From 0945c312f2f389106ca0be93d583d8ad26a2607c Mon Sep 17 00:00:00 2001 From: Thomas Kosiewski Date: Sat, 6 Jun 2026 14:22:16 +0200 Subject: [PATCH] docs(readme): move Codex/Claude demos above the fold Relocate the Demos section from after "Where it came from" (section 11 of 16) to right after "What you'd use it for", before Quickstart. The agent demos are the strongest proof of the tool but were buried behind a backstory section most readers never scroll to. New top-of-README flow lands them right when a reader is asking "does this actually work with a real agent?": hero GIF -> intro -> What you'd use it for -> Demos -> Quickstart Pure move: demo copy, videos, and the #demos anchor are unchanged. Change-Id: I595fd5c88a87156b244d6780f58092c458ca6a9c Co-Authored-By: Claude Opus 4.8 (1M context) Signed-off-by: Thomas Kosiewski --- README.md | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/README.md b/README.md index bf63fc40..3f24509a 100644 --- a/README.md +++ b/README.md @@ -19,6 +19,23 @@ Tools like `tmux` or `screen` help _you_ manage your own terminal windows. `agen - **A tighter feedback loop.** Tell the agent to actually _use_ the TUI it just built or fixed, then read the screen back, so it catches a broken layout itself before you ever see it. - **Reproducing terminal bugs.** Spin up a clean, isolated terminal, reproduce a flaky TUI bug report there, hand it to an agent to attempt a fix, and verify the fix with a fresh recording. +## Demos + +Real Codex and Claude TUIs discovering the `agent-tty` skill, driving `nvim --clean`, writing a file, and exporting inner proof artifacts. (GitHub renders these as click-to-play players.) + + + + + + + + + + +
CodexClaude
+ +Full reproducer, transcripts, and proof bundles are in [`dogfood/agent-uses-agent-tty/`](./dogfood/agent-uses-agent-tty/) and [`dogfood/CATALOG.md`](./dogfood/CATALOG.md). + ## Quickstart Requires Node `>=24 <27`. Screenshots and WebM video also need a Playwright Chromium install (`npx playwright install chromium`). @@ -92,23 +109,6 @@ I maintain [`coder/claudecode.nvim`](https://github.com/coder/claudecode.nvim) a A colleague then used `agent-tty` to build an experimental TUI for Coder agents almost entirely by letting coding agents drive it, checking the screenshots and recordings it produced instead of watching over their shoulder. That's the loop it's built for: an agent acts, `agent-tty` captures reviewable evidence, and a human (or another agent) verifies. -## Demos - -Real Codex and Claude TUIs discovering the `agent-tty` skill, driving `nvim --clean`, writing a file, and exporting inner proof artifacts. (GitHub renders these as click-to-play players.) - - - - - - - - - - -
CodexClaude
- -Full reproducer, transcripts, and proof bundles are in [`dogfood/agent-uses-agent-tty/`](./dogfood/agent-uses-agent-tty/) and [`dogfood/CATALOG.md`](./dogfood/CATALOG.md). - ## Command surface Every user-facing command takes `--json` and returns a stable, machine-readable envelope. The commands cover the session lifecycle (`create`, `list`, `inspect`, `destroy`, `gc`), input and control (`run`, `type`, `paste`, `send-keys`, `batch`, `resize`, `signal`, `mark`), observation and capture (`wait`, `snapshot`, `screenshot`, `record export`), the live `dashboard`, and environment checks (`version`, `doctor`, `skills`).