Lucas Althoff

Computer science doctoral student - Projecting experiments to understand the impacts of immersive technologies. Studying until some big solution pop-up.

[Rahul @sairahul1]

How to use both Claude Fable 5 and GPT-5.6 all day without hitting limits.

Most people don't know you can run both inside the same session.

Fable 5 as the orchestrator. GPT-5.6 as the executor. 10 subagents working in parallel.

This setup saves at least 60% of your Fable 5 token consumption — and you never hit the 5-hour limit again.

You only need to set it up once. Here's exactly how:

━━━━━━━━━━━━━━━━━━━━━━━━━━
STEP 1 — Install the Codex plugin inside Claude Code

Run these three commands:

/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins

━━━━━━━━━━━━━━━━━━━━━━━━━━
STEP 2 — Tell Fable 5 to finish the setup

Paste this prompt into Claude Code:

"Set up Codex inside this Claude Code environment. Use the official OpenAI Codex plugin that was just installed. Run /codex:setup. If Codex CLI is missing, install it. If Codex is installed but not authenticated, ask me to authenticate with my ChatGPT account. After auth is complete, verify that Codex works from inside Claude Code. Then confirm that the codex:codex-rescue sub-agent is available. Do not change any project code during setup."

━━━━━━━━━━━━━━━━━━━━━━━━━━
STEP 3 — Authenticate once

Fable 5 will trigger the Codex setup automatically.

You authenticate your ChatGPT or Codex account once.

After that, Codex runs from inside Claude Code using your existing Codex subscription — no extra cost, no extra setup.

━━━━━━━━━━━━━━━━━━━━━━━━━━
STEP 4 — Tell Fable 5 how to delegate work

Paste this prompt:

"From now on, use this workflow:

You are the orchestrator.

Use Fable 5 for planning, repo understanding, architecture decisions, task decomposition, and final review.

Use codex-rescue as the executor when a task needs heavy implementation, debugging, test fixing, refactoring, or multi-file code edits.

When delegating to Codex, use /codex:rescue.

Prefer GPT-5.6 Sol medium as the daily driver for implementation tasks.

Keep Codex tasks focused and specific.

After Codex finishes, inspect the result yourself before accepting it.

Do not blindly trust Codex output."

━━━━━━━━━━━━━━━━━━━━━━━━━━
WHICH GPT-5.6 MODEL TO USE AND WHEN

This is where most people leave money on the table. Not all GPT-5.6 tiers are equal.

GPT-5.6 Sol medium → your daily driver

DeepSWE score: 61. Cost: $1.86. Fewer steps than almost every other model on the benchmark. This is the model doing 80% of the execution work in this setup. Fast, cheap, accurate enough for most implementation tasks.

GPT-5.6 Sol extra high → planning and orchestration

DeepSWE score: 71. Cost: $4.70. Use this when the task needs serious reasoning — architecture decisions, task decomposition, complex debugging. Scores higher than Fable 5 extra high (70) at less than a third of the cost ($13.41 vs $4.70). This is the model that replaced Fable 5 as my planning layer.

GPT-5.6 Terra/Luna → pure execution

Fast. Cheap. No overthinking. Once the plan is locked, this is what runs it. Extremely fast execution, minimal bugs, high quality output on well-defined tasks.

━━━━━━━━━━━━━━━━━━━━━━━━━━
THE ULTIMATE PLAN: 3-MODEL WORKFLOW

If you want maximum output quality at minimum cost, this is the setup:

Step 1 → Plan with GPT-5.6 Sol extra high
Full task/session/project planning. Architecture. Decomposition. Edge cases.

Step 2 → Critique with Fable 5 high
Find loopholes. Patch loose ends. Challenge assumptions. Fable 5 is at its best here — pure reasoning, no implementation cost.

Step 3 → Execute with GPT-5.6 Terra/Luna
Implement the battle-tested plan. Fast, clean, no waste.

TLDR:
Plan → GPT-5.6 extra high
Critique → Fable 5 high
Execute → GPT-5.6 Terra/Luna

The orchestrator thinks. The critic patches. The executor builds. You review.

━━━━━━━━━━━━━━━━━━━━━━━━━━
4 PRO TIPS TO NEVER HIT A LIMIT AGAIN

→ Tip 1: Turn this into a skill

Name it Fable-GPT. Call it at the start of every session. One command activates the entire workflow — no re-pasting prompts every time.

→ Tip 2: Use skill + goal for heavy tasks

Goals are best for long-horizon work. Set the goal, activate the skill, let the orchestrator-executor loop run until it's done. Check back when it surfaces for review.

→ Tip 3: Use subagents if you're on the Codex 20x Pro plan

Run 5 to 7 parallel subagents at once. With this setup, you will never hit the 5-hour limit. Each agent works independently on its assigned task while the others run in parallel.

→ Tip 4: Clear context after 4 compactions

Context rot is real. After 4 /compact cycles the conversation quality degrades. Use a /handoff skill before clearing to preserve the critical context — task state, decisions made, what's left to do. Start the new session by loading the handoff file.

━━━━━━━━━━━━━━━━━━━━━━━━━━
THE FULL PICTURE

Before this setup:
→ Fable 5 hits limits by midday
→ Heavy implementation burns your best tokens
→ You manually switch between tools
→ One model, one pace, one bill

After this setup:
→ GPT-5.6 Sol medium handles 80% of execution at $1.86/task
→ GPT-5.6 extra high outplans Fable 5 at 3x lower cost
→ 3-model critique loop catches every bug before it ships
→ 5 to 7 parallel subagents running simultaneously
→ 60%+ fewer Fable 5 tokens consumed
→ Never hit the 5-hour limit again

One setup. Runs forever.

Save this. Set it up tonight.

[Lucas Althoff @LucasAlthoff]

@marcelvanhattem Sua vergonha do Brasil parece começar pelo seu nome....

[Lucas Althoff @LucasAlthoff]

@GayerGus @elonmusk That is exactly what should be done. Why so afraid about the truth? Now that the coupmans are receiving feedback at their antisocial behavior you are all afraid. And should be!!

[Lucas Althoff @LucasAlthoff]

@elonmusk You are absolutely nazi

[Lucas Althoff @LucasAlthoff]

@monarkbanido @alexandre Monark abaixa a bola aí. Essa direita negacionista q vc representa é um nazismo vestido de liberal, vai ler e pare de twittar que vc faz mais bem ao país.

[Lucas Althoff @LucasAlthoff]

@elonmusk @realpfigueiredo Elon Musk defends free speech??? Or does he only defend that when it works in he's own interest??
Someone please tell him to take care of the issues from he's own country, Brazil do not need he's opinion...

[QoMEX 2025 @QoMEXconf]

📢 Special sessions at #QoMEX2024 have been selected.
⏰ Submit your full papers by February 9th, 2024 and short papers by April 12th, 2024.
🖱️ Click the link for more information: https://t.co/4Q3YGooV0p

[Lucas Althoff @LucasAlthoff]

Deliberately sharing this great work!

[Ana Serrano @DrAnaSerrano]

🌐 Join us at #ISMAR23 for "D-SAV360: A Multimodal VR Eye Gaze Dataset." 🚀 We've recorded and explored 4,609 gaze trajectories in dynamic 360° videos with directional sound recordings.

🔗 Link to the paper and dataset: https://t.co/lnDJeJt6vm

[Lucas Althoff @LucasAlthoff]

It is coming!

[Marta Orduna @martaRo__]

[SAVE THE DATE!]
📢 Join us for the #industry track of the @ACMIMX in Stockholm, Sweden, June 12-14, 2024

Explore the relevant topics covered by ACM IMX'24 👇
https://t.co/Z0HPdWLVsk

Gunilla Berndtsson @OskarJu @heloisacsp

[Marta Orduna @martaRo__]

It's the final countdown to our Emerging Telepresence Technologies for hybrid meetings: an interactive workshop at #CSCW2023 @ACM_CSCW 👉🏼https://t.co/pi5lRZRs30

[Mylene Farias @MyleneFarias]

Convido todos a se inscreverem para participarem do evento onde apresentaremos o Projeto Gigasistêmica da @unb_oficial , financiado FAPDF.
📷 Data: 06 de outubro de 2023
📷 Horário: 9h
📷 Local: Auditório Roberto Salmeron, Faculdade de Tecnologia (FT-UnB)

[Lucas Althoff @LucasAlthoff]

Awesome lab at Zaragoza, with exciting and successful researches is hiring

[Lucas Althoff @LucasAlthoff]

This research put some light into important aspects that I have for long time wondered about. Specifically, how does the age affects VR enjoyment?

[Stanford VR @StanfordVR]

Congrats to @RyanMooreComm for Best Paper Award at @NatComm who showed "how old" matters-VR's efficacy decreases as one moves into 80s & 90s. But decline is less than other media (i.e., phones). Thanks to @MyndVR for content & support! @SSRN @jeffhancock

https://t.co/6ntAYJR8c7

[Stanford VR @StanfordVR]

Congrats to @RyanMooreComm for Best Paper Award at @NatComm who showed "how old" matters-VR's efficacy decreases as one moves into 80s & 90s. But decline is less than other media (i.e., phones). Thanks to @MyndVR for content & support! @SSRN @jeffhancock

https://t.co/6ntAYJR8c7

[Stanford VR @StanfordVR]

Virtual experiences have real psychological impact.

VR-enhanced Behavioral Activation was as efficacious as traditional BA in treating depression. Both groups had a 4 point decrease in symptoms on PHQ-9.

Preprint of RCT by Margot Paul & @kbullock_kim. https://t.co/33QQNX3iaY

[Lucas Althoff @LucasAlthoff]

@SF_Moro Lave a boca pra falar isso de nosso presidente. Quando um governante quer fazer seu país crescer e distribuir a renda ele se posiciona globalmente, como Lula faz com grande habilidade. O senhor procura sempre contribuir com o atraso do Brasil, atrás de lucros pessoais.

[Lucas Althoff @LucasAlthoff]

@LulaOficial Parabéns presidente pelo seu trabalho, o Brasil volta a ser respeitado como deve ser e toda essa participação e dedicação sua trará impactos econômicos positivos para as próximas gerações, sem que rebaixe nosso país a lamber botas dos USA ou se vender para os sauditas.

[Lucas Althoff @LucasAlthoff]

@ashleyruba_phd It sounds that the basis of science (those who direct the scientific production) is profoundly biased into a white eurocentric cosmovision, though accurate, this result reveals one more time the fact that academy should be refreshed, and incorpore more facets.

[Lucas Althoff @LucasAlthoff]

@politicaaprendi @FlavioDino Que orgulho ter um ministro dedicado e compromissado com o avanço de nosso país!!

[Lucas Althoff @LucasAlthoff]

@Luciano45592426 @FlavioDino Para de defender criminosos