Loop Refiner — Development agent for Claude Code
Apply critique issues to produce a minimally changed improved artifact.
How to install Loop Refiner
Installs to ~/.claude/agents/maister-dev-maister-loop-refiner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/maister-dev/maister/HEAD/.claude/agents/loop-refiner.md -o ~/.claude/agents/maister-dev-maister-loop-refiner.md Restart Claude Code, or start a new session, for it to be picked up.
What Loop Refiner does
name: loop-refiner description: Apply critique issues to produce a minimally changed improved artifact. Use proactively within /aif-loop when refinement is needed after failed evaluation. tools: Read, Write, Edit, Glob, Grep model: inherit permissionMode: acceptEdits maxTurns: 6
You are refiner.
Input:
- current artifact markdown
- critique issues
Output:
- Return only improved markdown artifact.
Rules:
- Change only sections required to resolve listed issues.
- Preserve unaffected s
Alternatives in Development
- Eval Engineer — GAIA evaluation framework specialist 1.5k ★
- Flutter Template Refiner — Expert in iterative application-to-template refinement for Flutter applications 85 ★
- Regression Sentinel — Watch evaluation metrics over time for trends and regressions 64 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Plan Polisher
Create or refresh an /aif-plan plan, critique it, and run one refinement round at most. The caller launches an
Loop Orchestrator
Route reflex-loop execution to the next role based on run state, stop guards, and last evaluation. Use proacti
Worca Cc Plan Refiner
Plan Refiner for the orchestrator pipeline. Reads an input plan (with code snippets), writes an improved -vN p
Bounty Report Agent
Use this agent once bounty-exploit-agent has a confirmed, minimally-demonstrated finding for a bug bounty prog
Foundry Voss
Use this agent for agent quality calibration, SKILL.md creation and refinement, agent output evaluation, crew
ChatGPT PR Review
Coordinates ChatGPT PR review round-by-round in a dedicated session (manual / automated / parallel modes). Rea
Related Skills
Simmer
Iterative artifact refinement using judge subagents that score against user-defined criteria across multiple r
Autoloop
Autonomous recursive improvement loop for a single target. Runs gap analysis, recursive refinement, evaluation
Workflow Retry
Resume a blocked workflow pipeline run from the phase where it failed. Use after manually fixing a blocked art