Development
Plugin
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
maintained88
capable62
documented100
adopted67
Install on Claude Code
> /plugin marketplace add PolyArch/humanize> /plugin install humanize@PolyArch
What's inside
Skills
6/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./humanize-refine-planRefine an annotated implementation plan into a comment-free plan and a QA ledger while preserving the gen-plan schema./humanize-rlcrStart RLCR (Ralph-Loop with Codex Review) on Codex using the native Stop hook./humanizeIterative development with AI review. Provides RLCR (Ralph-Loop with Codex Review) for implementation planning and code review loops.
Agents
4bitlesson-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.
Commands
5/cancel-rlcr-loopCancel active RLCR loop/gen-ideaGenerate a repo-grounded idea draft via directed-swarm exploration/gen-planGenerate implementation plan from draft document/refine-planRefine an annotated implementation plan and generate a QA ledger/start-rlcr-loopStart iterative loop with Codex review
Hooks
4README
1Humanize
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
204PolyArch/humanizeView on GitHub
.claude/
.claude-plugin/
marketplace.json
plugin.json
CLAUDE.md
.github/
workflows/
plan-file-test.yml
pr-target-check.yml
run-all-tests.yml
shell-syntax-check.yml
template-test.yml
version-bump-check.yml
.gitignore
agents/
bitlesson-selector.md
draft-relevance-checker.md
plan-compliance-checker.md
plan-understanding-quiz.md
commands/
cancel-rlcr-loop.md
gen-idea.md
gen-plan.md
refine-plan.md
start-rlcr-loop.md
config/
codex-hooks.json
default_config.json
docs/
bitlesson.md
images/
monitor.png
rlcr-workflow.svg
install-for-claude.md
install-for-codex.md
install-for-kimi.md
usage.md
hooks/
check-todos-from-transcript.py
hooks.json
lib/
loop-bg-tasks.sh
loop-common.sh
methodology-analysis.sh
project-root.sh
template-loader.sh
loop-bash-validator.sh
loop-codex-stop-hook.sh
loop-edit-validator.sh
loop-plan-file-validator.sh
loop-post-bash-hook.sh
loop-read-validator.sh
loop-write-validator.sh
prompt-template/
block/
bitlesson-delta-empty-kb.md
bitlesson-delta-inconsistent.md
bitlesson-delta-invalid.md
bitlesson-delta-missing-notes.md
bitlesson-delta-missing.md
claude-eyes-timeout.md
codex-review-failed.md
finalize-contract-access.md
finalize-state-file-modification.md
git-add-humanize.md
git-not-clean-humanize-local.md
git-not-clean-untracked.md
git-not-clean.md
git-push.md
git-status-failed.md
git-tracked-humanize.md
goal-tracker-bash-write.md
goal-tracker-modification.md
goal-tracker-not-initialized.md
incomplete-todos.md
large-files.md
mainline-drift-stop.md
mainline-verdict-missing.md
methodology-analysis-state-file-modification.md
plan-backup-protected.md
plan-file-modified.md
prompt-file-write.md
round-contract-bash-write.md
round-contract-missing.md
schema-outdated.md
state-file-modification.md
stop-hook-direct-execution.md
summary-bash-write.md
todos-file-access.md
unpushed-commits.md
work-summary-missing.md
wrong-contract-location.md
wrong-directory-path.md
wrong-file-location.md
wrong-round-file.md
wrong-round-number.md
wrong-summary-location.md
claude/
agent-teams-continue.md
agent-teams-core.md
agent-teams-instructions.md
drift-replan-prompt.md
finalize-phase-prompt.md
finalize-phase-skipped-prompt.md
goal-tracker-update-request.md
methodology-analysis-prompt.md
next-round-footer.md
next-round-prompt.md
open-question-notice.md
post-alignment-action-items.md
push-every-round-note.md
review-phase-prompt.md
codex/
code-review-phase.md
commit-history-section.md
full-alignment-review.md
goal-tracker-update-section.md
regular-review.md
idea/
gen-idea-template.md
plan/
gen-plan-template.md
refine-plan-qa-template.md
README.md
scripts/
ask-codex.sh
ask-gemini.sh
bitlesson-init.sh
bitlesson-select.sh
bitlesson-validate-delta.sh
cancel-rlcr-loop.sh
humanize.sh
install-codex-hooks.sh
install-skill.sh
install-skills-codex.sh
install-skills-kimi.sh
lib/
config-loader.sh
model-router.sh
monitor-common.sh
monitor-skill.sh
portable-timeout.sh
rlcr-stop-gate.sh
setup-rlcr-loop.sh
statusline.sh
validate-gen-idea-io.sh
validate-gen-plan-io.sh
validate-refine-plan-io.sh
skills/
ask-codex/
SKILL.md
ask-gemini/
SKILL.md
humanize/
humanize-gen-plan/
SKILL.md
humanize-refine-plan/
SKILL.md
humanize-rlcr/
SKILL.md
SKILL.md
templates/
bitlesson.md
tests/
fixtures/
comment-reactions.json
issue_comments.json
issue-comments.json
pr_reviews.json
pr-reviews.json
reactions.json
review_comments.json
review-comments.json
manual-monitor-test.sh
mocks/
gh
robustness/
test-base-branch-detection.sh
test-cancel-security-robustness.sh
test-concurrent-state-robustness.sh
test-git-operations-robustness.sh
test-goal-tracker-robustness.sh
test-hook-input-robustness.sh
test-hook-system-robustness.sh
test-path-validation-robustness.sh
test-plan-file-robustness.sh
test-session-robustness.sh
test-setup-scripts-robustness.sh
test-state-file-robustness.sh
test-state-transition-robustness.sh
test-template-error-robustness.sh
test-template-stress-robustness.sh
test-timeout-robustness.sh
run-all-tests.sh
setup-monitor-test-env.sh
test-agent-teams.sh
test-allowlist-validators.sh
test-ansi-parsing.sh
test-ask-codex.sh
test-bash-validator-patterns.sh
test-bitlesson-select-routing.sh
test-bitlesson-validate-delta.sh
test-cancel-signal-file.sh
test-codex-hook-install.sh
test-codex-review-merge.sh
test-commit-history-section.sh
test-config-error-handling.sh
test-config-merge.sh
test-disable-nested-codex-hooks.sh
test-error-scenarios.sh
test-finalize-phase.sh
test-gen-plan.sh
test-helpers.sh
test-humanize-escape.sh
test-model-router.sh
test-monitor-e2e-deletion.sh
test-monitor-e2e-real.sh
test-monitor-e2e-sigint.sh
test-monitor-runtime.sh
test-plan-file-hooks.sh
test-plan-file-validation.sh
test-refine-plan.sh
test-session-id.sh
test-skill-monitor.sh
test-state-exit-naming.sh
test-stop-gate.sh
test-stop-hook-bg-allow.sh
test-stop-hook-legacy-compat.sh
test-task-tag-routing.sh
test-template-loader.sh
test-template-references.sh
test-templates-comprehensive.sh
test-todo-checker.sh
test-unified-codex-config.sh
test-zsh-monitor-safety.shFAQ
humanize is a Claude Code plugin with 6 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes ask-codex, ask-gemini, humanize-gen-plan. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. 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?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is humanize free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.