Mathodology Award Judge — Development agent for Claude Code
Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria.
How to install Mathodology Award Judge
Installs to ~/.claude/agents/sweetcornna-mathodology-mathodology-award-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sweetcornna/mathodology/HEAD/.claude/agents/mathodology-award-judge.md -o ~/.claude/agents/sweetcornna-mathodology-mathodology-award-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Mathodology Award Judge does
name: mathodology-award-judge description: Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria. tools: Read, Grep, Glob, Bash model: opus
Mathodology Award Judge
You are **one seat** on a blind judge panel. You are not the lead, not the critic, and not the other seats. Score the submission in front of you and stop.
This brief is self-contained: do **not** read the workflow skills or gate docs — they contain run-management contex
Alternatives in Development
- Engram Assessor — Independent grader of learner productions for the Engram learning plugin 1.4k ★
- Thermo Nuclear Code Quality Review — Independent strict maintainability reviewer for a collected diff and changed-file contents 144 ★
- Voice Call Judge Escalated — High-effort voice-call rubric judge for conflicting or incident evidence 63 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Mathodology Problem Analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable
Judge Panel
Use when a draft or a past winning entry must be scored against a contest's official rubric before submission.
Mathodology Lead
Use as the Claude Code workflow lead for Mathodology award-level modeling submissions.
Blind Evaluator
Structurally separate eval agent. Receives ONLY the problem statement + rubric, NEVER the solution or the impl
Blind Peer Referee
Use this agent when a user wants an independent, structured peer review of an academic paper manuscript — eith
Fixture Builder
Creates and enriches eval suite fixtures — .md component files, .metadata.yaml grading criteria, and .rubric.y
Related Skills
Openprism Bakeoff
Blind-judge two models on one prompt to decide which earns a panel seat
Agentic Job Search
Agentic job-application system built AI-first with Claude Code: hourly watcher over 46 job boards with qualifi
Claude Council Of Five
Claude Code skill: five personas (Chair, Devil's Advocate, Principles Purist, Outsider, Executor) debate your