codex▌

Create, repair, validate, preview, and package Codex-compatible animated pets and pet spritesheets from character art.

Multi-agent orchestration layer for Codex CLI with 30 specialized agents and 40+ workflow skills. \n \n Includes 30 role-based agents across development, QA, domain expertise, and product strategy tiers; trigger via /prompts:role or workflow skills like $autopilot , $ralph , $team , and $code-review \n Supports parallel team execution in tmux with staged pipeline execution (plan → PRD → exec → verify → fix) and persistent MCP servers for state, memory, and code intelligence \n Offers workflow sk

Use OpenAI Codex CLI as a read-only oracle — planning, review, and analysis only. Codex provides its perspective; you synthesize and present results to the user.

Spawn autonomous subagents to offload context-heavy work and preserve parent token budget. \n \n Subagents burn their own tokens and return only final results, ideal for deep research (3+ searches), codebase exploration (8+ files), multi-step workflows, and long-running operations \n Choose between mini model (gpt-5.1-codex-mini) for pure search tasks or inherit parent model for multi-step analysis, refactoring, and generation work \n Supports up to 5 parallel subagents via background shell exec

Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

Cross-model validation using the codex binary directly. Claude writes code, Codex reviews it — different architecture, different training distribution, no self-approval bias.

### verify-ui - Check a UI change in a real browser before calling it done. - Starts or finds the dev server, opens the changed pages, takes screenshots at phone and desktop widths in light and dark mode, reads console errors, and looks for layout bugs that typecheck and curl miss. - Use after any change to pages, components, or styles, or when the user says "check it visually", "screenshot it", "does it look right", or "verify the UI".

### ux-review - Review a flow, screen, or piece of product copy from the user's point of view. - Checks orientation, next steps, friction, error recovery, and leaked internal details, then rewrites the copy in plain words. - Use when the user asks to improve UX, review a flow, simplify onboarding, write button or error copy, reduce friction, or asks "is this confusing".

### ste100 - Write or rewrite prose in ASD-STE100 Simplified Technical English (Issue 9) and remove AI slop. - Applies the countable STE rules (20-word procedure sentences, 25-word descriptive sentences, 6-sentence paragraphs, active voice, allowed verb forms, 3-word noun clusters, one instruction per sentence, condition before command), then a slop check built from Wikipedia's "Signs of AI writing" list, then an optional linter. - Use for docs, READMEs, runbooks, instructions, error messages, UI copy, incident reports, release notes, agent prompts and skill files, or when the user says "STE", "STE100", "ASD-STE100", "plain English", "simplify", "too wordy", "cut the fluff", "de-slop", "sounds like AI", or "make it human".

### social - Write X posts, X threads, and LinkedIn posts with a clear point of view, in the user's own voice. - Names the subject in the first line, takes a debatable side on ideas (never on people), backs it with sourced facts, keeps links in the first reply, and scores each draft before offering it. - Use when the user asks to write, draft, or plan posts for X, Twitter, or LinkedIn, or to turn a blog post, launch, or news story into social posts.