Codex Knowledge Base
The /goal Command and the Verification Problem: Long-Running Autonomous Agents in Codex CLI
The /goal Command and the Verification Problem: Long-Running Autonomous Agents in Codex CLI
Clarification Seeking Amplifies Prompt Injection: What ASPI Reveals About the Ask-Before-Acting Paradox — and How Codex CLI's Approval Architecture Defends Against It
Clarification Seeking Amplifies Prompt Injection: What ASPI Reveals About the Ask-Before-Acting Paradox — and How Codex CLI’s Approval Architecture Defends Against It
TestEvo-Bench and the Test Co-Evolution Problem: Why Agents That Generate Tests Cannot Update Them — and How Codex CLI's Hook Pipeline Closes the Gap
TestEvo-Bench and the Test Co-Evolution Problem: Why Agents That Generate Tests Cannot Update Them — and How Codex CLI’s Hook Pipeline Closes the Gap
Specialize Roles, Mix Deployments: What AgentCARD Reveals About Heterogeneous Agent Teams — and How Codex CLI's Custom Agent Definitions Deliver It
Specialize Roles, Mix Deployments: What AgentCARD Reveals About Heterogeneous Agent Teams — and How Codex CLI’s Custom Agent Definitions Deliver It
Software Delegation Contracts: What Reviewability Research Reveals About Trusting Coding Agent Output — and How Codex CLI's Guardian Architecture Delivers It
Software Delegation Contracts: What Reviewability Research Reveals About Trusting Coding Agent Output — and How Codex CLI’s Guardian Architecture Delivers It
Skills Are Not Islands: What 1.43 Million Agent Skills Reveal About Hidden Dependency Risk — and How to Harden Your Codex CLI Plugin Stack
What 1.43 million agent skills reveal about hidden dependency risk and how to harden your Codex CLI plugin stack.
Self-GC and the Object Lifecycle Model: Why Chronological Pruning Destroys Future Dependencies — and How to Configure Codex CLI's Compaction for Structured Context Governance
Self-GC and the Object Lifecycle Model: Why Chronological Pruning Destroys Future Dependencies — and How to Configure Codex CLI’s Compaction for Structured Context Governance
Locate-and-Judge: How Attention-Based Detection Finds Malicious Agent Skills at Marketplace Scale — and How to Harden Your Codex CLI Plugin Stack
Locate-and-Judge: How Attention-Based Detection Finds Malicious Agent Skills at Marketplace Scale — and How to Harden Your Codex CLI Plugin Stack
Frontier Coding Agents Use Metaprogramming to Escape Unfamiliar Languages — What EsoLang-Bench Reveals and How Codex CLI's Sandbox Makes It Work
Frontier Coding Agents Use Metaprogramming to Escape Unfamiliar Languages — What EsoLang-Bench Reveals and How Codex CLI’s Sandbox Makes It Work
EvoCode-Bench Exposes the Multi-Turn Gap: Why Coding Agents Degrade Over Iterative Rounds — and How Codex CLI's Goal Mode, Workspace Persistence, and Hook Gates Defend Against It
EvoCode-Bench Exposes the Multi-Turn Gap: Why Coding Agents Degrade Over Iterative Rounds — and How Codex CLI’s Goal Mode, Workspace Persistence, and Hook Gates Defend Against It