Keep shared instructions in a reviewed, version-controlled source, deliver them using each tool's supported format, and test the result in a new task. Copying a file is only the delivery step: the useful outcome is that the next task applies the right instruction.
Which file should each tool use?
- Codex: uses
AGENTS.mdinstructions along its project path. More specific instructions and overrides can affect what it loads. - Claude Code: uses
CLAUDE.mdfor project instructions that a team can share through source control. - Cursor: supports
AGENTS.mdfor straightforward project guidance and.cursor/rulesfor more specific rules. Organization-level Team Rules are also available on its Team and Enterprise plans.
These mechanisms have different loading and scope rules. Keep tool-specific settings separate and check the official documentation linked below before changing an existing setup.
Start with one rule and one owner
In a disposable example project, write a small shared rule: “In this project's reports, write calendar dates as YYYY-MM-DD. Ask when a date is ambiguous.” Put the appropriate instruction in each tool's supported project file. Have one person review changes to the common rule together; do not overwrite an existing file or copy personal instructions into team guidance.
For a small team working in one repository, reviewed files in Git may be sufficient. Choose one authoritative source for shared text. If a script generates other files, label them as generated and review the source instead of editing both copies independently. Preserve each tool's required format and scope.
How do you know the instruction worked?
- Confirm the intended project and instruction version reached each tool.
- Start a separate task in that project. Ask for a report dated 14 September 2026 without repeating the formatting rule.
- Inspect whether the result uses
2026-09-14. Save the task and rule version as evidence. - Test an ambiguous date and a different project. Check that the tool asks for clarification and that project-specific guidance has not spread to the wrong scope.
This is a suggested verification exercise, not a benchmark or a claim about guaranteed model behavior. A loaded file and a correct later response are separate observations. If the check fails, inspect the actual loaded instructions, conflicting rules, project scope, and tool version before adding more text.
Where does OneMind fit?
OneMind helps teams maintain reviewed, versioned instructions and lessons across AI tools. Use a Mind for the guidance you want to maintain, make the intended Team or Project scope explicit, and review a proposed correction before distribution. Then verify its use in a later task.
The useful difference to evaluate is whether the review and maintenance workflow reduces repeated corrections for your team. A file-based setup may already meet your needs. OneMind does not guarantee that an AI model will follow every instruction; access controls and tests remain necessary.
Common questions
Does sharing instructions synchronize chat history? No. Project instruction files provide guidance; they do not by themselves transfer another tool's conversation history.
Should every tool receive identical files? Shared guidance can express the same rule, while wrappers, formats, personal preferences, and project scopes differ. Resolve conflicts deliberately instead of blindly copying everything.
What can I try first? Choose one recurring correction and one project. Open OneMind, check the available setup for your tool, and follow the correction through review, delivery, and a later task. OneMind supports desktop browsers and macOS. Check current pricing for the plan that fits your team.
Primary references
Tool behavior changes. Consult the current Codex instruction guide, Claude Code memory documentation, and Cursor rules documentation. This guide describes a workflow to evaluate, not a customer case study.