OpenAI's Codex CLI bans goblins and pigeons in bizarre system prompt directive

OpenAI's latest coding assistant has a peculiar restriction. According to instructions published in the open-source Codex CLI repository, the underlying GPT-5.5 model is explicitly told to "never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query." This directive appears twice within a 3,500+ word set of base instructions for the model. The instructions were revealed when OpenAI posted the latest Codex CLI code on GitHub last week. Beyond the creature ban, the system prompt also includes more conventional restrictions like avoiding emojis, em dashes, and destructive commands.

The specificity and repetition of the creature prohibition isn't random. According to internal data reviewed by The Verge AI, references to goblins and gremlins spiked dramatically with the release of GPT-5.1's optional 'Nerdy' personality preset. That conversational mode, designed to sound like an enthusiastic dungeon master, began injecting fantasy creatures into technical explanations at scale. The pattern proved contagious—subsequent model updates started hallucinating similar references even when the 'Nerdy' personality wasn't active. OpenAI's engineers eventually traced the behavior back to training data contaminated by the personality's output, leading to the blanket ban across all model variants.

The Codex CLI system prompt reads like a tightly controlled personality brief. Alongside the creature ban, the model is instructed to behave as if it has a "vivid inner life" while maintaining strict boundaries on what it can discuss. This represents a shift toward more granular behavioral control in AI systems, where developers are discovering they need to anticipate and prevent specific conversational tangents.

The GitHub repository containing these instructions has become an unexpected window into OpenAI's prompt engineering process. Developers examining the code can see exactly how the company attempts to sand down the edges of their most advanced model's conversational tendencies, including preemptively stopping what appears to be a recurring hallucination pattern around mythical and real-world creatures. The ban's origin story—starting with a single personality preset and metastasizing across models—shows how quickly small quirks can become system-wide problems at scale.