Effortlane — AI skill for Claude Code
Effortlane: open-source model and reasoning-effort routing for coding agents.
How to install Effortlane
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open itscloud0/effortlane and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Effortlane does
Effortlane: open-source model and reasoning-effort routing for coding agents. Native Codex auth, Shadow evaluation, cache-aware policy and local metrics. macOS; experimental Claude Code Shadow.
Alternatives in AI
- Codex Skill — by klaudworks - Enables users to prompt codex from claude code 914 ★
- My Free Code — Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming 633 ★
- MCP Web Scrape — 🚀 mcp-web-scrape — Clean, cache-aware web content fetcher for AI agents 42 ★
README
Effortlane
**Choose model and reasoning effort. Keep your native coding agent.**
Open-source LLM routing for Codex on macOS, with Shadow evaluation and local usage telemetry.
[](https://github.com/itscloud0/effortlane/actions/workflows/tests.yml) [](LICENSE)  
[**Try Shadow →**](#quick-start) · [See the evidence](#what-we-have-measured) · [How it works](#how-it-works) · [Get help](#help-build-effortlane)
What is Effortlane?
Effortlane is a local model and reasoning-effort router for coding agents. It selects from your authenticated Codex model catalog before a user turn, preserves native ChatGPT authentication, and records routing evidence locally. In **Shadow mode**, you keep the real executor and effort while Effortlane records what it would recommend.
The goal: **less subscription allowance per correctly completed task**. A cheap call that causes retries or rework is not a saving.
| What you get | Why it matters |
|---|---|
| Model and effort selection | Adjust reasoning depth as well as model capability |
| Shadow before Auto | Inspect recommendations before letting them change execution |
| Decisions between turns | Keep one executor through a turn's thoughts and tool calls |
| Native login and context | Continue using your existing Codex account and full executor context |
| Local evidence and recovery | Inspect routes, cache counters and failures; return to native Codex |
[!IMPORTANT] **Experimental. Subscription savi
Related Skills
LLM Evaluation Framework
Production-grade LLM Evaluation & Benchmarking Framework - GPT-4, Claude, Gemini, Mistral. Accuracy, latency,
Codex Model Router
Codex 多模型路由:在 Codex Desktop 使用 Claude、第三方 API 和自定义模型。Local LLM proxy for OpenAI Responses / Chat Completions &
Vibe Gauge
🧠 Native macOS menu-bar dashboard for AI coding: Claude / Codex / Gemini / Grok quotas with sleep-aware usage
VibeGauge
🧠 Native macOS menu-bar dashboard for AI coding: Claude / Codex / Gemini / Grok quotas with sleep-aware usage
Downshift
Deterministic open-source model router — right-sized LLMs per workload. Agent hooks, catalog policy, shadow mo
Continual Memory Policy Model
Experimental local-first memory-policy research for Codex and Claude Code, with delayed feedback and gated ada
Related Agents
Report Logger
Routes a completed /analyze-policy report to the right destination — local archive, GitHub issue, tracker DB,
Statistician
Statistical rigor advisor: experimental design, signal-vs-noise, pressure-testing metric claims, sample-size a
Econ Kotelnikov
Котельников" — Эконом токенов фабрики Зевс. Закладывает в новую систему механизмы токеносбережения: hash-cache