Development
humanize
Derived from the GAAC (GitHub-as-a-Context) project. A Claude Code plugin that provides iterative development with independent AI review. Build with confidence through continuous feedback loops.
Plugin Signal79/100Solid
maintained87
capable62
documented100
adopted67
Install on Claude Code
Auto-invoked ships a router so the right skill fires automatically as you prompt. No remembering which skill to call.
Normal is the plain upstream plugin, installed as-is. You invoke its skills yourself.
The plugin> /plugin marketplace add PolyArch/humanize> /plugin install humanize@PolyArchAuto-invocation> /plugin marketplace add flowy-sh/flowy-core> /plugin install flowy-core> /plugin install flowy-humanize
What's inside
Skill(6 skills)
/ask-codexConsult Codex as an independent expert. Sends a question or task to codex exec and returns the response./ask-geminiConsult Gemini as an independent expert with deep web research. Sends a question or task to Gemini CLI and returns a research-backed response./humanize-gen-planGenerate a structured implementation plan from a draft document. Validates input, checks relevance, analyzes for issues, and generates a complete plan.md with acceptance criteria.
Command(5 commands)
Agent(4 agents)
bitlesson-selectorSelects required BitLesson entries for a specific sub-task. Use before execution for every task or sub-task.draft-relevance-checkerChecks if a draft document is relevant to the current repository. Use when validating draft content for gen-plan command.plan-compliance-checkerChecks plan relevance and compliance before RLCR loop. Use when validating plan files for start-rlcr-loop command.plan-understanding-quizAnalyzes a plan and generates multiple-choice technical comprehension questions to verify user understanding before RLCR loop. Use when validating user readiness for start-rlcr-loop command.
README
- 🚀 Humanize2 is under active developments and we are looking for your feedbacks!
- ✨ Now humanize has a cool homepage!
Humanize
Current Version: 1.16.0
Derived from the GAAC (GitHub-as-a-Context) project.
A Claude Code plugin that provides iterative development 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 -- Claude implements, Codex independently reviews. No blind spots.
- Ralph Loop with Swarm Mode -- Iterative refinement continues until all acceptance criteria are met. Optionally parallelize with Agent Teams.
- 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 (Claude works, Codex reviews summaries) and Code Review (Codex checks code quality with severity markers). Issues feed back into implementation until resolved.
Install
# Add PolyArch marketplace
/plugin marketplace add PolyArch/humanize
# If you want to use development branch for experimental features
/plugin marketplace add PolyArch/humanize#dev
# Then install humanize plugin
/plugin install humanize@PolyArch
Requires codex CLI for review. See the full Installation Guide for prerequisites and alternative setup options.
Quick Start
-
Generate an idea draft from a loose thought (optional — skip if you already have a draft):
/humanize:gen-idea "add undo/redo to the editor"Output goes to
.humanize/ideas/<slug>-<timestamp>.mdby default. Pass a.mdpath to expand existing rough notes.--ncontrols how many parallel directions explore the idea (default 6). -
Generate a plan from your draft:
/humanize:gen-plan --input draft.md --output docs/plan.md -
Refine an annotated plan before implementation when reviewers add comments (
CMT:...ENDCMT,<cmt>...</cmt>, or<comment>...</comment>):/humanize:refine-plan --input docs/plan.md -
Run the loop:
/humanize:start-rlcr-loop docs/plan.md -
Consult Gemini for deep web research (requires Gemini CLI):
/humanize:ask-gemini What are the latest best practices for X? -
Monitor progress (in another terminal, not inside Claude Code):
source <path/to/humanize>/scripts/humanize.sh # Or just add it into your .bashec or .zshrc 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
File tree
FAQ
humanize is a Claude Code plugin of 6 hand-picked skills with a FLOW.md router. Install it once and the right skill fires as you prompt, with no slash command to remember. It is built for development work. It includes ask-codex, ask-gemini, humanize-gen-plan. Free and open source.
- What is humanize?
- Derived from the GAAC (GitHub-as-a-Context) project. A Claude Code plugin that provides iterative development with independent AI review. Build with confidence through continuous feedback loops.
- How do I install humanize?
- Run these in Claude Code: /plugin marketplace add PolyArch/humanize then /plugin install humanize@PolyArch. Then prompt normally.
- Does humanize auto-invoke its skills?
- Yes. It ships a FLOW.md router that Flowy's hook fires, so the matching skill runs as you prompt. You never name a skill.
- Is humanize free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it