agentmods.dev

radar-fraud-rules

radar-fraud-rules is a skill for Claude Code, Codex from appeeky/stripe-skills. It costs 75 tokens per session (474 once invoked), scanned A, original, MIT.

A design and review of Stripe Radar rules, which decide whether payments should be blocked, sent for extra card verification, or reviewed because they may be fraudulent. 3D Secure is an extra identity check during some card payments.

In plain words
What is it for?
Use it to review fraud rules, prepaid-card blocking, 3D Secure requests, risk levels, block lists, decline patterns, and the effect of rule changes.
Why use it?
It helps reduce suspicious payments while checking whether rules might wrongly reject legitimate customers. Stripe Radar is Stripe’s fraud-screening system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 5repo 3mo ago A scan 75 tokens original MIT

Good fit Use it to review fraud rules, prepaid-card blocking, 3D Secure requests, risk levels, block lists, decline patterns, and the effect of rule changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/appeeky/stripe-skills/radar-fraud-rules
View source ↗ appeeky/stripe-skills appeeky.com
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 appeeky/stripe-skills --skill radar-fraud-rules
Clone the repo
git clone --depth 1 https://github.com/appeeky/stripe-skills

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 radar-fraud-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/appeeky/stripe-skills/radar-fraud-rules/github.svg)](https://agentmods.dev/skills/appeeky/stripe-skills/radar-fraud-rules)
Your own site
<a href="https://agentmods.dev/skills/appeeky/stripe-skills/radar-fraud-rules"><img src="https://agentmods.dev/badge/skills/appeeky/stripe-skills/radar-fraud-rules/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 radar-fraud-rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/appeeky/stripe-skills/radar-fraud-rules"><img src="https://agentmods.dev/badge/skills/appeeky/stripe-skills/radar-fraud-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 474 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.
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 $0.00075 $0.00474
Opus 5.5 $0.00030 $0.00190
Sonnet 5.5 $0.00015 $0.00095
Haiku 4.5 $0.00007 $0.00047

Measured 2mo ago against content hash 8b0eb84ae55f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

radar-fraud-rules 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 2mo 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/radar-fraud-rules/SKILL.md · 59 lines

What it actually says

Radar & Fraud Rules

Stripe MCP Setup

Requires Stripe MCP connected via OAuth or restricted key. Docs: https://docs.stripe.com/mcp

  1. GetMcpTools with server: "user-Stripe" (or plugin-stripe-stripe) before any call
  2. Prefer stripe_api_search → stripe_api_details → stripe_api_read for list/retrieve
  3. Always paginate — limit: 100, follow has_more with starting_after
  4. Amounts are in cents unless noted
  5. Never expose secret keys in output

Assess Current Rules

Dashboard: Radar → Rules. Document enabled vs disabled.

Default rules often include:

  • Block risk_level = highest
  • Default block lists
  • 3DS / CVC / postal (often disabled)

Custom rules require Radar for Fraud Teams.

Priority Rule Action
1 :card_funding: = 'prepaid' Block
2 :is_new_card_on_customer: Request 3DS
3 :risk_level: = 'elevated' Review
4 Repeat failed CVC Block (if enabled)

Start with Review before Block to measure false positives.

Verify Impact

After rule change, compare blocked payments in Dashboard → Payments (outcome: blocked).

search_stripe_documentation for latest Radar attribute names.

Output Template

Radar Audit

Current rules: [summary from user screenshot or API if available]
Recommended additions:
1. [rule] — [rationale]

Rollout: Review → 7d → Block
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. 2mo ago First seen · 59 lines · 75 tokens per session scan A 8b0eb84ae55f

Subscribe to this mod's changes

radar-fraud-rules is a skill published in the GitHub repository appeeky/stripe-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 474 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Finance and fintechSecurityskillsstripestripe-skills
Related

radar-fraud-rules compared with skills from other repositories

radar-fraud-rules next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
radar-fraud-rulesappeeky/stripe-skillsSkill53mo agoMITA75Claude Code, Codex
stock-liquidityhimself65/finance-skillsSkill3.5k3d agoMITA129Claude Code
company-valuationhimself65/finance-skillsSkill3.5k3d agoMITA155Claude Code
fintel-datahimself65/finance-skillsSkill3.5k3d agoMITA157Claude Code
earnings-recaphimself65/finance-skillsSkill3.5k3d agoMITA112Claude Code
estimate-analysishimself65/finance-skillsSkill3.5k3d agoMITA117Claude Code
alpha-vantageforyourhealth111-pixel/Vibe-SkillsSkill3.8k3d agoApache-2.0A126Claude Code, Codex