Set up Context Locker

What happens

1. Your app reads the steps and runs setup with its own --app name. Only that app is connected and configured.
2. You approve that app in your browser, with a code it shows you. The page names that app and what setup writes. Or you start in Context Locker: name the connection under Connections, and paste the prompt it gives you, with its one-time code, into your app.
3. It saves the sync script in a folder of its own, and writes the selected app's files.
4. It adds that app's hooks, so it syncs on its own events, such as the start of a session and compaction. With auto sync on, the default, it brings changes in and says so. With it off, on the app's page in Connections, it says changes are waiting, and syncs when your app runs it. Hermes and OpenClaw can also sync once a day from their own scheduler, if you say yes.
5. It checks everything.
6. If you ticked Bring in as you approved it, your app then imports what your AI apps on this computer already know: it copies it into a private folder, sorts it into one plan, and sends it to your inbox, where you pick what comes in. Nothing in your playbook changes until you do, and your apps' own files stay as they are. The import follows no link in your apps' folders, and lists each one it skipped.
7. Your app tells you what it now knows.

To connect another app, run setup separately through it. Existing connections and hooks stay as they are. Your app may ask you to allow the command. In Codex, trust the new hook in /hooks. In Hermes, approve the hooks the first time a chat asks. Without Node, your app sets up with the sync script alone, and shows you every file it will write before it writes them.

When a newer sync script is out, your app says so at the start of a session. Once you say yes, it updates the script with one command, which checks the new one against the SHA-256 Context Locker gives, keeps the old one beside it and changes nothing else. A release that changes more, such as a hook, asks you to set up again instead.

What it writes

• Claude Code: a file of its own, ~/.claude/rules/context-locker.md, and your skills in ~/.claude/skills.
• Codex: a marked block in ~/.codex/AGENTS.md, and your skills in ~/.agents/skills.
• Hermes: a marked block in ~/.hermes/SOUL.md, and your skills in ~/.hermes/skills.
• OpenClaw: marked blocks in its workspace's USER.md and AGENTS.md, and your skills in ~/.agents/skills.
• In a project: its notes in .context-locker/notes, which git leaves out. In a repo linked with a .contextlocker.json, the project's own block in the repo's files too.
• For importing: Context Locker's own import skill, context-locker-gather, with your skills, and the copies it makes in ~/.contextlocker/gather, which only your account can read. It deletes them once your plan is in, and any older than 7 days.

The files

The setup command saves these same scripts. Without Node, your app checks them against these SHA-256 hashes before running them. A published version never changes; a new version gets a new address.

• SKILL.mdThe setup steps your app follows.1604ab941a9f26e3b5af10b754719951c36f3ebbfbf8d4dc10ee0a0876e4d717
• sync.shThe sync script for macOS and Linux.bfe4ef2ace484b2f4fe1c22ea1b7afc66a38db598eb5301ca64b66974451be9b
• sync.ps1The sync script for Windows.5a4dc9ca6254300c9327b289401c9ac3c1eb1e3290ec132161bde57eef5443d5

Claude, ChatGPT and other chat apps

These connect with a connector, at this address:

When your app opens Context Locker, sign in, check what the app can do, and approve it.

Claude, on the web, in the desktop app or in Cowork:

1. Go to Customize > Connectors, choose + Add, then Add custom connector.
2. Name it Context Locker, enter the address as its URL, and choose Continue.
3. For Authentication, choose Sign in now, and for the OAuth client, Use Claude's published identity, the recommended one. Go on until you can choose Add, then approve it in Context Locker.
4. In a chat, turn it on with + and Connectors.

On a Team or Enterprise plan, an Owner adds it first, in Organization settings > Connectors, with Add, then Custom, then Web. Then each person finds it under Customize > Connectors and chooses Connect. On the Free plan, it's the one custom connector Claude allows.

ChatGPT, on the web:

1. Go to chatgpt.com/plugins, choose the plus button, then Add custom MCP server.
2. Name it Context Locker. Under Connection, enter the address as the server URL, and choose OAuth.
3. Read the warning, choose I understand and want to continue, then Create as a plugin.
4. Install it, and approve it in Context Locker. In a chat, type @ and choose it.

For an app in the cloud that takes a key, such as Muse or Grok Bot, and for any other app, see the docs.