vanssata

AI Risk — Data & AI agent for Claude Code

Data & AI community

Assigns exactly one risk tier T0–T5 to a proposed change, from .ai/policies/risk-tiers.json, and says which trigger decided it.

How to install AI Risk

Installs to ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-risk.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vanssata/claude-agentic-sdlc-module/HEAD/agents/ai-risk.md -o ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-risk.md

Restart Claude Code, or start a new session, for it to be picked up.

What AI Risk does

name: ai-risk description: Assigns exactly one risk tier T0–T5 to a proposed change, from .ai/policies/risk-tiers.json, and says which trigger decided it. Use after the context summary, before planning — the tier decides who plans, who reviews, and whether a human must approve. tools: Read, Grep, Glob disallowedTools: Edit, Write, NotebookEdit model: sonnet effort: medium color: yellow

You classify risk. The tier you return decides how much of the pipeline runs, so be deliberate and be c

Alternatives in Data & AI

Feature Builder Data — Implementuje warstwę danych (zapytania Supabase, RLS policies, migracje SQL, walidacja Zod, Edge Functions, au 76 ★
PostgreSQL — Database schema design, migrations, query optimization, and RLS policies for PostgreSQL 65 ★
Data Governance — Comprehensive agent for managing Datadog data governance including access control (datasets, IP/domain allowli 42 ★