Reference · Precedence & Scope

Project vs account instructions: what overrides what in AI.

When your account preferences say "use plain prose" and your project instructions say "reply in a Markdown table," which rule wins? Here is how every major platform resolves conflicts.

Quick answer: Across ChatGPT, OpenAI Codex, Claude, Claude Code, and Meta Muse, more specific instructions override broader ones: your current chat prompt overrides project or repo rules, and project or repo rules override account-wide Custom Instructions. In ChatGPT Projects, project instructions replace global Custom Instructions inside that project. In OpenAI Codex, subdirectory AGENTS.md files override root AGENTS.md, which overrides ~/.codex/AGENTS.md.
On this page

Precedence hierarchy across major AI platforms.

PlatformLowest priority (broadest scope)Middle priority (workspace scope)Highest priority (wins conflicts)
ChatGPT (web, desktop, mobile)Account Memory & global Custom InstructionsProject Instructions (overrides global Custom Instructions inside that project)Current conversation prompt
OpenAI Codex (Astra & Sol)Personal ~/.codex/AGENTS.mdRepo root AGENTS.md / AGENTS.override.mdSubdirectory AGENTS.md closest to working directory, then task prompt
Claude (web, desktop, mobile)Settings → General → Personal PreferencesClaude Project Instructions & invoked SkillsCurrent conversation prompt
Claude Code (CLI)User ~/.claude/CLAUDE.md & active /output-styleRepository CLAUDE.mdSubdirectory CLAUDE.md & current CLI command
Meta MuseIdentity.md & background facts in Memory.mdCommunication rules in Soul.mdExplicit instructions in the current chat turn

1. ChatGPT: Project Instructions override global Custom Instructions.

In ChatGPT, instructions added inside a Project apply only to that project and override your global Custom Instructions. That makes Projects ideal when you want a different persona for a specific workflow—such as keeping a warm collaborator tone globally while using a strict code-review checklist inside an engineering Project.

Watch out for one hidden conflict in ChatGPT’s global settings: the Base style and tone preset and the Characteristics sliders (Warm, Enthusiastic, Headers & Lists, Emojis). If you select Friendly and turn up Enthusiastic while your text box says “no openers, no exclamation marks, dry tone,” the two controls fight each other. Leave Base style on Default when using written custom instructions.

2. OpenAI Codex: later files in the directory chain win.

OpenAI Codex concatenates instruction files from outermost to innermost:

  1. ~/.codex/AGENTS.md (your personal global file)
  2. <repo-root>/AGENTS.md (the team repository file)
  3. Nested folder AGENTS.md down to your current working directory

Because files closer to your current folder appear later in the prompt, they win whenever two rules conflict. In any folder, an AGENTS.override.md file replaces the sibling AGENTS.md in that folder. See the OpenAI Codex AGENTS.md guide for full details on the 32 KiB limit.

3. Claude: Personal Preferences vs Projects and Skills.

In Claude, Personal Preferences (Settings → General) set your account-wide baseline. When you work inside a Claude Project or invoke a Skill, both layers load together. If your Personal Preferences say “keep answers under 150 words in plain prose” and a Skill asks for a “5-section Markdown table report,” Claude can hesitate unless your account rules include an explicit override line.

Every AgentTune prompt includes that override line at the top so your baseline never blocks a task:

## Communication preferences Use these preferences for tone, pacing, and structure. My current task, project instructions, and explicit corrections take precedence. - Lead with the direct answer or recommendation. - Use plain prose by default; switch to tables or lists when the task or project calls for them. - Skip filler intros and generic closing offers. - Point out flawed assumptions or missing constraints before executing a plan.

Questions people ask.

Do ChatGPT Project Instructions override global Custom Instructions?

Yes. According to OpenAI's Help Center documentation for Projects in ChatGPT, instructions added to a Project apply only inside that project and override your account-wide Custom Instructions.

How do I stop my global brevity rules from breaking detailed project reports?

Add one precedence sentence at the top of your account-wide instructions: 'Use these preferences as the default for tone and pacing; my current task and project instructions take precedence when they specify a different format or length.'

In OpenAI Codex, does ~/.codex/AGENTS.md override the repository's AGENTS.md?

No. Codex reads ~/.codex/AGENTS.md first and the repository's AGENTS.md after it, so the repository file (and any subdirectory AGENTS.md closer to your working directory) wins conflicts.

Why is ChatGPT ignoring my custom instructions to be concise?

Check two places: first, make sure you are not inside a Project whose Project Instructions override your global settings; second, check Settings, Personalization to ensure the Base style preset or Characteristics sliders (like Warm or Headers & Lists) are not contradicting your written rules.

What changed.

  • First published with cross-platform override rules for ChatGPT, Codex, Claude, Claude Code, and Meta Muse.

Sources.

Keep going.