reflexion

Collection of commands that force LLM to reflect on previous response and output. Based on papers like Self-Refine and Reflexion. These techniques improve the output of large language models by introducing feedback and refinement loops.

Installation

npx claude-plugins install @NeoLabHQ/context-engineering-kit/reflexion

Contents

Folders: commands, hooks

Files: README.md

Documentation

Self-refinement framework that introduces feedback and refinement loops to improve output quality through iterative improvement, complexity triage, and verification.

Focused on:

• Self-refinement - Agents review and improve their own outputs
• Multi-agent review - Specialized agents critique from different perspectives
• Iterative improvement - Systematic loops that converge on higher quality
• Memory integration - Lessons learned persist across interactions

Plugin Target

• Decrease hallucinations - reflection usually allows you to get rid of hallucinations by verifying the output
• Make output quality more predictable - same model usually produces more similar output after reflection, rather than after one shot prompt
• Improve output quality - reflection usually allows you to improve the output by identifying areas that were missed or misunderstood in one shot prompt

Overview

The Reflexion plugin implements multiple scientifically-proven techniques for improving LLM outputs through self-reflection, critique, and memory updates. It enables Claude to evaluate its own work, identify weaknesses, and generate improved versions.

Plugin is based on papers like Self-Refine and Reflexion . These techniques improve the output of large language models by introducing feedback and refinement loops.

They are proven to increase output quality by 8–21% based on both automatic metrics and human preferences across seven diverse tasks, including dialogue generation, coding, and mathematical reasoning, when compared to standard one-step model outputs.

On top of that, the plugin is based on the Agentic Context Engineering paper that uses memory updates after reflection, and consistently outperforms strong baselines by 10.6% on agents.

Quick Start

# Install the plugin
/plugin install reflexion@NeoLabHQ/context-engineering-kit

> claude "implement user authentication"
# Claude implements user authentication, then you can ask it to reflect on implementation

> /reflexion:reflect
# It analyses results and suggests improvements
# If issues are obvious, it will fix them immediately
# If they are minor, it will suggest improvements that you can respond to
> fix the issues

# If you would like it to avoid issues that were found during reflection to appear again,
# ask claude to extract resolution strategies and save the insights to project memory
> /reflexion:memorize

Alternatively, you can use the reflect word in initial prompt:

> claude "implement user authentication, then reflect"
# Claude implements user authentication,
# then hook automatically runs /reflexion:reflect

In order to use this hook, need to have bun installed. But for overall command it is not required.

Usage Examples

Automatic Reflection with Hooks

The plugin includes optional hooks that automatically trigger reflection when you include the word “reflect” in your prompt. This removes the need to manually run /reflexion:reflect after each task.

How It Works

1. Include the word “reflect” anywhere in your prompt
2. Claude completes your task
3. The hook automatically triggers /reflexion:reflect
4. Claude reviews and improves its work

# Automatic reflection triggered by "reflect" keyword
> Fix the bug in auth.ts then reflect
# Claude fixes the bug, then automatically reflects on the work

> Implement the feature, reflect on your work
# Same behavior - "reflect" triggers automatic reflection

Important: Only the exact word “reflect” triggers automatic reflection. Words like “reflection”, “reflective”, or “reflects” do not trigger it.

Commands Overview

/reflexion:reflect - Self-Refinement

Reflect on previous response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification

• Purpose - Review and improve previous response
• Output - Refined output with improvements

/reflexion:reflect ["focus area or threshold"]

Arguments

Optional areas to focus or confidence threshold to use, for example “security” or “deep reflect if less than 90% confidence”

How It Works

1. Complexity Triage: Automatically determines appropriate reflection depth

   • Quick Path (5s): Simple tasks get fast verification
   • Standard Path: Multi-file changes get full reflection
   • Deep Path: Critical systems get comprehensive analysis

2. Self-Assessment: Evaluates output against quality criteria

   • Completeness check
   • Quality assessment
   • Correctness verification
   • Fact-checking

3. Refinement Planning: If improvements needed, generates specific plan

   • Identifies issues
   • Proposes solutions
   • Prioritizes fixes

4. Implementation: Produces refined output addressing identified issues

Confidence Thresholds

The command uses co

…(truncated)

Source

View on GitHub