Fuzzer — Data & AI agent for Claude Code
Generates property-based tests that find edge cases humans miss.
How to install Fuzzer
Installs to ~/.claude/agents/elixpo-claudeops.elixpo-fuzzer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/elixpo/claudeOps.elixpo/HEAD/agents/fuzzer.md -o ~/.claude/agents/elixpo-claudeops.elixpo-fuzzer.md Restart Claude Code, or start a new session, for it to be picked up.
What Fuzzer does
name: fuzzer description: Generates property-based tests that find edge cases humans miss. Use for pure functions, parsers, serializers, data transformations, and any code where input space is large. tools: Read, Write, Edit, Bash, Grep, Glob model: sonnet effort: high color: green
You are a property-based testing specialist. You find bugs by testing PROPERTIES of code, not specific examples.
What Property-Based Testing Does
Instead of: `assert add(2, 3) == 5` You write: `for all int
Alternatives in Data & AI
- Harness Radar — Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — fro 801 ★
- Data Collector — Pure MCP and web data fetching for portfolio skills 139 ★
- Review Code Robustness — A code review agent that checks analysis scripts for fragile patterns, missing error handling at data boundari 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Hypothesis Tester
Generates property-based tests that find edge cases humans miss. Use for pure functions, parsers, serializers,
AI Stack Expert
Expert on AI coding tool configuration — file formats, folder structures, edge cases, and ecosystem trends. Ma
PM Logic Review
Read-only correctness reviewer for Product Masters LMS diffs. Finds the input/edge case that makes the logic p
LLM Performance Analyst
Evaluates LLM agent performance from session transcripts — token usage, tool-call efficiency, and error patter
Abuse Tester
Attacks Sortd's parsers and data paths with hostile inputs (money and currency strings, dates, statement rows,
Repo Intel Summarizer
Produce a 3-depth narrative description of a repository (1-line, 1-paragraph, 1-page) for AI agents and humans
Related Skills
Rowan Autosearch
Agent-driven molecular optimization over chemical space, using Rowan for property scoring and RDKit for constr
Property Testing Rules
Always-on property-testing standards from the Hypothesis documentation. Apply when writing tests for functions
Chem Properties Excel
Claude Code Skill: Extract chemicals from any input, query 14 property fields across 12 sources, generate Exce