Loop Judge — Development agent for Claude Code
Fresh-context cold-read judge for subjective acceptance criteria (readability, API clarity).
How to install Loop Judge
Installs to ~/.claude/agents/costajohnt-libredb-studio-loop-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/costajohnt/libredb-studio/HEAD/.claude/agents/loop-judge.md -o ~/.claude/agents/costajohnt-libredb-studio-loop-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Loop Judge does
name: loop-judge description: Fresh-context cold-read judge for subjective acceptance criteria (readability, API clarity). Runs after mechanical gates pass; returns a binary verdict. tools: Read, Grep, Glob model: inherit
You are a fresh-context judge for the maintainer loop. You exist because the building agent has just read this code deeply and is the worst possible judge of a cold first read.
Rules
- Read ONLY the files named in the request (plus any shared-vocabulary files it l
Alternatives in Development
- Gitnexus Docs Dod Reviewer — GitNexus docs and Definition-of-Done reviewer 45.8k ★
- Gsd Dom Verifier — Verifies live-DOM acceptance criteria for a completed execution wave using a browser MCP server 8.8k ★
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Fleet Reviewer
Code reviewer with direct p2p dev communication. Two-pass review (code quality + acceptance criteria). Writes
Yalla Reviewer
Adversarial code reviewer for Yalla Coding Team. Reviews code in fresh context with no anchoring bias. Uses bi
Galadriel
Fresh-context GATE evaluator for work declared finished. Binary PASS / NEEDS_WORK, no benefit of the doubt wit
Atlas Clarity Reviewer
Per-page clarity verdict for one architecture atlas page — followability, boundary-entry specificity, ambiguit
Sub Agent Tester
PROACTIVELY used to verify that an implementation actually satisfies the Issue's acceptance criteria at runtim
Ticket Evaluator
Skeptical ticket quality evaluator. Verifies acceptance criteria testability, clarity, and implementability.
Related Skills
Gov Metrics
Governance metrics — measure whether the gates actually work. Block rate, override/waiver rate, false-block pr
Ac Validation
Review Acceptance Criteria for one or more user stories against completeness and quality standards. Checks hap
Do It Skill
Claude Code skill: single-shot autonomous build pipeline (spec → plan → build → review → commit) with tiered r