nagisanzenin

Effort Grader — Project Management agent for Claude Code

Project Management community

Blind grader for effortmining.

How to install Effort Grader

Installs to ~/.claude/agents/nagisanzenin-effortmining-effort-grader.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/nagisanzenin/effortmining/HEAD/agents/effort-grader.md -o ~/.claude/agents/nagisanzenin-effortmining-effort-grader.md

Restart Claude Code, or start a new session, for it to be picked up.

What Effort Grader does

name: effort-grader description: "Blind grader for effortmining. Grades one artifact against a task prompt and a fixed rubric ONLY. The input payload deliberately carries no field naming the tier, agent, or model that produced the artifact, so the grade cannot be biased by effort level. Skeptic-first, rounds scores down, emits strict JSON consumed by bench/effort.py. Pinned to medium effort (one tier below the miner workers) to avoid grader-effort confounds. Use for non-deterministic benchma

Alternatives in Project Management

Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
Sc Recon Expander — Task-less smart-contract recon expander — resolves proxies/diamonds/roles/linked addresses per chain and retur 97 ★
Loom Advisor — Read-only advisory agent for debugging and repeated failures 53 ★