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 agentmods add skills/termio-sh/termio/termio-devicenpx skills add termio-sh/termio --skill termio-devicegit clone --depth 1 https://github.com/termio-sh/termioWrote 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/termio-sh/termio/termio-device)<a href="https://agentmods.dev/skills/termio-sh/termio/termio-device"><img src="https://agentmods.dev/badge/skills/termio-sh/termio/termio-device.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00099 | $0.00758 |
| Opus 5 | $0.00049 | $0.00379 |
| Sonnet 5 | $0.00020 | $0.00152 |
| Haiku 4.5 | $0.00010 | $0.00076 |
Grade A, and why
termio 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving sibling sessions (termiod)
If TERMIOD_SESSION_ID is not set in your environment, you are not running
inside a termiod session — say so and stop instead of trying to drive sessions
you cannot see.
You are running inside a session hosted by termiod on this machine, alongside
other sessions on the same host. Coordinate with them through the termiod
CLI. The installed CLI is the authority on syntax: where this text and
termiod --help disagree, trust the CLI.
Sessions here are scoped to this machine, not to a project. The daemon lists every session it hosts, so read the names and working directories before acting on one — there is no project filter to lean on.
termiod list --json— every session on this host, with its status (working/idle/needs_you/done/failed/unknown), name, and pid. Sessions are addressed by id or by name; both work everywhere a target is taken.termiod send <target> "<text>"— type into a session as if the user had. Use it to answer a sibling that is blocked on a question.--no-entertypes the text without pressing Enter.termiod create --name <name> --cwd <dir> -- <program> [args…]— start a new session and print its id. With no--argv it starts a login shell.termiod kill <target>— kill a session and its process group.termiod set-status "$TERMIOD_SESSION_ID" <state>— report your own state. Valid states areworking,idle,needs_you,done,failed, andunknown.--title "<short label>"sets the label a viewer shows beside the session.
When to use this
- Delegating. A task that is genuinely separate work — a long build, an independent investigation — can go to a new session so the user watches it in its own pane.
- Supervising. Before reporting that something is done, check whether a
sibling you started is still
workingor has goneneeds_you. - Unblocking. A sibling sitting at
needs_youis waiting on a human. If you can answer it from what you already know,sendthe answer.
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.
- 4d ago First seen · 56 lines · 99 tokens per session scan A 738b58c0fc7b
termio is a skill published in the GitHub repository termio-sh/termio (395 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 758 once invoked, about $0.0005 per session on Opus 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
workflows
Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.