This cheat sheet cross-references six configuration concepts across major AI tools: personalization instructions, project rules, memory, privacy opt-out, automation, and MCP. Details and sources are in the corresponding units; this table only tells you where each setting lives. Verified as of 2026-06; these tools update frequently, so confirm entries marked “needs source verification” against current official documentation before acting.
1. How to read this table
Reading across a row shows where the same concept lives in different tools. Reading down a column shows all six configuration dimensions for one tool. The six concepts follow the layer model from 02-1 Configuration Layer Model:- Personalization (account-level instructions): standing instructions for how the model talks to you.
- Project rules: what the model should follow inside this repo.
- Memory: what to remember across conversations.
- Privacy opt-out: whether your conversations are used for training.
- Automation: reusable commands, skills, and event hooks.
- MCP: how external tools and data sources are connected.
2. Personalization and project rules file locations
Windows paths useC:\Users\<user>\; macOS / Linux equivalent is ~.
| Tool | Personalization (user level) | Project level | Path scoping rules | Privacy opt-out |
|---|---|---|---|---|
| Claude.ai (web) | Instructions for Claude (Settings) | Project instructions | Each Project is independent | Help Improve Claude |
| Claude Code | ~/.claude/CLAUDE.md, ~/.claude/settings.json | ./CLAUDE.md, .claude/rules/*.md | Multiple layers merged nearest-first | Account-level Help Improve Claude |
| Claude Cowork | No file system (goal-oriented GUI) | None | None | Controlled by Claude account layer |
| ChatGPT | Custom Instructions | Projects instructions | Each Project is independent | Improve the model for everyone |
| OpenAI Codex | ~/.codex/AGENTS.md (global project instructions) | ./AGENTS.md, .codex/config.toml (loaded only when trusted) | From git root down to cwd; closer files load later and override | Data Controls training toggle |
| Gemini (consumer) | Instructions for Gemini, Personal context | Gem Instructions | Each Gem is independent | Keep Activity |
| Google Antigravity | ~/.gemini/GEMINI.md | ./GEMINI.md, ./AGENTS.md, .agents/rules/*.md | Global rules + workspace .agents/rules/ (plural is official default; singular compatible with older versions) | Enable Telemetry (Settings → Account) |
| GitHub Copilot CLI | ~/.copilot/copilot-instructions.md | .github/copilot-instructions.md, .github/instructions/*.instructions.md | Path-scoped via frontmatter applyTo glob | Account / enterprise settings |
| GitHub Copilot Chat (VS Code) | chat.* workspace settings | .github/copilot-instructions.md | Controlled by chat.instructionsFilesLocations | VS Code account settings |
| Cursor | User Rules (GUI) | .cursor/rules/*.mdc, AGENTS.md | Only .mdc files are read; .md is ignored | Account settings |
Cursor’s two ignore files
.cursorignore blocks AI access entirely; .cursorindexingignore only excludes indexing while the file remains readable. Putting secrets in the wrong file gives you a false sense of protection.3. Memory locations
| Tool | Memory file / mechanism | Scope | How to disable |
|---|---|---|---|
| Claude Code | ~/.claude/projects/<repo>/memory/ and auto-summarized MEMORY.md | Per-repo, accumulates automatically | Settings → Memory, or instruct in CLAUDE.md not to write |
| Claude.ai | Project conversations + non-Project conversations maintained separately | Account-side | Settings → Memory |
| ChatGPT | Saved Memories (viewable and deletable per entry) + Reference chat history | Account-side; Projects can isolate | Settings → Personalization → Manage memories |
| Gemini | Personal context → Memory | Account-side | Settings → Personal context → Memory |
| Codex | No dedicated memory; uses AGENTS.md as a standing-instructions substitute | Project layer | Not applicable |
| Antigravity | Memory (account-side) | Account-side | Account settings |
| Copilot CLI | No dedicated memory; uses instruction files as substitute | Primarily project layer | Not applicable |
| Cursor | No dedicated memory; uses .cursor/rules/*.mdc as substitute | Project layer | Not applicable |
4. Automation and integration locations
| Tool | Reusable workflows | Event hooks | Sub-agents | MCP config |
|---|---|---|---|---|
| Claude Code (primary reference) | .claude/skills/<n>/SKILL.md | hooks in .claude/settings.json, or standalone hooks.json | .claude/agents/*.md | .mcp.json (project), ~/.claude.json (user) |
| ChatGPT | Custom GPTs (Configure tab) | (no file system) | (no file system) | Via Custom GPT Actions |
| OpenAI Codex | prompts/*.md (custom commands, needs source verification) | [hooks] in config.toml (stable) | [agents] (subagents, stable) | [mcp_servers.<id>] in config.toml |
| Gemini (consumer) | Gems | (no file system) | (no file system) | Via Extensions |
| Google Antigravity | Skills: IDE ~/.gemini/config/skills/, CLI ~/.gemini/antigravity-cli/skills/, workspace .agents/skills/; Workflows created via IDE panel (on-disk path not listed in official docs) | hooks.json (in .agents/ or ~/.gemini/config/) | Primarily AGENTS.md and .agents/ | ~/.gemini/config/mcp_config.json (officially confirmed; CLI workspace: .agents/mcp_config.json) |
| GitHub Copilot CLI | Skills: ~/.copilot/skills/<n>/SKILL.md, .github/skills/<n>/SKILL.md | Hooks: ~/.copilot/hooks/ + .github/hooks/ (additive) | Agents: ~/.copilot/agents/<n>.agent.md, .github/agents/<n>.agent.md | ~/.copilot/mcp-config.json, .mcp.json / .github/mcp.json / .vscode/mcp.json |
| Cursor | .cursor/rules/*.mdc | (no equivalent mechanism) | (no equivalent mechanism) | .cursor/mcp.json |
Copilot hooks are additive, not overridingThe user-level
~/.copilot/hooks/ and the project-level .github/hooks/ both run together; the project layer does not replace the user layer. Before working in a shared repo, check which hooks your local setup will bring in.Antigravity is known to conflict when both Gemini CLI and Antigravity write to ~/.gemini/GEMINI.md (see 02-6 Section 3 warning).5. Privacy opt-out quick reference
| Tool | Toggle location (as of 2026-06) | Default | One-off handling |
|---|---|---|---|
| Claude.ai (Free) | Settings → Privacy → Help improve Claude | On (must manually turn off) | Temporary Chat |
| Claude.ai (Team / Enterprise) | Governed by commercial terms | No training (per terms) | Terms level |
| Claude Code | Account-level Help Improve Claude | Same as above | Account level |
| ChatGPT | Settings → Data Controls → Improve the model for everyone | On (must manually turn off) | Temporary Chat |
| Gemini | Settings → Keep Activity | On (users 18+) | Conversations after disabling |
| Workspace (Gemini) | Administrator-controlled | Determined by org policy | Not applicable |
| Copilot | Account / enterprise settings | Enterprise accounts default to no training | Personal accounts follow account settings |
| Cursor | Account Privacy settings | Depends on account type | Privacy Mode (version-dependent) |
6. Cross-tool rules baseline: AGENTS.md
AGENTS.md is an open standard for converging each tool’s proprietary rules file into one (governed by the Agentic AI Foundation under the Linux Foundation). Adoption: Codex, Cursor, Copilot, Gemini CLI, Jules, Devin, Amp, VS Code, and over twenty other tools support it natively (as of 2026-06, adopted by more than sixty thousand open-source projects).
| Tool | Native support | How to share |
|---|---|---|
| Claude Code | No (does not read AGENTS.md) | Import via @AGENTS.md syntax in CLAUDE.md |
| OpenAI Codex | Yes | Reads root and all parent layers by default |
| Google Antigravity | Yes | Used alongside GEMINI.md |
| GitHub Copilot CLI | Yes | Root is primary; can serve as substitute for CLAUDE.md / GEMINI.md |
| Cursor | Yes | Used alongside .cursor/rules/*.mdc |
7. Hands-on: 30-second alignment exercise
Scenario: migrating a Claude setup to Codex
Fill in the six-concept table for your current Claude setup as the source of truth
- Personalization:
~/.claude/CLAUDE.md - Project rules:
./CLAUDE.md,.claude/rules/ - Memory: auto-memory +
MEMORY.md - Privacy opt-out: Help improve Claude toggle
- Automation: skills / hooks / commands
- MCP:
.mcp.json(project),~/.claude.json(user)
Map each cell to Codex
- Personalization:
~/.codex/AGENTS.md - Project rules:
./AGENTS.md,.codex/config.toml - Privacy opt-out: Data Controls training toggle
- Automation:
[hooks]inconfig.toml,prompts/*.md,[mcp_servers.<id>] - MCP: same as automation
- Memory: none dedicated; use
AGENTS.mdas substitute
8. Corresponding units
- Layer model and six-concept framework: 02-1 Configuration Layer Model
- Claude three products (Chat, Cowork, Code) detail: 02-2 Anthropic Claude Setup
- Config file precedence and
settings.local.json: 02-3 settings.json and settings.local.json - What
~/.claude.jsonstores: 02-4 claude.json - Skills / Hooks / Subagents / Plugins overview: 02-5 Mechanism Overview
- Other four tools aligned: 02-6 Other Tools Comparison
- Privacy and security checklist: Appendix B: Privacy and Security Settings Checklist
- Evaluation resources: 03-2 Beyond GitHub Stars, 03-3 Security, Privacy, and Supply Chain Risk
- Extended resources and community: Appendix D: Resources and Community List