@euqns/nudge-mcp 0.16.0 → 1.0.0

package/README.md

@@ -66,19 +66,22 @@ authenticated on the user's computer. It binds to loopback and opens Nudge with
 a one-time pairing secret in the URL fragment:
 
 ```bash
-# Sign in to one of the supported CLIs first
-codex login                 # or: claude auth login / cursor-agent login
+# Sign in to any or all supported CLIs first
+codex login
+claude auth login
+cursor-agent login
 
 # Run this from the repository the agent should inspect
-npx -y @euqns/nudge-mcp@latest agent --provider codex
-# Providers: codex, claude, cursor
+npx -y @euqns/nudge-mcp@latest agent
 ```
 
-The companion does not accept or store provider API keys. It reuses the selected
-CLI's existing subscription login, following the same bring-your-own-subscription
-model as local multi-agent clients. It keeps local filesystem access read-only
-and allows only the exact Nudge origin that launched it. Authorized Nudge MCP
-tools can still update board data.
+The companion checks Codex, Claude Code, and Cursor independently, starts when at
+least one has a valid subscription login, and reports which CLIs are ready. One
+pairing exposes every ready provider, so each chat can choose its own agent and
+resume with that same agent later. `--provider codex|claude|cursor` remains an
+optional initial preference. The companion does not accept or store provider API
+keys. It keeps local filesystem access read-only and allows only the exact Nudge
+origin that launched it. Authorized Nudge MCP tools can still update board data.
 
 The Codex and Claude Code adapters supply their own Nudge MCP transport, so a
 fresh computer does not need a manual `mcp_servers.nudge` entry in
@@ -88,13 +91,13 @@ Cursor reads MCP servers from its normal `.cursor/mcp.json` configuration, so
 the Nudge MCP server must also be present there for board mutations.
 
 For Codex, the sidecar reads the installed model catalog and subscription rate-limit
-windows from the local Codex app server. Users can change models, choose any
-reasoning effort supported by that model, see the exact remaining percentage
-and reset time exposed by their plan, and inspect the input, output, cache, and
-reasoning-token usage for each completed turn. A model or effort change starts
-a fresh chat; prior chats are kept in browser-local history and resume their
-persisted local agent session when reopened. Claude Code and Cursor use the
-model and usage settings managed by their own CLI account.
+windows from the local Codex app server. Claude Code exposes its subscription model
+aliases and reasoning efforts, while Cursor reads the models available to the signed-in
+account from `cursor-agent --list-models`. Users can change models for every provider;
+Claude Code and Codex also expose reasoning effort. A model or effort change starts a
+fresh chat; prior chats are kept in browser-local history and resume their persisted
+local agent session when reopened. Codex additionally shows its exact rate-limit windows
+and per-turn token usage.
 
 When chat is opened from a board or canvas, Nudge sends the active board id,
 title, source, view, canvas id, and lightweight counts with each prompt. The