diff --git a/README.md b/README.md
index 18e3793..925673b 100644
--- a/README.md
+++ b/README.md
@@ -1,339 +1,205 @@
+
+
# oh-my-pi-telegram
-
+**A Telegram companion hub for live [Oh My Pi](https://github.com/can1357/oh-my-pi) (`omp`) sessions —
+queue prompts, stream replies, send files and voice, and supervise your agent from your phone.**
-**Telegram companion hub for live [Oh My Pi](https://github.com/can1357/oh-my-pi) (omp) sessions.**
+
+
+
-> **This is the Evandro Fonseca Junior fork** of [`@llblab/pi-telegram@0.22.0`](https://github.com/llblab/pi-telegram/tree/v0.22.0) (SHA `afe09c5`), repackaged and validated as a drop-in extension for [`can1357/oh-my-pi`](https://github.com/can1357/oh-my-pi) — the AI coding agent for the terminal.
->
-> Upstream lineage: `badlogic/pi-telegram` → `llblab/pi-telegram` (0.22.0) → **`evandrodevbr/oh-my-pi-telegram`** (this fork).
+[Install](#installation) · [Features](#what-it-does) · [How it works](#how-it-works) · [Limitations](#limitations) · [Development](#development) · [CI/CD](#cicd)
-## Oh My Pi (omp) Compatibility
+

-This fork is built and tested against:
+
-| Component | Version | Status |
-| --- | --- | --- |
-| `can1357/oh-my-pi` (CLI: `omp`) | `>=16.5.2` (`@oh-my-pi/pi-coding-agent`) | ✅ verified |
-| `@earendil-works/pi-{ai,agent-core,coding-agent}` | `>=0.80.6` | ✅ verified (peerDeps preserved from upstream) |
-| `node` | `>=22.19.0` | ✅ verified on Node 24.15.0 |
-| Telegram Bot API | current | ✅ unchanged from upstream |
+> [!NOTE]
+> **Project status:** fork of [`@llblab/pi-telegram@0.22.0`](https://github.com/llblab/pi-telegram/tree/v0.22.0)
+> (SHA `afe09c5`), repackaged as `@evandrodevbr/oh-my-pi-telegram` and declared as an
+> `omp` extension. Per [`CHANGELOG.md`](CHANGELOG.md), the fork passes the upstream
+> gates (typecheck, 1229/1230 tests with one platform-only skip, `npm audit` with 0
+> vulnerabilities, clean `npm pack --dry-run`). The latest commit adds a design spec
+> for an OMP 17 status-bar segment ([`docs/superpowers/specs/`](docs/superpowers/specs/2026-07-15-telegram-omp-status-design.md));
+> that spec needs a new OMP core API and is **not implemented in this repository yet**.
-### Install into omp
+> [!IMPORTANT]
+> **This is a runtime adapter, not a remote terminal.** Telegram prompts are normal
+> model turns in the instance's *currently active* session and inherit its
+> post-compaction context, so token cost is not proportional only to the new mobile
+> message. Telegram can compact the current session, but cannot create, resume, fork,
+> browse or switch sessions, and arbitrary slash commands are never forwarded to the TUI.
+
+## Installation
+
+Requires `omp` ≥ 16.5.2 (`@oh-my-pi/pi-coding-agent`) and Node.js ≥ 22.19.0.
```bash
-# From npm (after this fork is published):
-omp install npm:@evandrodevbr/oh-my-pi-telegram
+# From git (this repository)
+omp plugin install https://git.evandro.dev.br/evandro/oh-my-pi-telegram.git
-# From git (always works):
-omp install git:github.com/evandrodevbr/oh-my-pi-telegram
+# From npm (once the package is published)
+omp plugin install npm:@evandrodevbr/oh-my-pi-telegram
-# From a local checkout (development):
-omp install --link /path/to/oh-my-pi-telegram
+# From a local checkout (development)
+omp plugin link /path/to/oh-my-pi-telegram
```
-Then inside `omp`:
+Restart (or reload) `omp` so the extension loads, then:
-```bash
-/telegram-setup # paste bot token
-/telegram-connect # activate polling for this omp instance
-```
+1. Create a bot with [@BotFather](https://t.me/BotFather) (`/newbot`) and copy the token.
+2. In `omp`, run `/telegram-setup` and paste the token.
+3. Run `/telegram-connect` to activate polling for this instance.
+4. In the bot DM, send `/start`.
-In your Telegram bot DM:
+> [!WARNING]
+> **The first Telegram user to message the bot becomes the allowed owner**; everyone
+> else is ignored. Pair right after `/telegram-connect`, and never put the bot token in
+> chat, source, committed config or logs. Setup can prefill the token from
+> `TELEGRAM_BOT_TOKEN`, `TELEGRAM_BOT_KEY`, `TELEGRAM_TOKEN` or `TELEGRAM_KEY`; the saved
+> config lives in `~/.pi/agent/telegram.json`.
-```text
-/start
-```
+## Why this fork and not upstream
-The first user becomes the allowed owner.
+`llblab/pi-telegram@0.22.0` targets the Pi extension platform (`@earendil-works/pi-*`).
+`omp` consumes the same platform republished as `@oh-my-pi/pi-coding-agent`. This fork:
-### Why this fork exists
+1. Renames the package to `@evandrodevbr/oh-my-pi-telegram` so it is unambiguous in the `omp` extension registry.
+2. Keeps the upstream `peerDependencies` on `@earendil-works/pi-{ai,agent-core,coding-agent}` `>=0.80.6`, the runtime surface `omp` consumes — no code changes or shims.
+3. Declares the extension through an `omp` block in `package.json` (`extensions`, display name and `compatibleWith: >=16.5.2`); the old `pi` block was replaced by it.
+4. Re-runs every upstream gate (`typecheck` → `test` → `audit` → `pack:check`) on the `v0.22.0` source.
-`llblab/pi-telegram@0.22.0` targets the **Pi extension platform** (`@earendil-works/pi-*`). `omp` ships the same platform but republishes it under `@oh-my-pi/pi-coding-agent` with the additional harness tooling (LSP, DAP, hashline, subagents, advisor, TTSR, …). This fork:
+Lineage: `badlogic/pi-telegram` → `llblab/pi-telegram` (0.22.0) → **this fork**.
-1. **Renames the npm package** to `@evandrodevbr/oh-my-pi-telegram` so it is unambiguous in the `omp` extension registry.
-2. **Keeps the upstream `peerDependencies`** on `@earendil-works/*` (these are the canonical runtime packages that both Pi and omp consume).
-3. **Adds an `omp` field** in `package.json` with explicit compatibility metadata for downstream extension discovery.
-4. **Re-runs every upstream gate** (`typecheck` → `test` → `audit` → `pack:check`) on the exact `v0.22.0` source — 1229 tests pass, 0 vulnerabilities, pack clean.
-5. **Adds this README section** so the fork is discoverable as the Telegram bridge for omp.
+## What it does
-## What `pi-telegram` (and this fork) does
+| Surface | What you can do |
+|---|---|
+| **Prompt intake** | Send text, replies, edits, images, files, albums and voice notes into the session |
+| **Queue control** | Messages sent while the agent is busy become queued turns; inspect, delete, promote, continue, abort, stop or force the next one |
+| **Operator menu** | `/start` opens status, prompt templates, model, thinking level, settings, queue and extension sections |
+| **Prompt templates** | Run Pi prompt templates as Telegram-safe commands such as `/fix_tests` |
+| **Model and thinking** | Switch model or reasoning level through safe continuation flows; confirm `/compact` |
+| **Rich replies** | Native Rich Markdown (default) or legacy Markdown-to-HTML for final answers; optional live draft previews; native `…typing` status while the agent works |
+| **Files** | Inbound files land in `