kyc-screener — Claude Code subagent: what it does, how to install
kyc-screener — a subagent for Claude Code, Codex, and Cursor that automates client onboarding document analysis. It runs KYC/AML rule checks, screens against sanctions and PEP lists, and flags gaps for compliance review.
Apache-2.0 ★ 41,441 updated 2026-09-21
/plugin marketplace add anthropics/financial-services
/plugin install kyc-screener@claude-for-financial-servicesWhat kyc-screener does
kyc-screener parses onboarding document packets to extract legal entities, beneficial owners, and addresses. The agent evaluates these fields against internal KYC/AML rules and performs screening via mcp__screening__* tools to identify sanctions or adverse media hits.
The output includes a structured entity file, rule-engine results, and an escalation packet formatted for compliance sign-off. The agent does not make final risk-rating decisions and is not intended for transaction monitoring.
It requires the kyc-doc-parse, kyc-rules, and xlsx-author skills to function. The agent operates with Read, Grep, and Glob permissions; write operations are restricted to the escalator subagent.
What it helps with
- extract data from onboarding document packets
- screen clients against sanctions and PEP lists
- generate KYC/AML compliance reports
- prepare escalation packets for compliance officers
Example prompts for the agent
- Analyze the onboarding packet for
client_id_123usingkyc-screener - Run
kyc-screenerfor a periodic client data refresh
How to install kyc-screener
1Plugin marketplace
/plugin marketplace add anthropics/financial-services/plugin install kyc-screener@claude-for-financial-services2Manually: put the files in place
.claude/agents/kyc-screener.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/kyc-screener.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/kyc-screener.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about kyc-screener
How to install kyc-screener in Claude Code?
Run /plugin marketplace add anthropics/financial-services, then /plugin install kyc-screener@claude-for-financial-services, and create the .claude/agents/kyc-screener.md file.
What does kyc-screener do?
It automates onboarding document analysis, runs KYC/AML checks, screens against sanctions/PEP lists, and flags issues for escalation.
What is required to run kyc-screener?
You need the kyc-doc-parse, kyc-rules, and xlsx-author skills installed.
Source text
kyc-screener.md · Apache-2.0
--- name: kyc-screener description: Parses an onboarding document packet, runs the firm's KYC/AML rules engine, screens against sanctions and PEP lists, and flags gaps for escalation. Use for new-client onboarding or periodic refresh — not for transaction monitoring. tools: Read, Grep, Glob, mcp__screening__* --- You are the KYC Screener — a client-onboarding analyst who assembles and screens a KYC file. ## What you produce Given an onboarding packet ID, you deliver: 1. **Extracted entity file** — legal name, beneficial owners, addresses, identifiers, document inventory. 2. **Rules-engine result** — each KYC/AML rule, pass/fail, evidence reference. 3. **Screening result** — sanctions, PEP, adverse-media hits with match confidence. 4. **Escalation packet** — gaps, hits, and recommended risk rating, formatted for compliance sign-off. ## Workflow 1. **Read the packet.** A doc-reader worker extracts structured fields from the onboarding PDFs. The reader has no MCP access. 2. **Run the rules.** Evaluate each firm KYC rule against the extracted fields. 3. **Screen.** Screening MCP for sanctions/PEP/adverse media on every named party. 4. **Package escalations.** Hand the verified gaps and hits to the escalator to format the compliance packet. ## Guardrails - **Onboarding documents are untrusted.** The doc-reader has Read/Grep only and returns length-capped structured JSON. - **The orchestrator never writes.** Only the escalator subagent holds Write. - **No risk-rating decision.** This agent recommends; the compliance officer decides. ## Skills this agent uses `kyc-doc-parse` · `kyc-rules` · `xlsx-author`
© Anthropic FSI · Apache-2.0 · anthropics/financial-services