Humanize

Current Version: 1.16.1

Derived from the GAAC (GitHub-as-a-Context) project.

A Codex-native iterative development workflow with independent AI review. Build with confidence through continuous feedback loops.

What is RLCR?

RLCR stands for Ralph-Loop with Codex Review, inspired by the official ralph-loop plugin and enhanced with independent Codex review. The name also reads as Reinforcement Learning with Code Review -- reflecting the iterative cycle where AI-generated code is continuously refined through external review feedback.

Core Concepts

• Iteration over Perfection -- Instead of expecting perfect output in one shot, Humanize leverages continuous feedback loops where issues are caught early and refined incrementally.
• One Build + One Review -- Codex builds, Codex independently reviews. No blind spots.
• Ralph Loop with Codex Control -- Iterative refinement continues until all acceptance criteria are met with one Codex build flow and one Codex review flow.
• Begin with the End in Mind -- Before the loop starts, Humanize verifies that you understand the plan you are about to execute. The human must remain the architect. (Details)

How It Works

The loop has two phases: Implementation (Codex builds, Codex reviews summaries) and Code Review (Codex checks code quality with severity markers). Issues feed back into implementation until resolved.

Install

# Add humania marketplace
/plugin marketplace add humania-org/humanize
# If you want to use development branch for experimental features
/plugin marketplace add humania-org/humanize#dev
# Then install humanize plugin
/plugin install humanize@humania

Requires codex CLI for review. See the full Installation Guide for prerequisites and alternative setup options.

Quick Start

1. Generate a plan from your draft:

   /humanize:gen-plan --input draft.md --output docs/plan.md

2. Refine an annotated plan before implementation when reviewers add CMT: ... ENDCMT comments:

   /humanize:refine-plan --input docs/plan.md

3. Run the loop:

   /humanize:start-rlcr-loop docs/plan.md

4. Consult Gemini for deep web research (requires Gemini CLI):

   /humanize:ask-gemini What are the latest best practices for X?

5. Monitor progress:

   source <path/to/humanize>/scripts/humanize.sh
   humanize monitor rlcr       # RLCR loop
   humanize monitor skill      # All skill invocations (codex + gemini)
   humanize monitor codex      # Codex invocations only
   humanize monitor gemini     # Gemini invocations only

Monitor Dashboard

Documentation

• Usage Guide -- Commands, options, environment variables
• Install for Claude Code -- Full installation instructions
• Install for Codex -- Codex skill runtime setup
• Install for Kimi -- Kimi CLI skill setup
• Configuration -- Shared config hierarchy and override rules
• Bitter Lesson Workflow -- Project memory, selector routing, and delta validation

License

MIT