oathe / claude code

Hit your Claude Code usage limit? Keep working in Codex or Cursor.

You're mid-refactor. Claude Code prints You've reached your usage limit and stops. Your files are fine. What you were doing is in a context window that no longer exists.

Run claude as usual. Your agent claims your task when work begins. Oathe checkpoints it as it runs, and it's still yours after the session ends.

See what carries over when you resume a Claude Code session in Codex.

Start

Node 22.13 or newer and Postgres running. You don't need either on Oathe Cloud.

npm install -g @oathe/oathe cd your-project oathe init # once per machine claude # nothing changes about how you launch it

Nothing about Claude Code changes. Same prompts, same tools, same subagents, same permission modes. Oathe sits underneath and records what you're doing.

Continue in another agent

Ctrl-C anytime. Open Codex or Cursor in the same folder.

codex # Codex picks up your task agent # or Cursor's CLI

You don't paste a transcript or explain it again. The next agent gets what you claimed, what's done, what's left and a test that decides whether it's finished. It reads the diff and reruns the test before trusting anything the last agent told it.

More on Claude Code handoff. Works the other way too: start in Codex and finish in Claude Code.

"Done" is a claim until something checks it

Claude Code can say it's done when it isn't.

When it says your work is finished, Oathe records that as something the agent said. A fresh checker that didn't do the work looks at what the agent did, against what you asked for. If it passes, your task is finished. If it fails, it reopens. The checker can be a different tool from the one that did the work.

oathe claim fix-login "users can sign in again" oathe done fix-login "guard rewritten, test added" src/auth.test.js oathe verify fix-login # a checker that didn't do the work

In-session, Claude Code can do all of this itself through the oathe_* MCP tools.

Before Claude Code installs a skill

Every MCP server you add runs with the same access Claude Code has.

Oathe Scan runs a skill in a sandbox first and reports what it actually did: file access, network calls, process activity. We've audited 3,087 of them, including 24 that were outright malicious.