risk

risk is a command for Claude Code from vyayasan/kyc-analyst. It costs 7 tokens per session (333 once invoked), scanned A, original, MIT.

A command for reassessing a customer’s financial-crime risk using geographic, customer, product, and onboarding-channel factors. It produces a risk band from low to critical and specifies the required review or escalation level.

In plain words
What is it for?
Use it for customer due diligence, enhanced due diligence, monitoring decisions, analyst review, and escalation to management or the money-laundering reporting officer.
Why use it?
It replaces an informal risk judgment with a repeatable score based on stated inputs. This makes customer assessments more consistent and easier to audit.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the kyc-analyst plugin — 5 skills, 6 commands shipped together

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 commands/vyayasan/kyc-analyst/risk
Clone the repo
git clone --depth 1 https://github.com/vyayasan/kyc-analyst

Made for: Claude Code.

Or install kyc-analyst, the plugin that ships this one along with the rest of its 5 skills, 6 commands.

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 risk

README.md
[![agentmods](https://agentmods.dev/badge/commands/vyayasan/kyc-analyst/risk.svg)](https://agentmods.dev/commands/vyayasan/kyc-analyst/risk)
Your own site
<a href="https://agentmods.dev/commands/vyayasan/kyc-analyst/risk"><img src="https://agentmods.dev/badge/commands/vyayasan/kyc-analyst/risk.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 333 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 5.1 $0.00007 $0.00333
Opus 5 $0.00003 $0.00167
Sonnet 5 $0.00001 $0.00067
Haiku 4.5 $0.00001 $0.00033

Measured 6d ago against content hash 1bb4720d964f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

risk 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 6d 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.

commands/risk.md · 50 lines

What it actually says

Risk

Comprehensive risk reassessment using four-factor heuristic model with updated due diligence requirements based on current risk profile.

Usage

/kyc:risk <customer name>

Risk Factors

Factor Weight Description
Geographic Risk 30% Customer jurisdiction, transaction countries, wealth origin
Customer Risk 35% PEP status, industry, source of wealth clarity, complexity
Product Risk 25% Account type, expected activity, transaction volume
Channel Risk 10% Onboarding method, documentation quality

Risk Bands

Band Score Range Action Required
LOW 0-20 CDD sufficient, analyst approval
MEDIUM 21-60 Enhanced monitoring, senior analyst review
HIGH 61-80 EDD required, manager + MLRO approval
CRITICAL 81-100 Immediate escalation, senior management decision

Deterministic Scoring

The risk score is calculated mathematically from objective inputs. Same inputs always produce the same score. This ensures:

  • Reproducibility across analysts
  • Fairness across customers
  • Auditability for regulators
  • Consistency across cases

HITL Checkpoint

Risk rating assignment requires analyst review and sign-off. Automated scoring informs but does not replace human judgment.


Version: 1.0.0 Author: Vyayasan

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. 6d ago First seen · 50 lines · 7 tokens per session scan A 1bb4720d964f

Subscribe to this mod's changes

risk is a command published in the GitHub repository vyayasan/kyc-analyst (56 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 333 once invoked, about $0.0000 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.