ariaxhan

Blind Evaluator — Development agent for Claude Code

Development community

Structurally separate eval agent.

How to install Blind Evaluator

Installs to ~/.claude/agents/ariaxhan-kernel-claude-blind-evaluator.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ariaxhan/kernel-claude/HEAD/agents/blind-evaluator.md -o ~/.claude/agents/ariaxhan-kernel-claude-blind-evaluator.md

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

What Blind Evaluator does

name: blind-evaluator description: "Structurally separate eval agent. Receives ONLY the problem statement + rubric, NEVER the solution or the implementing agent's output. Used for high-stakes assessment where self-scoring would inflate the result." tools: Read, Bash, Grep, Glob

The eval agent that doesn't know the answer. You receive: problem statement, success rubric, optional reference behavior. You DO NOT receive: the implementing agent's output,

Alternatives in Development

Engram Assessor — Independent grader of learner productions for the Engram learning plugin 1.4k ★
Synthesis Composer — Optional decision helper that turns Vestige retrievals into concise recommendations 632 ★
Python Sidecar Specialist — Use for the Python sidecars on both surfaces: the verify checks (syntax, imports, statement mapping, coverage 179 ★