Anomaly Fraud Scanner

Scans transactions for fraud and anomaly signals — duplicate charges within 48 hours, transactions more than 3 standard deviations above a merchant's historical average, first-ever transaction with a new merchant above a high-dollar threshold, and unusual geography or time. Produces severity-tagged alerts with the transaction id, evidence, and a recommended action (call bank, freeze card, dispute, monitor). Use for vigilance scans on every drop, after any large unexplained outflow, or when user mentions fraud check, suspicious charge, anomaly detection, or duplicate charge.

200 stars 25 forksOther Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add lyndonkl/claude

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lyndonkl/claude --skill anomaly-fraud-scanner
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/anomaly-fraud-scanner ~/.claude/skills/anomaly-fraud-scanner

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Anomaly Fraud Scanner

## Table of Contents
- [Overview](#overview)
- [Input contract](#input-contract)
- [Detection rules](#detection-rules)
- [Workflow](#workflow)
- [Output contract](#output-contract)
- [Guardrails](#guardrails)

## Overview

Fraud detection on a household budget is a different problem from fraud detection at a bank. The bank already runs sophisticated rules; this skill exists to catch what the bank misses — small recurring fraud below their threshold, unfamiliar merchant patterns, and post-hoc audit of charges the user has not yet noticed.

It runs five complementary detectors, each producing severity-tagged alerts.

## Input contract

The caller provides:

- `transactions_new` — transactions added by the most recent drop.
- `transactions_history` — last 12 months of confirmed transactions.
- `accounts` — for context (account type, owner, geography).
- `today` — ISO date.
- `thresholds` — optional overrides:
  ```
  {
    "duplicate_window_hours": 48,
    "anomaly_sigma": 3.0,
    "first_merchant_high_dollar_cents": 50000,
    "geo_radius_miles": 1000
  }
  ```

## Detection rules

### Rule 1 — Duplicate within 48 hours

Two transactions on the same `account_id` with the same `merchant` and the same `amount_cents` posted within `duplicate_window_hours` of each other.

- Severity: `medium` for amounts < $200, `high` for amounts ≥ $200.
Read the full skill on GitHub

Details

Skill name
anomaly-fraud-scanner
Path
skills/anomaly-fraud-scanner/SKILL.md
Repo updated
1 September 2026

FAQ

What does the Anomaly Fraud Scanner skill do?

Scans transactions for fraud and anomaly signals — duplicate charges within 48 hours, transactions more than 3 standard deviations above a merchant's historical average, first-ever transaction with a new merchant above a high-dollar threshold, and unusual geography or time. Produces severity-tagged alerts with the transaction id, evidence, and a recommended action (call bank, freeze card, dispute, monitor). Use for vigilance scans on every drop, after any large unexplained outflow, or when user mentions fraud check, suspicious charge, anomaly detection, or duplicate charge.

How do I install the Anomaly Fraud Scanner skill?

Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Anomaly Fraud Scanner popular?

It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.

Related skills

Abstraction Concrete Examples

200

lyndonkl/claude

Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.

Testing & QA25

Academic Letter Architect

200

lyndonkl/claude

Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.

Research & Science25

Adr Architecture

200

lyndonkl/claude

Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.

Software Development25

Auction First Price Shading

200

lyndonkl/claude

Computes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use

Other25

Adverse Selection Prior

200

lyndonkl/claude

Produces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty propos

Other25

Audit Drift

200

lyndonkl/claude

Checks every post currently assigned to a substacker section against that section's promise and flags posts that no longer fit. Distinguishes acceptable-stretch (minor) from borderline (surface for review) from genuine-drift (violates promise). Never reassigns automatically — only flags. Use on every Curator run where at least one section already exists. Trigger keywords — drift, drift audit, section fit, promise violation, post in wrong section.

Other25

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.