codex-fleet
Standalone Codex CLI runner + fleet orchestrator. Does THREE things and always EXECUTES them (never just describes): (1) general code tasks via `codex exec`, (2) high-quality image generation via Codex's built-in `gpt-image-2` tool, and (3) parallel multi-lane fleets — spawning many `codex exec` delegates at once with worktree isolation. Defaults locked: model `gpt-5.6-sol`, reasoning `high`, `--skip-git-repo-check` always. For multiple independent jobs, fire them ALL in parallel — compute is not the constraint, throughput is. Triggers on: "use codex", "run codex", "codex exec", "imagegen", "generate image", "make image", "render this", "ask codex to ...", "have codex ...", "spawn a fleet", "parallel codex", any image-asset request (icons/sigils/banners/portraits/backgrounds/sprites/UI assets/mockups/photoreal/etc.), and any request to delegate code-level work to Codex.
avenoxai · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add avenoxai/avenoxskills --skill codex-fleet技能说明
name: codex-fleet
description: Standalone Codex CLI runner + fleet orchestrator. Does THREE things and always EXECUTES them (never just describes): (1) general code tasks via codex exec, (2) high-quality image generation via Codex's built-in gpt-image-2 tool, and (3) parallel multi-lane fleets — spawning many codex exec delegates at once with worktree isolation. Defaults locked: model gpt-5.6-sol, reasoning high, --skip-git-repo-check always. For multiple independent jobs, fire them ALL in parallel — compute is not the constraint, throughput is. Triggers on: "use codex", "run codex", "codex exec", "imagegen", "generate image", "make image", "render this", "ask codex to ...", "have codex ...", "spawn a fleet", "parallel codex", any image-asset request (icons/sigils/banners/portraits/backgrounds/sprites/UI assets/mockups/photoreal/etc.), and any request to delegate code-level work to Codex.
Codex Fleet — Standalone Action Runner
A single self-contained skill for driving the Codex CLI from any agent (Claude Code, Cursor, or your own harness). No external control plane required — everything here runs against a plain local
codexinstall. Drop this file into.claude/skills/codex-fleet/SKILL.md(or your agent's skills dir) and go.Built and battle-tested by Avenox. Share freely.
This skill does three things and ALWAYS executes them, never describes them:
- General Codex CLI tasks — code review, refactor, multi-file edits, analysis, diagnosis, anything you'd hand to a peer-AI for parallel processing.
- Image generation — real rendered images via Codex's built-in
gpt-image-2tool: backgrounds, portraits, icons, sigils, banners, UI assets, sprites, mockups, photoreal, infographics. - Fleets — spawning many
codex execdelegates in parallel (one lane or twenty), with worktree isolation for concurrent write lanes.
CRITICAL: This is an ACTION skill, not commentary
When invoked you MUST:
- Actually invoke
codex execvia the Bash tool. Never write instructions for the user to run themselves. - Default to background execution (
run_in_background: true) for any task likely to take >10s. This lets the main agent continue other work in parallel while Codex runs. The harness notifies on completion. - For multiple independent jobs, fire them ALL in parallel. Codex sessions don't contend. Compute is not the bottleneck — throughput is. If the user asks for 4 images or 3 codex investigations, that's 4 or 3 simultaneous Bash calls in one message, all
run_in_background: true. - Summarize results from logs after each background job completes — don't dump raw stdout unless asked.
If the user's request is "use codex to X" or "run codex on X", run codex exec ... "X". Don't wrap, don't paraphrase, don't ask "should I proceed" — just go.
Prerequisites
- Codex CLI 0.128+ installed and authenticated (
codex --version). Reasoning tierslow/medium/high/xhighrequire 0.128+. - For the image-gen CLI fallback and
gpt-image-1.5transparency path only:OPENAI_API_KEY. The built-inimage_gentool uses your Codex subscription and needs no key.
Defaults (locked in)
| Setting | Value | When to override |
|---|---|---|
| Model | gpt-5.6-sol | -m <model> only if user specifies |
| Reasoning effort | high | xhigh ONLY on explicit user request ("use xhigh", "max reasoning", "deep"); medium/low for cheap mechanical lanes |
| Service tier | standard — fast is OFF | see the note below; opt in per-call only |
| Sandbox | read-only | workspace-write for edits; danger-full-access for image gen or network (ask first) |
--skip-git-repo-check | always | always |
| Stderr | suppressed (2>/dev/null) | only show when debugging |
--color never | recommended | when you need to grep stdout cleanly |
Reasoning levels available (codex 0.128+): low, medium, high, xhigh. Lean toward high. Don't downgrade to "save effort" unless the lane is genuinely mechanical.
Fast tier is OFF by default — do not add it.
-c service_tier=fast -c fast_default_opt_out=falsebuys ~1.5× speed at ~2.5× rate cost. That trade is wrong for how this skill is used: everything here is background-first and parallel, so nobody is staring at a single lane's latency, and burning 2.5× rate on twenty lanes drains your limits for no wall-clock gain. Standard tier gives you the same quality plus rate-limit headroom. Every example in this file omits it deliberately. Opt in per-call only when a human is actively blocked on one foreground result — never for fleets, never as a global default.
Part 1 — General Codex Tasks
Base command
codex exec --skip-git-repo-check \
-m gpt-5.6-sol \
-c model_reasoning_effort=high \
--sandbox read-only \
"<PROMPT>" 2>/dev/null
Sandbox quick reference
| Use case | Flags |
|---|---|
| Read-only review / analysis / diagnosis (default) | --sandbox read-only |
| Apply local edits | --sandbox workspace-write --full-auto |
| Network access or broad system access | --sandbox danger-full-access --full-auto (confirm with user first) |
For a working dir other than CWD: add -C <DIR>.
For escalated reasoning: replace model_reasoning_effort=high with =xhigh.
Background-first invocation pattern
Run any non-trivial codex task in the background. Don't block the main thread:
Bash tool call:
command: codex exec --skip-git-repo-check -m gpt-5.6-sol \
-c model_reasoning_effort=high \
--sandbox read-only \
"Review src/foo.ts for race conditions and report findings." 2>/dev/null
run_in_background: true
Then continue other work. When the background notification fires, read the log/output and summarize.
For tasks where you genuinely need the result before doing anything else (rare), run foreground.
Parallelization (the default for multiple jobs)
If t
阅读完整来源 ↗