Claude Sessions Sync logo

Claude Sessions Sync

Community
serejaris
claude-sessions-sync

Sync Claude Code session records between two Anthropic accounts in the Claude desktop app on macOS. Use when switching accounts (for example when one hits usage limits) and old sessions disappear from the picker, or to mirror records before/after a switch.

Overview

Publisherserejaris
Repositorypersonal-corp-os
Skill nameclaude-sessions-sync
Stars
232
Forks
26
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by serejaris on GitHub. Read the source before you install it.

Installation

Install the Claude Sessions Sync AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/serejaris/personal-corp-os/tree/main/skills/claude-sessions-sync
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/serejaris/personal-corp-os.git /tmp/personal-corp-os
mkdir -p .claude/skills
cp -r /tmp/personal-corp-os/skills/claude-sessions-sync .claude/skills/claude-sessions-sync
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Claude Sessions Sync in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Claude Sessions Sync on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Claude Sessions Sync is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Claude sessions sync (between desktop-app accounts)

How it works (verified 2026-10-01…07, Claude Code 2.1.286, macOS):

  • Session records live in ~/Library/Application Support/Claude/claude-code-sessions/<accountUuid>/<orgUuid>/local_*.json. The second path level is the organization UUID; the app lists only the current account+org pair, which is why switching accounts hides the other side's sessions.
  • Transcripts live in ~/.claude/projects/ and are shared across all accounts — never touch them. A record points at its transcript through the cliSessionId field.
  • Active account: ~/Library/Application Support/Claude/config.json → lastKnownAccountUuid. The active org folder is the one holding the freshest record (mtime).
  • Account switches may leave empty race folders <old-account>/<new-org> — ignore them.

Procedure

  1. The app must be fully closed: pgrep -f "/Applications/Claude.app/Contents/MacOS" is empty; otherwise osascript -e 'quit app "Claude"' and wait. Copying while the app is alive can be rolled back by its in-memory list cache (LSS-cached-sessions) and record rewrites.
  2. Identify both working folders: under each account UUID take the subfolder with the most local_*.json records (or the freshest one).
  3. Run a bidirectional newest-wins sync of local_*.json — the script below. A one-way copy leaves drift: sessions you continued on one side go stale on the other.
  4. Merge archived-sessions.idx: union the archived lists of both folders, write the same file into both.
  5. Copy missing deleted_* markers in both directions, otherwise deleted sessions resurrect in the picker.
  6. Do NOT sync scheduled-tasks.json or backlog/ — each account+org pair keeps its own.
  7. Reopen the app, switch the login to the target account, verify the record count in the picker.

Script (edit FIRST/SECOND, app closed)

python
import os, json, shutil

SESS = os.path.expanduser("~/Library/Application Support/Claude/claude-code-sessions")
FIRST  = f"{SESS}/<account-uuid-1>/<org-uuid-1>"
SECOND = f"{SESS}/<account-uuid-2>/<org-uuid-2>"

def records(d):
    return {f: os.path.getmtime(os.path.join(d, f))
            for f in os.listdir(d) if f.startswith("local_") and f.endswith(".json")}

f_rec, s_rec = records(FIRST), records(SECOND)
for f, m in s_rec.items():
    if f not in f_rec or m > f_rec[f]:
        shutil.copy2(os.path.join(SECOND, f), os.path.join(FIRST, f))
for f, m in f_rec.items():
    if f not in s_rec or m > s_rec[f]:
        shutil.copy2(os.path.join(FIRST, f), os.path.join(SECOND, f))

arch = set()
for d in (FIRST, SECOND):
    p = os.path.join(d, "archived-sessions.idx")
    if os.path.exists(p):
        try: arch |= set(json.load(open(p)).get("archived", []))
        except Exception: pass
idx = {"v": 1, "archived": sorted(arch)}
for d in (FIRST, SECOND):
    json.dump(idx, open(os.path.join(d, "archived-sessions.idx"), "w"))

for a, b in ((FIRST, SECOND), (SECOND, FIRST)):
    for f in os.listdir(a):
        if f.startswith("deleted_") and not os.path.exists(os.path.join(b, f)):
            shutil.copy2(os.path.join(a, f), os.path.join(b, f))

Gotchas

  • Claude Code cleans old transcripts (about a month back by default): such records return to the picker but open empty. There is nothing to restore from.
  • Copies drift apart while you work on one account — rerun the sync on every switch.
  • Continuing a moved session sends its transcript to the current account (privacy note for personal-vs-work orgs).
  • There is no official cross-account migration (anthropics/claude-code#48511 closed as not planned); terminal claude --resume <id> sees all local sessions under any login.

Background write-up: https://sereja.tech/blog/claude-code-sessions-between-accounts/

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Claude Sessions Sync AI skill do?

Sync Claude Code session records between two Anthropic accounts in the Claude desktop app on macOS. Use when switching accounts (for example when one hits usage limits) and old sessions disappear from the picker, or to mirror records before/after a switch.

Why use Claude Sessions Sync on TypingMind?

Because you install it once and use it with any model. Claude Sessions Sync is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Claude Sessions Sync in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/serejaris/personal-corp-os/tree/main/skills/claude-sessions-sync. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Claude Sessions Sync?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Claude Sessions Sync?

As many as you like. As long as a model supports skills, you can use Claude Sessions Sync with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Claude Sessions Sync AI skill free?

Yes. It is published on GitHub by serejaris under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇