codex-first

A routing policy for Claude Code that sends implementation, repair, exploration, rebasing, and pull-request work to the Codex command-line tool when its model rules allow it.

In plain words
What is it for?
It helps decide where coding and exploratory tasks should run, including when to use Codex-backed automatic review.
Why use it?
It separates planning and review from hands-on coding according to the active model and token-cost rules.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/steipete/agent-scripts/codex-first
Any agent
npx skills add steipete/agent-scripts --skill codex-first
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-scripts

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.04099
Opus 5 $0.00036 $0.02049
Sonnet 5 $0.00014 $0.00820
Haiku 4.5 $0.00007 $0.00410

Measured yesterday against content hash 51504085c21a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

codex-first scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

Or install the self-contained CLI via `curl -fsSL https://chatgpt.com/codex/install.sh | sh`, which needs no wrapper.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Or install the self-contained CLI via `curl -fsSL https://chatgpt.com/codex/install.sh | sh`, which needs no wrapper.
skills/codex-first/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex First

Hard gate

Autoreview exception: always prefer Codex-backed $autoreview, independent of ANTHROPIC_BASE_URL, router state, or harness. Reviewing a frozen bundle is not hands-on self-delegation. Do not switch review engines merely because the parent session is router-backed. This exception takes precedence over the gate below.

Private runtime override: invoke $codex-next before evaluating this gate when that skill is available. On Peter-managed Macs it may replace the generic model-family gate for both coding and exploratory/subagent work. Follow its resolved current-model decision; do not continue through the generic gate after it has selected an execution surface.

For direct hands-on delegation without a private override, use this skill only when the active agent is Claude Code and the session is running on a native Claude model.

Model check (primary). The point of the gate is model economics: Claude tokens are metered and expensive, so hands-on work moves to Codex; but if the session is already routed to a cheaper/other model, delegation gains nothing. Decide by the model the session actually runs on, not by the transport:

  1. Read the model id from the system prompt's environment section ("You are powered by the model …"). Router-wrapped ids may be opaque (claude-ccr-<hex>); the hex suffix is often ASCII — decode it (echo <hex> | xxd -r -p) to reveal the underlying route, e.g. Gorilla CCP/native-claude-fable-5.
  2. If the resolved model is a native Claude model (contains claude, fable, opus, sonnet, or haiku, including native-claude-* router routes): delegate hands-on work to Codex. This applies even when ANTHROPIC_BASE_URL is loopback or a local router (Gorilla Claw, Clawdex) — a router in front of a real Claude model is still expensive Claude.
  3. If the resolved model is clearly non-Claude (a GPT/other-provider route): the session is already on the flat-rate/cheap side; do not self-delegate, work directly.

Read the full file on GitHub · 277 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 277 lines · 72 tokens per session scan C 51504085c21a

Subscribe to this mod's changes

codex-first is a skill published in the GitHub repository steipete/agent-scripts (6,580 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 4,099 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens