One Brain, Two Wallets: Two Claude Code Accounts on One Machine

I hit my Claude Code usage limit mid-week. I have a second subscription, but switching accounts the naive way — /logout, /login, repeat — is miserable, and it turns out "switching accounts" in Claude Code silently means switching everything: skills, MCP servers, settings, hooks, memory, session history. All of it. What I actually wanted: one brain, two wallets. Same skills, same MCP servers, same muscle memory — just a different subscription getting billed. Here's the setup that got me there. ~20 minutes, fully reversible. Step 1: Two config dirs, two aliases Claude Code keeps all its state in a config directory — ~/.claude by default — and honors a CLAUDE_CONFIG_DIR env var to point elsewhere. That's the whole trick: # ~/.zshrc # Claude Code multi-account aliases alias claude-work='CLAUDE_CONFIG_DIR=~/.claude claude' alias claude-personal='CLAUDE_CONFIG_DIR=~/.claude-personal claude' Enter fullscreen mode Exit fullscreen mode mkdir ~/.claude-personal source ~/.zshrc claude-personal # prompts OAuth login for the second account — one time Enter fullscreen mode Exit fullscreen mode Credentials land in whichever dir is active. Bare claude still defaults to ~/.claude, so nothing about your existing workflow changes. Gotcha #1: .claude.json moves when you set the env var Claude Code's user-level config file (~/.claude.json — MCP servers, folder trust, onboarding state) lives next to ~/.claude, not inside it. But when CLAUDE_CONFIG_DIR is set, it's read from inside the config dir instead. So claude-work — even though it points at the same ~/.claude you've always used — creates a fresh, empty ~/.claude/.claude.json and suddenly has zero MCP servers. Fix: symlink it to the master, since it's the same account: ln -s ~/.claude.json ~/.claude/.claude.json Enter fullscreen mode Exit fullscreen mode Now bare claude and claude-work are byte-for-byte identical. Step 2: Share the brain The second account starts as a blank slate. Since only billing should differ, symlink everything shareable from the main dir: cd ~/.claude-personal ln -s ~/.claude/skills skills ln -s ~/.claude/CLAUDE.md CLAUDE.md ln -s ~/.claude/settings.json settings.json # hooks, permissions, env ln -s ~/.claude/settings.local.json settings.local.json ln -s ~/.claude/plugins plugins Enter fullscreen mode Exit fullscreen mode One source of truth: add a skill or tweak a hook once, both accounts see it. MCP servers need more care. They live in .claude.json, which also holds the account identity (oauthAccount) — so you can't symlink the whole file across accounts. Merge just the mcpServers block: jq --slurpfile mcp /tmp/merged.json && mv /tmp/merged.json ~/.claude-personal/.claude.json Enter fullscreen mode Exit fullscreen mode Gotcha #2: --resume doesn't know about accounts Session transcripts live at /projects//.jsonl. Resume a personal session under the work account and Claude just says the session doesn't exist. Worse, anything that launches bare claude for you — crash-restore scripts, launchd jobs — always resumes against the default dir. The fix is a tiny shim earlier in $PATH than the real binary. Every session ID exists in exactly one account's tree, so ownership is the routing signal: #!/bin/bash # ~/.local/bin/claude — routes --resume to the account that owns the session REAL=/opt/homebrew/bin/claude # wherever `command -v claude` pointed before if [[ -z "$CLAUDE_CONFIG_DIR" ]]; then id="" prev="" for arg in "$@"; do if [[ $prev == "--resume" || $prev == "-r" ]]; then id=$arg; break; fi if [[ $arg == --resume=* ]]; then id=${arg#--resume=}; break; fi prev=$arg done if [[ -n $id ]] && compgen -G "$HOME/.claude-personal/projects/*/$id.jsonl" >/dev/null; then export CLAUDE_CONFIG_DIR="$HOME/.claude-personal" fi fi exec "$REAL" "$@" Enter fullscreen mode Exit fullscreen mode Now claude --resume just works, from anywhere, for either account. Explicit CLAUDE_CONFIG_DIR (your aliases) passes through untouched. Bonus: moving a conversation between wallets The whole reason I did this was running out of credits mid-conversation. Since a session is just a transcript file, "continue this work conversation on my personal account" is a copy + resume: #!/bin/bash # ~/.local/bin/claude-pickup — continue a work session as personal set -euo pipefail id=${1:?usage: claude-pickup } src=$(ls ~/.claude/projects/*/"$id".jsonl 2>/dev/null | head -1) [[ -n $src ]] || { echo "session $id not found" >&2; exit 1; } proj=$(basename "$(dirname "$src")") mkdir -p ~/.claude-personal/projects/"$proj" cp -n "$src" ~/.claude-personal/projects/"$proj"/ CLAUDE_CONFIG_DIR=~/.claude-personal exec claude --resume "$id" Enter fullscreen mode Exit fullscreen mode The work account keeps its copy as history; new turns land only in the personal copy. And since the shim checks the personal tree first, future bare claude --resume of that ID follows the conversation to its new wallet automatically. What stays separate (and should) Credentials and billing — the entire point. Session transcripts — the shim depends on separate trees. Folder trust — each account re-asks "do you trust this folder?" once per directory. Expected, answer once. OAuth'd MCP servers (Linear, Notion, …) — tokens are per config dir; run /mcp once in the new account to re-auth. CLI-based MCP servers that use machine credentials work immediately. The result claude # work (default, unchanged) claude-personal # second subscription, same brain claude --resume X # figures out the account itself claude-pickup X # mid-conversation wallet swap Enter fullscreen mode Exit fullscreen mode Same skills, same MCP servers, same hooks, same memory. The only thing that changes is who gets the bill.