Independent Evaluator — Design agent for Claude Code
Independently score architecture/UI/implementation candidates using traceable evidence and reject hard blockers within a finite improvement budget.
How to install Independent Evaluator
Installs to ~/.claude/agents/khadinakbarlabs-chrome-extension-builder-plugin-independent-evaluator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/khadinakbarlabs/chrome-extension-builder-plugin/HEAD/agents/independent-evaluator.md -o ~/.claude/agents/khadinakbarlabs-chrome-extension-builder-plugin-independent-evaluator.md Restart Claude Code, or start a new session, for it to be picked up.
What Independent Evaluator does
name: independent-evaluator description: Independently score architecture/UI/implementation candidates using traceable evidence and reject hard blockers within a finite improvement budget. tools: Read, Glob, Grep, Bash model: inherit skills:
- chrome-extension-builder:chrome-extension-builder-evolution
Collaboration contract
Read the mapped skill before work. The orchestrator assigns exact inputs, output destination and exclusive file ownership. Repository/user instructions and ex
Alternatives in Design
- Omarchy Plugin Architect — Design and build Omarchy (Quickshell/QML) bar-widget, panel, and service plugins that actually work on a stock 2.7k ★
- Gdd Auditor — Independent GDD reviewer 517 ★
- Omd Persona Tester — Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget 465 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Ms Browser Verifier
Visual PR review via browser. Completes user journeys end-to-end, fixes trivial issues inline, reports blocker
Red Team Advisor
harness-architect 9-Phase 산출물(03-pipeline-design.md, 04-agent-team.md 등) 정합성 검증 전용. 일반 프로젝트의 코드·PR·문서 review 에
Planning
Tech lead. Turns approved requirements, architecture and design review into an ordered, traceable implementati
Game Analyst
Game-design feasibility analyst. Takes game-researcher output + project context (Godot 4, solo dev, tactical R
ADR Critic
Use when a drafted Architecture Decision Record must be checked against a written standard before it is accept
ADR Scribe
Use when a blind design panel has produced a score table and one winning design and the decision now has to be
Related Skills
Evaluator
Use when the user invokes /evo:evaluator or asks to evaluate, assess, score, or independently audit code quali
Craft Research Verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree
Orchestrate Consult
Run an independent external audit of a completed ZOdyssey run. Hands the plan + full git diff to the external