Import creates the agent in one step, and imported agents stop expiring

CHANGELOG.md

@@ -9,6 +9,17 @@ Product release notes: [docs.proofable.me/changelog](https://docs.proofable.me/c
 
 ## [Unreleased]
 
+## [0.1.10] - 2026-10-28
+
+### Changed
+
+- **`proofable import` creates the agent in one step.** A signed-in terminal now creates the agent on your profile with its full instructions and mounts it into the current project, for the host the source names or the one you pass with `--apply`. Its permissions never expire unless you set an end with `--expires-at` (a date or Unix milliseconds); `--no-mount` skips the mount. It prints the agent's name, what it may do, when its permissions end, and its agent page. `owner/name` reads a GitHub repository, and `--dry-run` shows what would happen without creating anything.
+
+### Fixed
+
+- **`proofable auth --oauth` signs in the CLI and leaves your editors alone.** It no longer writes its short-lived token into Cursor, VS Code or Claude, which keep the sign-in `proofable setup` gave them, and it works on a machine with none of them installed. Name an editor with `--client` to write the token there too.
+- **Long agent instructions are never dropped without a word.** A terminal that is not signed in is sent to the browser import. When a step has to finish in the browser and the link cannot carry the instructions, the CLI says so and tells you to paste them there.
+
 ## [0.1.9] - 2026-10-27
 
 ### Fixed
@@ -174,7 +185,8 @@ The `@proofable/sdk` package continues the line published as `@neus/sdk`. The no
 | [1.1.0](https://www.npmjs.com/package/@neus/sdk/v/1.1.0) | 2026-05-26 | First public SDK release on npm: OAuth-first setup, the CLI, public MCP tools including encrypted Vault secrets, and the Claude Code plugin with the trust workflow skill. |
 | [1.0.12](https://www.npmjs.com/package/@neus/sdk/v/1.0.12) | 2026-05-26 | First `@neus/sdk` release with the hosted MCP CLI (`neus setup`, `neus auth`, import/export) and the OAuth browser flow. |
 
-[Unreleased]: https://github.com/proofable/sdk/compare/v0.1.9...HEAD
+[Unreleased]: https://github.com/proofable/sdk/compare/v0.1.10...HEAD
+[0.1.10]: https://github.com/proofable/sdk/compare/v0.1.9...v0.1.10
 [0.1.9]: https://github.com/proofable/sdk/compare/v0.1.8...v0.1.9
 [0.1.8]: https://github.com/proofable/sdk/compare/v0.1.7...v0.1.8
 [0.1.7]: https://github.com/proofable/sdk/compare/v0.1.6...v0.1.7

README.md

@@ -5,15 +5,53 @@ Add verification gates, reusable proof, and agent permissions to your app.
 [![npm](https://img.shields.io/npm/v/%40proofable%2Fsdk?label=%40proofable%2Fsdk&color=98C0EF)](https://www.npmjs.com/package/%40proofable%2Fsdk)
 [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](./LICENSE)
 
-Verify someone once, then reuse that proof on every later check.
-
 ## Start here
 
+Bring the agent you already run. Proofable gives it an ID tied to you and a list of what it may do.
+
+Requires Node.js 20 or later.
+
+**1. Connect and sign in**
+
 ```bash
-npm install @proofable/sdk
+npx -y @proofable/sdk setup
+npx -y @proofable/sdk auth --oauth
 ```
 
-Requires Node.js 20 or later.
+`setup` connects Proofable to the AI tools on this machine.
+`auth --oauth` signs this terminal in through your browser.
+
+**2. Import your agent**
+
+```bash
+npx -y @proofable/sdk import owner/name --apply claude
+```
+
+Point it at a GitHub repository (`owner/name` or its URL) or a folder.
+It creates the agent on your profile and writes it into this project.
+Name the tool with `--apply`. It takes `cursor`, `claude`, `codex`, `hermes`, `openclaw` or `opencode`, and VS Code uses `cursor`.
+
+**3. Use it**
+
+`import` prints what the agent may do, the files it wrote and the agent's page.
+Open this project in that tool. The agent's instructions and permissions are in those files.
+Its permissions never expire unless you pass `--expires-at <date>`.
+
+**Or let your coding agent do it**
+
+Paste this into Claude Code, Cursor or Codex.
+
+```text
+Set up Proofable for this project. Run `npx -y @proofable/sdk setup`. Then run `npx -y @proofable/sdk auth --oauth` and wait for me to sign in through the browser. Then run `npx -y @proofable/sdk import . --apply <host>`, replacing <host> with claude, cursor or codex to match the tool you run in. Show me what the agent may do and its page link.
+```
+
+## Add a check to your app
+
+Verify someone once, then reuse that proof on every later check.
+
+```bash
+npm install @proofable/sdk
+```
 
 **Send a person to verify**
 
@@ -76,13 +114,17 @@ import { VerifyGate } from '@proofable/sdk/widgets';
 Interactive clients add `https://mcp.proofable.me/mcp`, click **Connect**, and sign in. Servers and CI send a server key from `PROOFABLE_ACCESS_KEY` as a Bearer token.
 
 ```bash
-npx -y @proofable/sdk setup
 npx -y @proofable/sdk setup --access-key $PROOFABLE_ACCESS_KEY
+npx -y @proofable/sdk import <github-url|owner/name|folder> --dry-run
 npx -y @proofable/sdk mount <agentId> --apply <host>
 npx -y @proofable/sdk doctor --live
 ```
 
-`--apply` accepts `cursor`, `claude`, `codex`, `hermes`, `openclaw`, or `opencode`. VS Code uses `--apply cursor`. Setup steps: [docs.proofable.me/mcp/setup](https://docs.proofable.me/mcp/setup).
+`import` also reads an MCP server URL or an A2A agent card.
+`--dry-run` shows what it would create. `--no-mount` creates the agent without writing it into the project.
+A terminal that is not signed in gets a browser link instead.
+
+`mount` writes an agent you already have into this project for another tool. Setup steps: [docs.proofable.me/mcp/setup](https://docs.proofable.me/mcp/setup).
 
 ## Core methods