docs(readme): lead with install, condense the feature highlights

Put the curl/npm install at the very top and trim the body to the
features worth scanning — tournaments, rewind, cross-session memory,
MCP, subagents, hooks — since most readers won't go deep.

Author: halfaipg

README.md

@@ -1,107 +1,90 @@
 <h1 align="center">codebase</h1>
 
 <p align="center">
-  <strong>An AI coding agent for builders.</strong><br/>
-  Lives in your terminal. Reads your project, writes code, runs commands, ships work.
+  <strong>An AI coding agent that lives in your terminal.</strong><br/>
+  Any LLM. Reads your project, writes code, runs commands, ships work.
 </p>
 
 <p align="center">
   <a href="https://www.npmjs.com/package/codebase-cli"><img alt="npm" src="https://img.shields.io/npm/v/codebase-cli?style=flat-square" /></a>
   <a href="https://github.com/codebase-foundation/codebase-cli/blob/master/LICENSE"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" /></a>
 </p>
 
-<p align="center">
-  Built on <strong><a href="https://github.com/earendil-works/pi">pi</a></strong> &mdash;
-  the agent loop, provider adapters, and session protocol that make this whole
-  thing tick. <a href="https://github.com/earendil-works/pi">Go give them a star.</a>
-</p>
+## Install
 
----
+Requires **Node.js ≥ 20**.
 
-## Two ways to run it
+```sh
+# macOS / Linux
+curl -fsSL https://codebase.design/install.sh | sh
 
-**Bring your own LLM.** Drop an API key in your shell and go — Anthropic, OpenAI, Groq, OpenRouter, Mistral, Ollama, any OpenAI-compatible endpoint.
+# Windows (PowerShell)
+irm https://codebase.design/install.ps1 | iex
 
-```sh
-ANTHROPIC_API_KEY=sk-ant-... codebase
-# or
-OPENAI_API_KEY=sk-... codebase
+# any platform, with npm
+npm i -g codebase-cli
 ```
 
-**Sign in to [codebase.design](https://codebase.design) and skip key wrangling.** One auth, every model.
-
-- **Free tier** — try open-weight models (MiniMax, Qwen, Llama, etc.) with a **10-turn taste** so you can kick the tires before paying anyone for anything. No API keys to set up.
-- **Paid account** — uncaps the open-weights, adds the frontier models (Claude Opus / Sonnet, GPT-5, …), higher rate limits, and longer context windows. One subscription replaces N provider bills.
+Then, in any project:
 
 ```sh
-codebase auth login
+cd your-project
 codebase
 ```
 
-Switch between models any time with `/model` (interactive picker) or `/model <id>`.
+Type, hit enter. It reads files, edits code, runs tests, and shows its work. `/help` lists everything.
 
-## Install
+## Pick your LLM
 
-Requires **Node.js ≥ 20**.
+**Bring your own key** — Anthropic, OpenAI, Groq, OpenRouter, Mistral, Ollama, or any OpenAI-compatible endpoint:
 
 ```sh
-# one-liner (macOS / Linux)
-curl -fsSL https://codebase.design/install.sh | sh
-
-# Windows (PowerShell)
-irm https://codebase.design/install.ps1 | iex
-
-# any platform
-npm i -g codebase-cli
+ANTHROPIC_API_KEY=sk-ant-... codebase     # or OPENAI_API_KEY, GROQ_API_KEY, …
 ```
 
-## Quick start
+**Or sign in once** and skip the key wrangling — [codebase.design](https://codebase.design) gives you a free taste of open-weight models, and a paid account uncaps those plus the frontier models (Claude Opus/Sonnet, GPT-5, …) behind one bill. First run walks you through it; it even auto-detects a local LLM (LM Studio / Ollama / vLLM).
 
 ```sh
-cd your-project
-codebase
+codebase auth login
 ```
 
-Type. Hit enter. The agent reads files, runs tests, edits code, and shows you what it did. Slash `/help` for the rest.
+Swap models live with `/model`. Set reasoning depth with `/effort`.
+
+## What makes it good
 
-A few things worth knowing:
+- **🏁 Tournaments.** `/tournament <task>` races several agents on the same change in isolated worktrees, a judge ranks them, you merge the winner. `--models opus,sonnet,haiku` pits models head-to-head on *your* code.
+- **↺ Rewind anything.** `/rewind` rolls the conversation *and* the files back to before any earlier prompt — a bad turn fully un-happens. Every edit is checkpointed.
+- **🧠 Remembers across sessions.** Pulls durable facts (your prefs, project decisions, the rules you set) out of a session in the background so the next one starts informed. `#note` to add one by hand.
+- **🔌 MCP.** Connect external tool servers (filesystem, Postgres, git, fetch, …) over stdio or remote HTTP, OAuth and all. Their tools splice straight into the agent.
+- **🤖 Subagents.** Fan out read-only researchers or write-capable workers that keep their tool-noise out of your main context — each can run in its own git worktree, on its own model and reasoning level.
+- **🪝 Hooks.** Shell commands on lifecycle events (pre/post tool, edit, prompt, session start/end) — run a formatter on save, block secrets, commit on exit.
+- **🌐 SSH.** Run commands on enrolled remote hosts by name, behind the same safety validator as the local shell.
 
-- `/model` — pick a model interactively, live list of what your account can hit
-- `/plan` — Q&A before the agent touches anything
-- `!cmd` — run a shell command without spending a turn
-- `@path` — pin a file into the next prompt
-- `\<Enter>` — multi-line input
-- **Type while the agent is working** — your prompt queues, fires when the current turn ends (`Ctrl-C` while busy clears the queue along with the turn)
-- **Ctrl-C** stops the current turn, twice fast exits
+…plus a fast differential TUI (clean copy-mode with `Ctrl-O`, image paste with `Ctrl-V`, history search with `Ctrl-R`, `$EDITOR` compose with `Ctrl-G`), **plan mode** for a cheap Q&A pass before editing, **auto-compaction** of long sessions, **multi-session resume** (`/resume`, `/rename`, `/tag`), **skills** & **output styles** as drop-in markdown, **45+ tools** behind one interface, and **effect-based permissions** you can teach with `/permissions`.
 
-## What it does
+## Cheat sheet
+
+```
+/model /effort /plan /tournament /rewind /resume /permissions /mcp /agents /help
+!cmd     run a shell command without spending a turn
+@path    pin a file into the next prompt
+#note    save a memory   ·   \<Enter>  multi-line   ·   Ctrl-C  stop turn / exit
+```
 
-- **Streaming responses.** Real-time token output, coalesced to 60 fps so the TUI doesn't thrash.
-- **Multi-turn agentic loop.** Tool call → result → next turn, automatically.
-- **Parallel tool execution.** Read-only tools (grep, glob, read, git status…) run concurrently within a turn.
-- **Project awareness.** Auto-loads `AGENTS.md`, `CLAUDE.md`, `CODEX.md`, or `.cursorrules` from the project root into the system prompt.
-- **Conversation compaction.** Long sessions automatically summarize older turns to stay under the context window.
-- **Session persistence.** Auto-resume from where you left off; `--new` for a clean slate.
-- **Plan mode.** A cheap-model Q&A pass surfaces the right plan before the expensive agent starts editing.
-- **Intent routing.** Chit-chat doesn't burn a full agent turn; complex asks roll into plan mode automatically.
-- **Subagent dispatch.** Spawn isolated research agents that keep their tool noise out of your main context.
+Type while it's working — your prompt queues and fires when the turn ends.
 
-## Builder-focused defaults
+## Built on pi
 
-- **Any LLM**, not just Anthropic. Provider choice is config.
-- **45+ tools** behind one small interface — adding one is mechanical.
-- **Effect-based permissions** instead of tool-name allowlists.
-- **Single immutable state** driven by a typed reducer — the UI is one render of one value.
-- **Multi-process safe OAuth** with lockfile-coordinated token refresh — run 10 instances of codebase at once and they share a single refresh per hour.
-- **Plain `npm i -g`**, no bundler lock-in.
+The agent loop, provider adapters, and session protocol come from
+**[pi](https://github.com/earendil-works/pi)** (MIT). Go give them a star.
 
 ## More
 
-- [`.settings/`](.settings/) — orientation: tenets, architecture, extending, testing
-- [`CLAUDE.md`](CLAUDE.md) — quick reference for AI agents working in this repo
+- [`CLAUDE.md`](CLAUDE.md) — full feature reference
+- [`.settings/`](.settings/) — tenets, architecture, extending, testing
 - [`docs/MIGRATION_v1_to_v2.md`](docs/MIGRATION_v1_to_v2.md) — upgrading from the Go v1 binary
-- `/help` inside the CLI — every slash command and shortcut
+- `/help` inside the CLI — every command and shortcut
 
 ## License
 
-MIT. Built on [pi-mono](https://github.com/earendil-works/pi) (MIT).
+MIT.