REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
The terminal that outlives its window. Shells survive quitting the app, agents can drive other agents, and remote machines work the same way. Pure Rust, GPU-rendered.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/l0ng-ai-tty7)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 tty7 | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | l0ng-ai | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 1,508 | 467,235 | 234,125 | 149,873 | 144,332 |
| 最近代码更新 | 2026年11月16日 | 2026年11月18日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | Apache-2.0 | MIT | – | Apache-2.0 | MIT |
l0ng-ai 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodexCursorGitHub CopilotOpenCode
依据开发者 README 和 repo 中的文件夹
GitHub account l0ng-ai (person), 9 years old
★ 1,508 stars · code last changed 2026年11月16日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 540261b (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (1211). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /tty7,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
npx skills add l0ng-ai/tty7摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/l0ng-ai/tty7.git /tmp/popnx-skill-l0ng-ai-tty7-540261b && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-l0ng-ai-tty7-540261b/skills/tty7' ~/.claude/skills/tty7ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 tty7 文件夹放到 ~/.agents/skills/tty7
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/l0ng-ai/tty7.git /tmp/popnx-skill-l0ng-ai-tty7-540261b && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-l0ng-ai-tty7-540261b/skills/tty7' ~/.agents/skills/tty7Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/l0ng-ai/tty7.git /tmp/popnx-skill-l0ng-ai-tty7-540261b && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-l0ng-ai-tty7-540261b/skills/tty7' ~/.agents/skills/tty7复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 tty7
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/l0ng-ai/tty7.git /tmp/popnx-skill-l0ng-ai-tty7-540261b && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-l0ng-ai-tty7-540261b/skills/tty7' ~/.cursor/skills/tty7适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月18日
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: tty7
description: >-
Drive the tty7 terminal workbench from the shell with the `tty7` binary — list workspaces/tabs/panes, split a pane, send text or keystrokes into one, capture what is on a pane's screen, run a command in a real PTY and pass its exit code through, run a command in a shell pane you already have and get back its output and exit code, block until a pane finishes or needs input, see which coding agents are running and which ports a pane is listening on. Use this whenever tty7, panes, workspaces, or `%42`/`@7`/"the other pane"/"the other agent" come up; whenever you want to hand work to another agent and collect the result ("get Claude/Codex to do X", "派个活", "let another agent handle this", running several agents in parallel and merging what they produce); whenever you need to start something long-running or interactive (dev server, REPL, ssh session, `tail -f`, a TUI) that should not sit blocking your Bash tool; whenever a program needs a real terminal to behave the way the user sees it; and whenever you need to look at or report on what is running in some *other* terminal on this machine. Cheap to check: if `$TTY7_PANE` is set you are already inside tty7 and every command here works with no setup.
---
# Driving tty7 from the command line
`tty7` is a thin, non-interactive client of the tty7 server. Every verb returns
and exits; `--json` makes the output machine-readable. The GUI never has to be
running — the server is what owns the panes.
## First: where are you?
```bash
tty7 doctor
```
One table, and it answers everything you need before doing anything else:
whether a server is reachable, whether the dialect matches, whether each agent's
status hooks are installed, and whether `TTY7_CONFIG_DIR` / `TTY7_WS` /
`TTY7_PANE` are set — i.e. whether you are running *inside* a tty7 pane.
Being inside a pane matters for two reasons: the address-taking verbs
(`split`, `send`, `exec`, `capture`, `procs`, `wait`, `pane close`) default to
`$TTY7_PANE`, and `run --keep` files its pane into `$TTY7_WS`. Outside a tty7
shell you must name a target explicitly, and the error will say so rather than
guessing.
The hooks row matters if you intend to delegate to another agent: without them
an agent reports no status, so `tty7 wait` on it will only ever time out.
If `tty7 doctor` says the server is unreachable, stop and tell the user — do
not run `tty7 server start` on your own initiative. Starting a server they
didn't ask for changes what their GUI attaches to.
## What are you here to do?
Four jobs, four shapes:
1. **Run something that shouldn't block you or needs a real TTY** — a dev
server, a long test run, a TUI. [Running a command](#running-a-command-two-shapes).
2. **Talk to something stateful over time** — a REPL, `ssh`, a debugger.
Same primitives: [send](#non-blocking-a-pane-you-talk-to-over-time),
[read](#reading-a-pane), repeat.
3. **Look at what this machine is doing** — other panes, other agents, ports.
[Looking around](#looking-around), strictly read-only.
4. **Hand work to another coding agent** — one worker or a fan-out of several.
Read `references/delegation.md` first; the short version is
[below](#handing-work-to-another-agent).
The Bash tool remains right for anything that starts, does its job, and exits
without needing a terminal or an audience. A pane earns its keep when the
process outlives your turn, needs a real PTY, or should be visible to the user
in their tty7 window — that last one is often the whole point.
## Addresses
| Shape | Means | Stable? |
|---|---|---|
| `%42` | a pane | yes — a pane keeps its id for its whole life |
| `@7` | a tab, numbered across the **whole machine** in tree order | **no** — it shifts whenever a workspace or tab appears or disappears |
| `@<full tab UUID>` | that same tab, by id | yes |
| `api` / `76698a44` / a full UUID | a workspace, by name, by unique id prefix, or by id | yes |
Re-resolve `@N` right before you use it; never cache one across a step that
creates or removes a tab. Pane ids, tab ids and workspace ids are safe to
remember — so when you create a tab and mean to address it again later, keep the
id `tty7 tab new --json` hands back rather than counting `@N` a second time.
The sigils are optional wherever an address is expected: `%42` and `42` are the
same pane, `@7` and `7` the same tab. Ids copied out of `--json` paste straight
back in.
Omitting the address inside a tty7 shell means "this pane" / "this workspace".
An explicit address always wins over the environment.
## Running a command: three shapes
### Blocking, with a real exit code
```bash
tty7 run -- cargo test # streams to your stdout, exits with cargo's code
tty7 run --cwd /path -- make
tty7 run --keep -- cargo build # leaves the pane as a new tab afterwards
```
The command's output streams to your stdout as it happens, and `tty7` exits
with the command's own exit code. This is the closest thing to a Bash call —
the difference is the PTY and the fact that the user can see it.
Three things to know. `--keep` needs a workspace, so it only works inside a tty7
shell or with `--ws <workspace>`. With `--json`, the streamed output comes first
and the JSON object last — the combined stream is *not* parseable as JSON, so
read the last line. And the pane is 120 columns wide with no way to change it,
so output that assumes a wider terminal wraps.
### Blocking, in a pane you already have
```bash
tty7 exec "$PANE" --timeout 900 -- cargo test # prints its output, exits with its code
```
`exec` types the line at the pane's shell prompt — its cwd, its environment,
its history — waits for the prompt to come back, prints what the command
printed (as text, like `capture --plain`; `--raw` keeps the escapes) and exits
with the command's own code. It is how you run the next command in a pane you
set up earlier (a `cd`, an activated venv, an `ssh` session with tty7's shell
integration on the far end) without the send / wait / capture / guess dance.
What it needs, and says when it doesn't have: the pane's shell must have tty7's
shell integration (a pane that has never sent a prompt mark is refused), and
the pane must be sitting at a prompt (a busy one is refused — `wait --until
free` first). The words after `--` become one shell line, so `&&`, pipes and
redirections work if you quote them: `tty7 exec %3 -- 'make && ./run'`. Always
give `--timeout` when nobody is watching: a line the shell never runs — an
unclosed quote waiting on `dquote>` — has no end to wait for. On timeout it
exits 124 and leaves the command running.
### Non-blocking: a pane you talk to over time
This is the one that makes tty7 worth reaching for. Get a pane, send it work,
come back later.
```bash
PANE=$(tty7 split --v) # or --h; splits $TTY7_PANE, prints "%83"
tty7 send "$PANE" 'npm run dev' --enter
```
`split` prints the new pane's address on stdout, which is what you capture into
a variable. Without an axis it is a usage error — `--v` stacks the new pane
below, `--h` puts it to the right.
Splitting `$TTY7_PANE` changes the user's visible layout, which is usually the
point: they can watch the dev server you started. Say that you did it, and close
the pane when you're done with it.
If you are *not* inside a tty7 pane there is nothing to split, so make your own
place to work first. `tty7 new --json /path/to/repo` hands you both ids at
once — don't go digging through `ws tree` for the pane:
```bash
read -r WS PANE < <(tty7 new --json /path/to/repo \
| python3 -c 'import json,sys; d=json.load(sys.stdin); print(d["id"], "%%%d" % d["pane"])')
```
`send` types text into the pane exactly as a keyboard would; `--enter` appends
the carriage return, or presses Enter on its own when you give it no text
(`tty7 send "$PANE" --enter` runs what is already typed there). It does not
wait and it does not tell you what happened — reading is a separate step, and
waiting is `tty7 wait`.
For keystrokes rather t提问、分享技巧或报告无法使用。按“有帮助”数量排序。