Risk Scorer — Development agent for Claude Code
Fast risk assessment of PR changes.
How to install Risk Scorer
Installs to ~/.claude/agents/andyzengmath-soliton-risk-scorer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/andyzengmath/soliton/HEAD/agents/risk-scorer.md -o ~/.claude/agents/andyzengmath-soliton-risk-scorer.md Restart Claude Code, or start a new session, for it to be picked up.
What Risk Scorer does
name: risk-scorer description: Fast risk assessment of PR changes. Computes a 0-100 risk score from 6 weighted factors and recommends which review agents to dispatch. model: sonnet tools: ["Read", "Grep", "Glob", "Bash"]
Risk Scorer Agent
You are the risk scoring engine for Soliton PR Review. You receive a ReviewRequest and compute a RiskAssessment before any review agents are dispatched. Your job is to be FAST and ACCURATE — the entire review pipeline depends on your risk level dete
Alternatives in Development
- Cs Guardian — Customer success partner for account health, churn risk, renewals, escalations, and QBRs 1.3k ★
- Legal Risks — Legal Risk Assessment Subagent 841 ★
- Lex Legal — Use this agent when dealing with legal and compliance activities 523 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Scoring
Score a Notion lead row against the user-editable scoring schema. Reads schema tab + enriched lead, computes w
Health Checker
Code health dashboard agent - structured 3-phase methodology (detect, measure, prescribe) with weighted 0-10 s
Holdings Valuation Scorer
Grades the valuation of one ETF's holdings, assessing P/E, P/B, and EV multiples against industry averages, ea
Financial Controller
Financial Controller for agent teams. Audits token usage, run duration, tool calls and efficiency across all d
Compare Branch
Compare current branch vs main/staging — changes, risk assessment, merge readiness.
Deoxys
Score skill candidates using weighted criteria
Related Skills
Fraud Detection Using Agentic AI
AI-powered insurance claims fraud detection agent — combines a Random Forest classifier for risk scoring with
Plan Freeze
Commit the active feature's spec.md + plan.md on a plan/ branch and open a PR for human review. Wraps scripts/
Score Opportunity
Calculate opportunity score using weighted rubric