avenoxskills skill
Eleven production skills: Codex fleets, code bundles for external review, video editing and a multi-chain explorer.
- 148 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Parallel Codex lanes run commands and write to worktrees.
- Exporting code to an external chat sends source: rely on the secret scan but review the bundle.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/avenoxskillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Parallel Codex lanes run commands and write to worktrees.
- Exporting code to an external chat sends source: rely on the secret scan but review the bundle.
This is third-party code. Review the repository files before installing.
What it does
A skill set from the Avenox YouTube channel author. Agent operations: `codex-fleet` runs `codex exec` and parallel lanes in separate worktrees, `omp-fleet` does the same for the Oh My Pi CLI, `fable-orchestration` sets out what goes to cheaper sub-agents, and `limit` shows Claude and Codex usage windows. External review: `gptpro` packs a monorepo into zip bundles with a secret scan, and `gptpro-handoff` runs the workflow around the report. Video: `avenox-video`, `avenox-roughcut`, `avenox-graphics` and `avenox-thumbnail` form a local pipeline from raw take to thumbnail. Blockchain: `chainscan` reads data through the Etherscan V2 API and Foundry `cast`.
Who it is for. Developers and video creators who run several agents in parallel and want working recipes along with documented gotchas.
Good fit when
- A developer splits a big task into parallel Codex lanes isolated by worktrees.
- A team exports a monorepo for an external model to review without `node_modules` and keys.
- Before delegating, Claude and Codex usage windows must be compared.
- A creator cuts a raw take, removing pauses and retakes using the transcript.
- A researcher inspects a contract ABI and transactions across several chains.
Not a fit when
- You need one skill without shared folders: the video trio requires `avenox-studio/`.
- You work on Windows without WSL: some scripts target macOS and Linux.
- No Etherscan key or Codex subscription is available.
Example request
Show Claude and Codex usage windows, then split three tasks between Codex lanes and cheaper sub-agents.Limitations
Video skills target macOS (hardware encoding, `mlx-whisper`); Linux needs substitutes such as `libx264` and a CUDA whisper build. Thumbnails need your own mascot in `assets/`, and third-party tool logos are not shipped. `chainscan` needs an Etherscan V2 key, with Foundry fallbacks. Parallel Codex lanes write to worktrees and spend subscription limits, so set the lane count deliberately.
How to disable. Remove the copied skill folders from `~/.claude/skills/`. Clean up worktrees and video jobs under `STUDIO_JOBS` separately.
FAQ
Can I take a single skill?
Yes, copy the whole skill folder with `scripts/` and `references/`. The video trio also uses the shared `avenox-studio/` folder.
What does `limit` do?
It shows Claude and Codex usage windows on one screen and warns about stale data so the agent picks a pool before burning quota.
What does `gptpro` do?
It packs a monorepo into zip bundles by subsystem without `node_modules`. A detected key aborts the export.
Does the set work in Cursor?
The README lists Claude Code, Cursor and any harness that reads `SKILL.md` skills as compatible.
What is `fable-orchestration` for?
It sets a delegation policy: what stays with the main model, what goes to cheaper sub-agents and what goes to Codex lanes. Routing follows task difficulty.
Discussion
No questions or reviews yet.
Related
SkillsA catalog of nearly two hundred skills: code delivery, review, debugging, AI governance, product work and agent coordination.
A Codex skill collection: phased planning, parallel subagents, documentation access, a browser, 51 hooks and ready agent roles.
A collection of 14 portable skills for long agent runs: work planning, live app QA, search across past sessions and a phone call
A personal collection of about 130 Claude Code and Codex skills: media pipelines, Cloudflare, YouTube, design and task review
oh-my-codex
oh-my-codex (OMX)
A layer on top of Codex CLI: one flow from clarifying a task to verification, agent teams, hooks, a HUD and state in .omx/
Agents, skills and templates for structured AI development in OpenCode, Codex and Claude Code: docs, plans, review, checkpoints
README in short
The GOTCHAS sections collect bugs found in practice: an `auto-editor` range leak, Codex `-i` parsing, `omp` lane memory use and duplicate parallel image renders.