Aidd Arch Judge — Development agent for Claude Code
Scores AIDD architecture candidates against the fixed rubric, independently.
How to install Aidd Arch Judge
Installs to ~/.claude/agents/ravitejaadarsu-aidd-delta-aidd-arch-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ravitejaadarsu/AIDD-Delta/HEAD/agents/aidd-arch-judge.md -o ~/.claude/agents/ravitejaadarsu-aidd-delta-aidd-arch-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Aidd Arch Judge does
name: aidd-arch-judge description: Scores AIDD architecture candidates against the fixed rubric, independently. tools: Read, Grep, Glob, Write
You are the AIDD **arch-judge** role.
Read `.aidd/framework/roles/arch-judge.md` and follow it exactly — Mission, Inputs, Protocol, Self-Verification, Report Format. Your dispatch prompt carries the specific assignment (story id, dimension, lens, stage, or finding). Artifacts are your only channel: read the inputs the role file names, write the
Alternatives in Development
- Shep Clean Arch Auditor — Read-only clean architecture auditor for shep 247 ★
- Mathodology Award Judge — Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria 137 ★
- Voice Call Judge Escalated — High-effort voice-call rubric judge for conflicting or incident evidence 63 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Plan Judge
Independent reviewer that scores an implementation plan against the fixed plan-quality rubric and returns spec
Resume Judge
Scores a resume or letter draft against the anchored rubric in templates/rubric-resume.md and returns per-dime
Hackathon Judge
Independent hackathon judge with no stake in the build. Given a judge prompt and evidence pack, it scores the
Rubric Judge
Scores one gate's artifact set against that gate's rubric and writes a findings report the human reads alongsi
Call Scorer
Scores one sales or discovery call transcript against SPIN, Gap Selling, the Trust Equation, yellow lights, JO
Lite Scan
Low-cost read-only scanner for mechanical lookups — file/symbol inventory, grep/stats aggregation, fixture sam
Related Skills
Skill Eval Loop
Agent Skill: harden another skill from its automatic agent evals. Score every Claude Code, Codex and Gemini CL
Audit Skills
Periodic health audit of all skills in .claude/skills/ and agents in .claude/agents/. Scores each against a 16
Rate Cv
Claude Code skill that scores and critiques CVs against a weighted engineering-leadership rubric, with ATS and
