Soju06

25 mods across 2 repositories, 2.9k stars between them.

codex-review-loop

01

Soju06/codex-lb

Skill Claude CodeCodex

Adversarial PR code review using Codex CLI. Codex review (20-50 min) -> structured findings -> HITL approval -> fix loop.

2.9k yesterday A 36 tokens original MIT

openai-docs

02

Soju06/codex-lb

Skill Claude CodeCodex

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to…

2.9k yesterday A 74 tokens original MIT

Soju06/codex-lb

Skill Claude CodeCodex

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

2.9k yesterday A 31 tokens copy · 83% MIT

Soju06/codex-lb

Skill Claude CodeCodex

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

2.9k yesterday A 31 tokens copy · 88% MIT

Soju06/codex-lb

Skill Claude CodeCodex

Archive multiple completed changes at once. Use when archiving several parallel changes.

2.9k yesterday A 23 tokens copy · 100% MIT

Soju06/codex-lb

Skill Claude CodeCodex

OpenSpec context documentation policy: keep requirements in spec.md and capture narrative context in context/overview/rationale docs under openspec/specs. Use when creating or updating OpenSpec docs, spec context, or onboarding/guide documentation.

2.9k yesterday A 52 tokens original MIT

Soju06/codex-lb

Skill Claude CodeCodex

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

2.9k yesterday A 39 tokens copy · 77% MIT

openspec-explore

08

Soju06/codex-lb

Skill Claude CodeCodex

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

2.9k yesterday A 39 tokens copy · 92% MIT

openspec-ff-change

09

Soju06/codex-lb

Skill Claude CodeCodex

Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.

2.9k yesterday A 34 tokens copy · 100% MIT

openspec-new-change

10

Soju06/codex-lb

Skill Claude CodeCodex

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

2.9k yesterday A 40 tokens copy · 80% MIT

openspec-onboard

11

Soju06/codex-lb

Skill Claude CodeCodex

Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

2.9k yesterday A 26 tokens copy · 73% MIT

openspec-sync-specs

12

Soju06/codex-lb

Skill Claude CodeCodex

Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

2.9k yesterday A 38 tokens copy · 86% MIT

Soju06/codex-lb

Skill Claude CodeCodex

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

2.9k yesterday A 32 tokens copy · 75% MIT

project-conventions

14

Soju06/codex-lb

Skill Claude CodeCodex

Project code conventions reference. Covers typing, structure, DI, testing, and anti-pattern rules for module implementation.

2.9k yesterday A 27 tokens original MIT

Soju06/codex-lb

Skill Claude CodeCodex

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

2.9k yesterday A 58 tokens copy · 88% MIT

Soju06/codex-lb

Skill Claude CodeCodex

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…

2.9k yesterday A 67 tokens copy · 78% MIT

Soju06/codex-lb

Skill Claude CodeCodex

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

2.9k yesterday A 44 tokens copy · 100% MIT

codex-lb AGENTS.md

18

Soju06/codex-lb

Instructions file CodexOpenCode

Instructions for Soju06/codex-lb, covering agents, environment, code conventions, workflow (openspec-first) and how to work (default).

2.9k yesterday A 1,906 tokens original MIT

codex-lb CLAUDE.md

19

Soju06/codex-lb

Instructions file

Instructions for Soju06/codex-lb, a project described as: Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints.

2.9k yesterday A 3 tokens copy · 100% MIT

knowpatch

21

Soju06/knowpatch

Plugin Claude Code

LLM knowledge cutoff compensator — corrects outdated versions and deprecated APIs.

2 5mo ago A tokens not measured original MIT

knowpatch AGENTS.md

22

Soju06/knowpatch

Instructions file CodexOpenCode

Instructions for Soju06/knowpatch, covering knowpatch, environment, project context, code conventions (key points) and quality gate.

2 5mo ago A 630 tokens original MIT

knowpatch CLAUDE.md

23

Soju06/knowpatch

Instructions file

Instructions for Soju06/knowpatch, a project described as: LLM knowledge cutoff compensator for AI coding agents — corrects outdated versions, deprecated APIs, renamed packages, and removed CLI commands.

2 5mo ago A 3 tokens copy · 100% MIT

UserPromptSubmit

24

Soju06/knowpatch

Hook

Runs when you submit a prompt, before the agent sees it, executing detect.js via node. From Soju06/knowpatch.

2 5mo ago A tokens not measured copy · 86% MIT