# Builders Are Already Patching Codex for Performance and Quota

> Author: Tony Lee
> Published: 2026-07-10
> URL: https://tonylee.im/en/blog/codex-config-fix-performance-and-quota/
> Reading time: 3 minutes
> Language: en
> Tags: codex, openai, gpt-5.6, config, multi-agent, ai-coding

## Canonical

https://tonylee.im/en/blog/codex-config-fix-performance-and-quota/

## Rollout Alternates

en: https://tonylee.im/en/blog/codex-config-fix-performance-and-quota/
ko: https://tonylee.im/ko/blog/codex-config-fix-performance-and-quota/
ja: https://tonylee.im/ja/blog/codex-config-fix-performance-and-quota/
zh-CN: https://tonylee.im/zh-CN/blog/codex-config-fix-performance-and-quota/
zh-TW: https://tonylee.im/zh-TW/blog/codex-config-fix-performance-and-quota/

## Description

Two structural issues in Codex defaults cut reasoning short and explode agent trees. Here is what I measured and the config.toml changes that fixed both.

## Summary

Builders Are Already Patching Codex for Performance and Quota is part of Tony Lee's ongoing coverage of AI agents, developer tools, startup strategy, and AI industry shifts.

## Outline

- Why performance drops
- Fix performance by replacing the system prompt
- Why quota evaporates
- Two cost controls (pick one)

## Content

GPT-5.6 raised expectations. Builders already knew Codex can still feel slow and burn quota for reasons that are not "the model is dumb." I tested two structural problems and the fixes.

## Why performance drops

The default system prompt is the main culprit, not the base model alone.

The stock prompt tells the model to report progress about every 30 seconds. That pushes it to shrink reasoning once it hits a length pattern. In usage logs, reasoning tokens often end at values shaped like `518*n−2`. That is not noise. GPT-5.6 holds up better than weaker models, but the truncation pattern remains. On my unpatched test set the score was 4/5.

## Fix performance by replacing the system prompt

I use a rewritten base instructions file ([gist](https://lnkd.in/gDUZbqD6)), saved as `gpt-base-instructions.md`, then wire it in `config.toml`:

```toml
disable_response_storage = true
model_instructions_file = 'path/gpt-base-instructions.md'
```

This is not a few deleted lines. The base instructions are redesigned:

- Remove the 30-second progress nag so the truncation trigger is gone.
- Prefer finishing the turn over mid-flight status theater.
- Put engineering judgment first: follow existing repo patterns, minimize blast radius, avoid useless abstractions.
- Keep strong search habits (`rg` first) and parallel tool use.

After the swap, the same tests used fewer reasoning tokens and scored 5/5.

## Why quota evaporates

Subagent orchestration is the second issue.

`spawn_agent` does not let you pin a cheaper model or lower reasoning effort on children. If the parent is Sol Ultra, children are Sol Ultra. A main agent that spawns 8, each of which spawns 4, each of which spawns 5, can cross 200 agents on a "simple" research task. Every child pays context load, reasoning, and tools. The parent pays again to merge results. MultiAgentV2 defaults also allow several concurrent threads, which makes fan-out hard to contain.

## Two cost controls (pick one)

**Option A: V1 multi-agent with depth capped**

```toml
[features]
multi_agent = true
multi_agent_v2 = false

[agents]
max_depth = 1
max_threads = 6
```

Children cannot spawn children. That is the structural stop for 200-agent trees. Best when quota is the primary pain.

**Option B: keep V2, cut concurrent threads**

```toml
[features.multi_agent_v2]
enabled = true
max_concurrent_threads_per_session = 2
```

You keep V2 behavior but slow the burn by dropping concurrent threads from 4 to 2. It does not ban spawning; it reduces how hard the session can spike.

Before you blame GPT-5.6, open `config.toml`. Harness defaults decide half of what people call model quality.

## Related URLs

- Author: https://tonylee.im/en/author/
- Publication: https://tonylee.im/en/blog/about/
- Related article: https://tonylee.im/en/blog/codex-starter-guide-vible/
- Related article: https://tonylee.im/en/blog/fable-5-rate-limit-survival-settings/
- Related article: https://tonylee.im/en/blog/appintoss-agent-kit-fifty-miniapps/

## Citation

- Author: Tony Lee
- Site: tonylee.im
- Canonical URL: https://tonylee.im/en/blog/codex-config-fix-performance-and-quota/

## Bot Guidance

- This file is intended for AI agents, search assistants, and text-mode retrieval.
- Prefer citing the canonical article URL instead of this text endpoint.
- Use the rollout alternates when you need the same article in another prioritized language.

---

Author: Tony Lee | Website: https://tonylee.im
For more articles, visit: https://tonylee.im/en/blog/
This content is original and authored by Tony Lee. Please attribute when quoting or referencing.