Prior Scores Finder — Research agent for Claude Code
Finds prior scored reforms to anchor a new analysis — PolicyEngine's own published scores first, then official fiscal notes (state legislative fiscal offices, JCT, CBO, CRFB), then think-tank analyses.
How to install Prior Scores Finder
Installs to ~/.claude/agents/policyengine-policyengine-claude-prior-scores-finder.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/PolicyEngine/policyengine-claude/HEAD/agents/prior-scores-finder.md -o ~/.claude/agents/policyengine-policyengine-claude-prior-scores-finder.md Restart Claude Code, or start a new session, for it to be picked up.
What Prior Scores Finder does
name: prior-scores-finder description: Finds prior scored reforms to anchor a new analysis — PolicyEngine's own published scores first, then official fiscal notes (state legislative fiscal offices, JCT, CBO, CRFB), then think-tank analyses (Tax Foundation, ITEP, CBPP, TPC). Generalizes the legislative-tracker fiscal-finder by adding the PolicyEngine prior-scores layer. tools: WebFetch, WebSearch, Read, Bash, Skill model: sonnet
Prior Scores Finder
Returns a ranked list of analog refo
Alternatives in Research
- Exploit Researcher — Vulnerability research agent — identifies CVEs, finds exploit PoCs, maps attack chains, and develops custom ex 348 ★
- Deep Research Critic — Adversarial reader of a nav-deep-research draft 232 ★
- Gemini GPT Hybrid Soft — Intelligent hybrid agent that uses Gemini and GPT for analysis and problem identification, then returns insigh 153 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Reform Comparator
Stage-5 comparator. Takes the microsim output and the prior-scores anchor, returns PASS (within expected band,
Step Finder
Finds reusable step definitions and checks whether a proposed new step would ambiguously match an existing one
Story Researcher
Verifies the anchor story, case study, number or quote behind a Written as Spoken post, then returns what can
Gauntlet Cleaner
Stage 3 of the agent gauntlet. Runs CRAP analysis (coverage × cyclomatic complexity) and a general code review
SDK Researcher
Deep-research a specific SDK or service. Reads official docs, finds all credentials requirements, documents AP
Lydia
CFO advisory agent for financial strategy, modeling, analysis, and fiscal leadership. Use when analyzing finan
Related Skills
Logo Finder Skill
Logo finder skill for Claude and other AI agents (open Agent Skills standard) — finds the current official com
Prior Analysis
Search the local analyses archive for prior /analyze-policy runs — did we already score this? What did we conc
Distressed Homes Finder
Claude Code skill: finds distressed / motivated-seller homes and rent-from-owner leads across Craigslist, Zill