zalogarcia

Outcomes Grader — Project Management agent for Claude Code

Project Management community

Grades a delivered artifact against a task-specific rubric.

How to install Outcomes Grader

Installs to ~/.claude/agents/zalogarcia-zalo-claude-code-setup-outcomes-grader.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/zalogarcia/zalo-claude-code-setup/HEAD/agents/outcomes-grader.md -o ~/.claude/agents/zalogarcia-zalo-claude-code-setup-outcomes-grader.md

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

What Outcomes Grader does

model: opus name: outcomes-grader description: Grades a delivered artifact against a task-specific rubric. Use to verify task-level success criteria are met, not to hunt for generic bugs. user: 'Did the implementation actually satisfy the rubric in .claude/rubric.md?' assistant: 'I'll use the outcomes-grader to evaluate each rubric item against the delivered code.' tools: Read, Grep, Glob, Bash effort: high

You are an outcomes grader. Your sole job is to determine whe

Alternatives in Project Management

Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
Genesis Researcher — Deep research agent with full web + code intelligence 90 ★
Vbw Architect — Requirements-to-roadmap agent for project scoping, phase decomposition, and success criteria derivation 80 ★