# Codex, Behind the Harness — Dominik Kundel, OpenAI

Source: [AI Engineer](https://www.youtube.com/watch?v=shRR1e2HXMk)  
Feed7 permalink: https://feed7.dev/p/codex-behind-the-harness-dominik-kundel-openai-04cntno  
Published: 2026-08-10T16:00:06.000Z  
Trust: Source Linked (source_linked)

## Why Included

Codex exposes several reusable harness patterns: deferred tools, persistent browser execution, sandboxed edits, automated permission review, WebSockets, and server-side compaction.

## Source Summary

Codex’s open-source Rust harness caps skill descriptions at **2% of the context window** and defers some tools until search finds them. Since **GPT-5.4**, deferred tool loading is also available through the Responses API.

## Practical Implication

For custom coding agents, borrow the boundaries rather than rebuilding every mechanism: persistent execution for browser scripts, apply-patch for edits, OS-specific sandboxes, read-only review agents for escalations, and server-side compaction for long runs.

## Agent-Ready Context

Codex’s open-source Rust harness caps skill descriptions at **2% of the context window** and defers some tools until search finds them. Since **GPT-5.4**, deferred tool loading is also available through the Responses API.

For custom coding agents, borrow the boundaries rather than rebuilding every mechanism: persistent execution for browser scripts, apply-patch for edits, OS-specific sandboxes, read-only review agents for escalations, and server-side compaction for long runs.

At **1,000 tokens per second**, GPT-5.3 Codex Spark made network round trips the bottleneck, motivating a persistent WebSocket mode. These details describe the current harness and API surface; both are expected to shift with later models.

## Connected Context

Feed7 judgment across 419 accumulated Signals:

This turns several broad harness recommendations into concrete Codex boundaries: budget skill discovery, defer tools, preserve execution, constrain edits with sandboxes and review, and compact server-side. It reinforces progressive loading, isolation, and long-run context controls in the candidates, while adding a latency consequence: once inference is extremely fast, connection architecture becomes part of agent performance. The mechanisms remain model- and API-version dependent.

- [Skills are new features: Building Skill-Centric Harness — Yogendra Miraje, FactSet](https://feed7.dev/p/skills-are-new-features-building-skill-centric-harness-yogendra-miraje-f-0lp4c7o) — FactSet frames progressive skill loading and sandboxed execution as governance requirements; Codex provides concrete implementations through a context budget, deferred discovery, OS sandboxes, and review escalation.
- [Evolution of agentic surfaces — Gagan Bhat & Isabella Kai He, Anthropic](https://feed7.dev/p/evolution-of-agentic-surfaces-gagan-bhat-isabella-kai-he-anthropic-0mtshqh) — Both show that harness behavior is coupled to model releases; Anthropic’s obsolete reset workaround is direct evidence for retesting Codex’s current compaction and loading choices as models change.
- [Anthropic's CCA Exam as a Field-Guide for Agentic Engineering — Frank Coyle, UC Berkeley](https://feed7.dev/p/anthropic-s-cca-exam-as-a-field-guide-for-agentic-engineering-frank-coyl-00nf896) — The candidate’s compaction, termination inspection, and constrained-agent guidance is reinforced by Codex’s server-side compaction and read-only review boundary.
- [Multiplayer agentic engineering — Arjun Singh, Superconductor](https://feed7.dev/p/multiplayer-agentic-engineering-arjun-singh-superconductor-01w4k91) — Superconductor’s isolated cloud sessions establish isolation as a team workflow requirement; Codex adds lower-level sandbox and permission-review mechanisms for enforcing that boundary.

## Context Map

- Layer: agent
- Domains: coding, security
- Topics: harness-engineering, context-engineering, sandboxing

## Uncertainty

- At **1,000 tokens per second**, GPT-5.3 Codex Spark made network round trips the bottleneck, motivating a persistent WebSocket mode. These details describe the current harness and API surface; both are expected to shift with later models.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.