tty7 is a Rust terminal workbench in which a background server keeps shells, panes, and supported coding-agent sessions running independently of the window. Developers use it for local or SSH-based work, persistent sessions, repository-aware terminal tasks, and coordination between coding agents. The catalogue entry provides a skill for working with tty7.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add l0ng-ai/tty7 --skill tty7git clone --depth 1 https://github.com/l0ng-ai/tty7Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/l0ng-ai/tty7/tty7)<a href="https://agentmods.dev/skills/l0ng-ai/tty7/tty7"><img src="https://agentmods.dev/badge/skills/l0ng-ai/tty7/tty7/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/l0ng-ai/tty7/tty7"><img src="https://agentmods.dev/badge/skills/l0ng-ai/tty7/tty7.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00293 | $0.04643 |
| Opus 5.5 | $0.00117 | $0.01857 |
| Sonnet 5.5 | $0.00059 | $0.00929 |
| Haiku 4.5 | $0.00029 | $0.00464 |
Grade A, and why
tty7 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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?
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:
- Run something that shouldn't block you or needs a real TTY — a dev server, a long test run, a TUI. Running a command.
- Talk to something stateful over time — a REPL,
ssh, a debugger. Same primitives: send, read, repeat. - Look at what this machine is doing — other panes, other agents, ports. Looking around, strictly read-only.
- Hand work to another coding agent — one worker or a fan-out of several.
Read
references/delegation.mdfirst; the short version is below.
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.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 26d ago Changed · +35 lines · +19 tokens per session 11156111ecf7
- 1mo ago First seen · 326 lines · 274 tokens per session scan A 74919b5a3562
tty7 is a skill published in the GitHub repository l0ng-ai/tty7 (1,306 stars, last pushed yesterday), licensed Apache-2.0. It adds 293 tokens to every session and 4,643 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
audiobook-maker
A workflow for turning long text, novels, and reports into spoken audio files. Text longer than 3,000 Chinese characters is split into smaller sections before speech is generated.
obsidian-sync
Refresh Obsidian dashboard and daily notes from current experiment state.
pxb-liepin
A Chinese-language workflow for finding and screening job candidates through Liepin, a Chinese recruitment platform, while keeping job descriptions, candidate records, and duplicate checks organized.
herdr
Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDRENV=1).
vault-setup
Set up a machine to work with a workhub vault - check/install required software (git, Node.js, Claude Code, OpenCode), initialize the vault if needed, wire up Claude plugins, and run the OpenCode sync scripts. Use when onboarding a new machine, after a fresh vault-init, or when the harness feels half-configured.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.