blader

Arbitrage — AI skill for Claude Code

AI community

A Claude Code skill for token arbitrage: keep premium model tokens for judgment, dispatch all code-writing to codex.

How to install Arbitrage

This entry records only its repository, not the path inside it, so there is no exact command to give. Open blader/arbitrage and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Arbitrage does

A Claude Code skill for token arbitrage: keep premium model tokens for judgment, dispatch all code-writing to codex.

Alternatives in AI

Codeburn — Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Code 9.7k ★
Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★

README

Arbitrage

A skill for Claude Code that exploits the price gap between your premium model and your idle codex quota.

Frontier-model tokens are expensive, and most of them get spent typing code — the one part of the job a cheaper agent already does fine. Meanwhile your codex subscription sits there barely touched. This skill makes the expensive model act like it knows that: it keeps the judgment work (planning, specs, architecture, visual validation, diff review) and dispatches every line of implementation to codex running in the background.

Token arbitrage for agentic coding.

Install

**Claude Code**

git clone https://github.com/blader/arbitrage.git ~/.claude/skills/arbitrage

**Codex**

git clone https://github.com/blader/arbitrage.git ~/.codex/skills/arbitrage

Requires the codex CLI (`codex exec`) on your PATH.

How it works

Before any code gets written, the agent writes a spec: objective, constraints, acceptance criteria (the exact test command that must pass), and what not to touch. For frontend work the spec carries the design intent.
It dispatches implementation to codex in the background and keeps planning or validating in parallel instead of sitting and waiting.
The diff comes back. The agent reviews it, commits, and opens PRs from the main session. codex never touches git.
Frontend gets a visual validation loop: codex types the UI, the premium model runs the app, screenshots it, judges it against the design intent, and re-dispatches with concrete feedback until it looks right.

The escape hatch

The skill forbids predicting that codex will fail ("this is too hard for it"). Struggle has to be observed. But two strikes and it's over: if a re-dispatch with corrective feedback still misses the acceptance criteria, the premium model writes the code itself and salvages what it can from codex's diff.