Global-mindee

65 mods across 1 repository, 11 stars between them.

full-loop

01

Global-mindee/WAY

Skill Claude CodeCodex

An eight-step workflow that turns a natural-language request into a plan, optional market research, approved implementation, independent review, and stored lessons. It is designed for large, multi-step tasks or unattended work.

11 1mo ago A 116 tokens original MIT

loop-critic

02

Global-mindee/WAY

Agent Claude Code

A read-only reviewer that judges whether a software work plan is clear and ready to execute. It returns either OKAY or REJECT after checking clarity, testability, completeness, risks, and alternatives.

11 1mo ago A 79 tokens original MIT

loop-executor

03

Global-mindee/WAY

Agent Claude Code

An execution agent for a full-loop software delivery process, following an approved plan and its acceptance criteria. Acceptance criteria are the specific conditions used to decide whether the work is complete.

11 1mo ago A 55 tokens original MIT

loop-planner

04

Global-mindee/WAY

Agent Claude Code

A planning agent for a full-loop software workflow. It creates a detailed implementation plan with context, available resources, acceptance checks, risks, and verification steps.

11 1mo ago A 65 tokens original MIT

loop-reviewer-spec

05

Global-mindee/WAY

Agent Claude Code

An independent review agent for checking whether a full-loop pipeline met its acceptance checklist.

11 1mo ago A 54 tokens original MIT

Global-mindee/WAY

Agent Claude Code

A verification agent for a full-loop development process that checks acceptance criteria by running their listed commands and examining the results.

11 1mo ago A 49 tokens original MIT

UserPromptSubmit

07

Global-mindee/WAY

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing skill-keyword-injector.js and svop-injector.js via node (2 commands). From Global-mindee/WAY.

11 1mo ago A tokens not measured copy · 39% MIT

SessionStart

08

Global-mindee/WAY

Hook Claude Code

Runs when a session starts, executing session-start-scan.js via node. From Global-mindee/WAY.

11 1mo ago A tokens not measured copy · 45% MIT

Stop

09

Global-mindee/WAY

Hook Claude Code

Runs when the agent finishes a response, executing context-usage-monitor.js, full-loop-driver.js and svop-auditor.js via node (3 commands). From Global-mindee/WAY.

11 1mo ago A tokens not measured copy · 47% MIT

PreCompact

10

Global-mindee/WAY

Hook Claude Code

Runs before the context is compacted, executing context-usage-monitor.js via node with --precompact. From Global-mindee/WAY.

11 1mo ago A tokens not measured original MIT

PreToolUse

11

Global-mindee/WAY

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing external-impact-guard.js via node. From Global-mindee/WAY.

11 1mo ago A tokens not measured copy · 52% MIT

WAY

12

Global-mindee/WAY

Settings file Claude Code

Agent settings declaring 5 hook events (UserPromptSubmit, SessionStart, Stop, PreCompact).

11 1mo ago A tokens not measured original MIT

sde-extractor

13

Global-mindee/WAY

Skill Claude CodeCodex

An onboarding tool that analyzes stored conversation, account, Git, and shell data to draft a user's self-description.

11 1mo ago A 100 tokens original MIT

WAY AGENTS.md

14

Global-mindee/WAY

Instructions file CodexOpenCode

A repository instruction file that points coding agents to the main CLAUDE.md file for their rules and working procedures. AGENTS.md is an open standard pointer used so different tools can find the same instructions.

11 1mo ago A 135 tokens original MIT

WAY CLAUDE.md

15

Global-mindee/WAY

Instructions file

A Korean-language operating guide for W.A.Y?, an AI collaboration system for a solo operator's work and personal business.

11 1mo ago A 6,426 tokens original MIT

INDEX

16

Global-mindee/WAY

Agent

Agent "INDEX" from Global-mindee/WAY, covering agents/index.md — 활성 agents 의미론적 매칭 인덱스, 사용법 (usage-guide.md 참조), 카테고리 요약, 01dev-workflow (5) and 02research (3).

11 1mo ago A 0 tokens original MIT

USAGE-GUIDE

17

Global-mindee/WAY

Agent

An instruction guide that tells an AI agent how to choose and run the most relevant specialized agent for a user's request.

11 1mo ago A 0 tokens original MIT

ab-test-setup

18

Global-mindee/WAY

Skill Claude CodeCodex

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test…

11 1mo ago A 171 tokens copy · 100% MIT

accessibility-wcag

19

Global-mindee/WAY

Skill Claude CodeCodex

Web accessibility patterns for WCAG 2.2 compliance including ARIA, keyboard navigation, screen readers, and testing.

11 1mo ago A 29 tokens original MIT

ai-slop-cleaner

20

Global-mindee/WAY

Skill Claude CodeCodex

A code-cleanup workflow for removing unnecessary or repeated code produced by AI, while preserving the existing behavior. It can also perform a review-only cleanup pass.

11 1mo ago A 80 tokens original MIT

analytics-tracking

21

Global-mindee/WAY

Skill Claude CodeCodex

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…

11 1mo ago A 134 tokens copy · 88% MIT

api-design-patterns

22

Global-mindee/WAY

Skill Claude CodeCodex

REST API design with resource naming, pagination, versioning, and OpenAPI spec generation.

11 1mo ago A 22 tokens original MIT

ci-cd-pipelines

23

Global-mindee/WAY

Skill Claude CodeCodex

CI/CD pipeline patterns for GitHub Actions, GitLab CI, testing strategies, and deployment automation.

11 1mo ago A 25 tokens original MIT

content-strategy

24

Global-mindee/WAY

Skill Claude CodeCodex

When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content…

11 1mo ago A 144 tokens copy · 91% MIT