codex-assets

Create, repair, validate, visually QA, and package Codex-compatible v2 animated pets from character art, generated images, company or prospect brand cues, or visual references. Use for any new Codex pet, custom mascot, non-pixel pet style, brand-inspired pet, existing-pet repair, or 8x11 spritesheet workflow requiring all 9 standard animation rows, 16 look directions, deterministic assembly, QA artifacts, and spriteVersionNumber 2 packaging.

Rewrite current branch into N semantic commits with a legacy backup branch and optional rebase onto origin/main.

Merge origin/main into current branch while preserving branch intent, context, and ownership decisions.

Chain branch onboarding, code-health, and non-test analysis into a branch-scoped remediation plan.

Summarize current branch diff from fork point with intent, scope, risks, and context for follow-on work.

Audit codebase architecture: module dependencies, layering, circular imports, ownership, and structural decay.

Assess tech debt and rank refactoring priorities, change pain, maintainability risks, and cleanup roadmap.

Read-only overall codebase health score across PR quality, architecture, tech debt, and tests.

Review existing code or diffs for design smells, decay risk, maintainability issues, and concrete fixes.

Diagnose and apply broad code-quality fixes across review, architecture, debt, and tests; ask before risky edits.

Review existing test suites for brittleness, mock abuse, slow tests, poor readability, and coverage gaps.

Run repo code-health checks: duplication, dead code, complexity, maintainability, coverage hotspots, diff summary.

Analyze predicates, paths, and pure regions to find behavior-preserving logic compression opportunities.

Reduce radon/xenon complexity while keeping non-test runtime LOC growth at or below zero.

Audit and minimally repair Markdown docs for broken links, stale paths, make targets, and SSOT rules.

End-to-end GitHub PR review-comment fix loop: fetch context, patch, validate, commit/push, reply, resolve.

Convert code/docs/papers/images into a knowledge graph, clustered HTML report, JSON, and audit output.

Create or extend pytest AST boundary tests from AGENTS import, layer, and runtime constraints.

Sync latest main into current branch with onboarding, safe merge, conflict resolution, and doc refresh.

Review deep UI/mode flag passing into domain or renderer internals; suggest strategy/boundary fixes.

Deletion-first non-test runtime code reduction; cluster equivalent logic and merge fragments without changing behavior.

Read all open GitHub issues and PRs for the active repo to reconstruct current project/work state.

Prepare and publish GitHub PRs from branch evidence with Korean brief, checklist gates, and approval-gated push/create.

Use local probe CLI first for deep codebase search, symbol tracing, architecture audit, or bug investigation.

Refresh branch-scoped docs and AGENTS from current diff, code evidence, and repo SSOT conventions.

Preflight current git/OMX state, then continue the user's attached in-flight task on the right branch context.

Document current code behavior as an As-Is baseline before refactor, spec drift checks, or cleanup.

Split a large dirty working tree into reviewable semantic local commits without rewriting existing history.

Compare paired _TOBE.md and _ASIS.md docs to identify code/spec drift and refactor scope.

Inventory TODO markers and newly added TODOs in the current diff for handoff or cleanup.

Use when answering Data Analytics or code-health questions about the snk2501o Sinokor stowage optimization repository, including repo risk, SPP benchmark evidence, TUI planning diagnostics, and source-backed onboarding context.

[OMX] Strict autonomous loop: $deep-interview -> $ralplan -> $ultragoal (+ $team if needed) -> $code-review -> $ultraqa

[OMX] Run a comprehensive code review

[OMX] Self-referential loop until task completion with architect verification

[OMX] Adversarial dynamic e2e QA workflow - generate hostile scenarios, test, verify, fix, report, and clean up

[OMX] Socratic deep interview with mathematical ambiguity gating before execution

[OMX] Setup and configure oh-my-codex using current CLI behavior

[OMX] Strategic planning with optional interview workflow

[OMX] Alias for $plan --consensus

[OMX] N coordinated agents on shared task list using tmux-based orchestration