codejunkie99/tokensavings-pro

Latest recorded source activity: August 31, 2026 at 11:28

SkillsMP catalog refreshed: October 29, 2026 at 18:30

skills collected: 1

GitHub stars: 21
GitHub forks: 2

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/codejunkie99/tokensavings-pro.

Repository README

Repository README source: README.md

Read the source README

Expand full README

# Dual Mode loop + slash command Luna executes. Sol reasons. The packet is the bridge. This is the Luna + Sol dual-model loop as a reusable Codex skill and a copy-paste ChatGPT prompt. The goal: stretch your Codex quota by never sending the whole repo to Sol, and never letting Luna invent architecture. ## Install as a Codex skill (macOS/Linux) ```bash mkdir -p ~/.codex/skills cp -R dualmode ~/.codex/skills/dualmode ``` Then restart Codex and invoke: - `$dualmode` or `/dualmode` to load the skill. - The skill's `references/loop-prompt.md` is the raw prompt to paste into a plain ChatGPT conversation if you're not in Codex. The packet template (`references/task-packet.md`) and a filled example (`references/example-packet.md`) show exactly what Sol receives, so the loop does not depend on guessing. ## Quota receipt The "20x" figure is official only for **Pro 20x vs Plus on GPT-5.6 Luna**: 5,000-40,000 vs 250-2,000 messages per 5h. Source: https://learn.chatgpt.com/codex/pricing ## License MIT. See [LICENSE](LICENSE).

Loading the repository README…

Skills in this repository

Software Developers

1 occupation category · 100% classified

skill

occupation

description

updated

dualmode

Software Developers

Run the Luna execution + Sol reasoning dual-model loop. Use when the user invokes $dualmode or /dualmode, asks to set up Luna + Sol handoffs, wants to split reasoning from execution to stretch Codex quota, or asks for the task packet loop. Resident in Codex…

2026-08-31

Showing 1 of 1 collected skill.