argument.

Part of the suede-skills plugin — 78 skills, 6 agents, 3 MCP servers shipped together

Good fit Use it to investigate eligible orders and subscriptions and prepare a refund dispute, with the account owner's confirmation required before any action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jasoncolapietro/suede-creator-skills/amazon-returns-recovery
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.

Any agent
npx skills add JasonColapietro/suede-creator-skills --skill amazon-returns-recovery
Clone the repo
git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills

Made for: Claude Code, Codex.

Or install suede-skills, the plugin that ships this one along with the rest of its 78 skills, 6 agents, 3 MCP servers.

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 amazon-returns-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/amazon-returns-recovery/github.svg)](https://agentmods.dev/skills/jasoncolapietro/suede-creator-skills/amazon-returns-recovery)
Your own site
<a href="https://agentmods.dev/skills/jasoncolapietro/suede-creator-skills/amazon-returns-recovery"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/amazon-returns-recovery/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.

agentmods 80×15 button for amazon-returns-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/jasoncolapietro/suede-creator-skills/amazon-returns-recovery"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/amazon-returns-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,463 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 32
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00138 $0.02463
Opus 5 $0.00069 $0.01231
Sonnet 5 $0.00028 $0.00493
Haiku 4.5 $0.00014 $0.00246

Measured 12d ago against content hash 45ee4f29a33c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

amazon-returns-recovery 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 12d 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.

skills/amazon-returns-recovery/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amazon Returns Recovery

Iron Law:

Nothing is disputed, canceled, or sent without the account owner's per-item
confirmation. Discovery is read-only; every action phase is gated.

Why this exists

  1. Money like this doesn't announce itself. Restocking fees, short refunds, and forgotten subscription charges sit unannounced in order history unless something checks.
  2. Overturning an already-denied refund after the return window closed is the realistic ceiling of a well-reasoned exception ask — so ask for more than a waiver when the facts support it.

Read references/example-cases.md before drafting a dispute: three real resolved cases with the exact wording that worked.

Prerequisites

  • Claude in Chrome browser extension connected to the browser, and the user already signed into the target Amazon account. If mcp__claude-in-chrome__* tools aren't loaded yet, fetch them via ToolSearch first (see the extension's own MCP instructions for the batch-load query).
  • This runs against a real account. If the account is shared (family members with separate shipping addresses on the same login), be ready to see orders that aren't the user's — flag those, don't just fold them into the same batch without asking.

Phase 1a — Order/return discovery (read-only, no side effects)

Goal: find every completed return where Amazon deducted a restocking fee, without touching anything.

  1. Search order history broadly by category keyword, not just exact terms — Amazon's your-orders/search matches loosely, so one keyword (e.g. "razor") surfaces adjacent items (shavers, trimmers) too. Restocking fees concentrate on higher-value electronics/appliances, so prioritize checking those over consumables or clothing.
    • https://www.amazon.com/your-orders/search/ref=ppx_yo2ov_dt_b_search?opt=ab&search=<keyword>
    • Paginate through all result pages — don't stop at page 1. Older orders (a year+ back) still show up here even though they've long since dropped off Your Returns.
  2. For faster coverage of recent activity, also check https://www.amazon.com/your-returns — but note it only shows roughly the last 3 months, so it's a supplement to the search sweep, not a replacement for it.
  3. For each order that shows "Return complete" / "Refund Complete" / "Refund issued", open its detail page: https://www.amazon.com/your-orders/order-details?orderID=<orderID> Find the Refund Total line — it has a small chevron that expands to an itemized breakdown (Item(s) refund / Tax refund / Restocking fee / Refund Total). Click it. Orders with no fee just show item + tax = refund total; orders with a fee show the deduction explicitly.
  4. Record every hit: order #, item name, item price, restocking fee amount, who it shipped to, and whether it was sold by Amazon.com directly or a third-party seller (first-party listings are the strongest cases — Amazon's own chat agents can waive those without looping in a marketplace seller).
  5. Don't try to make this exhaustive on the first pass if the account has a long history — report what's found so far and note that more may be scattered across older years if the user wants a deeper sweep.

Read the full file on GitHub · 172 lines

Files

What ships with it

4 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.

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. 12d ago First seen · 172 lines · 138 tokens per session scan A 45ee4f29a33c

Subscribe to this mod's changes

amazon-returns-recovery is a skill published in the GitHub repository JasonColapietro/suede-creator-skills (135 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 2,463 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

stripe-payments

Add Stripe payments to a web app — Checkout Sessions, Payment Intents, subscriptions, webhooks, customer portal, and pricing pages. Covers the decision of which Stripe API to use, produces working integration code, and handles webhook verification. No MCP server needed — uses Stripe npm package directly. Triggers…

jezweb/claude-skills · 101 tokens

stripe-link-cli

Agent payments via Stripe Link — cards, SPT, approvals.

NousResearch/hermes-agent · 17 tokens

einbeziehung-online-clickwrap-browsewrap

Für Einbeziehung Online Clickwrap Browsewrap: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 42 tokens

kurzfristige-preiserhoehung-lieferfrist

Für Kurzfristige Preiserhöhung 309: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel. Fachgebiet: AGB-Recht-Prüfer. Route: kurzfristige-preiserhoehung-lieferfrist.

Klotzkette/claude-fuer-deutsches-recht · 72 tokens

plattform-online-gate-rollout-rangfolge

Für Plattform und Online Checkout: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: plattform-online-gate-rollout-rangfolge.

Klotzkette/claude-fuer-deutsches-recht · 62 tokens

agb-bei-kreditvertraegen-verbraucherdarlehen

Für AGB bei Kreditverträgen Verbraucherdarlehen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 49 tokens