Mathodology Problem Analyst — Development agent for Claude Code
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
How to install Mathodology Problem Analyst
Installs to ~/.claude/agents/sweetcornna-mathodology-mathodology-problem-analyst.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sweetcornna/mathodology/HEAD/.claude/agents/mathodology-problem-analyst.md -o ~/.claude/agents/sweetcornna-mathodology-mathodology-problem-analyst.md Restart Claude Code, or start a new session, for it to be picked up.
What Mathodology Problem Analyst does
name: mathodology-problem-analyst description: Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping. tools: Read, Write, Grep, Glob model: opus skills: [mathodology-award-gates]
Mathodology Problem Analyst
You turn the contest prompt into an executable modeling brief.
If the mathodology-award-gates skill content is not already in context, read `.claude/skills/mathodology-award-gates/SKILL.md` first.
Produce:
- proble
Alternatives in Development
- Screen Analyst — Use this agent exclusively in the /b3:screen pipeline to fetch precomputed screening metrics for a B3 ticker 124 ★
- Council Regulator — Regulator / Constraint Analyst persona for the autodecision council 97 ★
- Jdb Session.Agent — Run interactive JDB debugging sessions 65 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Mathodology Award Judge
Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria.
Doey Interviewer
World-class requirements analyst — structured interview protocol for extracting clear intent, scope, constrain
Mathodology Critic
Use for independent review of assumptions, model validity, evidence, reproducibility, writing, and final submi
Polymathic Gates
Reasons through Bill Gates's cognitive architecture — platform thinking, systematic deep-reading, multi-source
Goap Agent
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when task
Jev Judge
Reusable Judge/Verifier question-drafter for text-shaped deliverables — pass/fail, meets-bar yes/no, or rubric
Related Skills
Ldd Architect
Documented sugar for LDD[level=L3]: — runs the 5-phase design protocol (Constraints → Non-goals → 3 Candidates
Formula
Define the formula. Scope the problem, challenge assumptions, establish success criteria. No formula, no cook.
Anchoring Abstraction To Measurable Constraints 20260709
Translates complex ontological or philosophical hypotheses into testable, quantifiable variables grounded by s