Mention Chips That Show What They Do
Every chip in Agent Input shows what Send will do with it. A new agent has a dashed outline and a ＋ on its logo, a linked terminal has a solid outline and a live dot, a project sits under a folder tab, and a terminal on a paired computer carries that computer's name and an online or offline dot.
Why You Need This
How this feature boosts your daily productivity
One prompt can start a new Codex terminal, hand work to a Claude that is already running, bring in another project's context and reach an agent on your Mac mini. When every mention looked the same, you couldn't tell which chip would start a new terminal and which would reach one that was already running, or whether the other computer was even online, until after you pressed Send. Now each kind has its own shape. New agents are dashed with a ＋, linked terminals are solid with a live dot, projects show their avatar under a folder tab, and paired-computer terminals show the computer's name with a green or amber presence dot plus → for Send once or ⇄ for Converse. Hover any chip and it spells out what will happen, such as spawns a new Codex terminal when you send.
How It Works
Get started in 4 simple steps
Type @ in Agent Input
Pick an agent, an open terminal, a project or a terminal on a paired computer from the picker.
Read the chip
Dashed with ＋ starts a new agent, solid with a live dot is a linked terminal, a folder tab is a project, and a shaded computer name is a paired computer.
Check before you send
Hover a chip for what Send will do with it, drag it to move, or drop it on another chip to swap them.
Press Send
The agent receives the same text it always did. Chips are stored as @name, so drafts keep them.
Without 1DevTool
The manual way vs. the 1DevTool way
The Hard Way
The 1DevTool Way
Key Capabilities
Everything included with Mention Chips That Show What They Do
Why It Matters
The productivity impact of having ai productivity built into your workspace
No Surprise Terminals
A dashed chip with a ＋ tells you Send will start a new agent, before it happens.
Know Where It Lands
A paired computer's name and presence dot sit on the chip, so you see an offline machine before you send.
Prompts Still Read Well
Names stay at text size and colour stays in the logo, so a prompt with many mentions is still easy to read.
More in AI Productivity
Other features in this category you might find useful
Prompt History
Search prompts and sticky notes from Remote Control while away from the desktop. Switch between This project and All projects, filter prompts by agent or notes by source, copy entries, delete with Operator access, and sync local prompt history.
Resume UI
Read any past AI session before you resume it. Resume AI Sessions is a split view with a searchable list of every Claude Code, Codex, Gemini CLI and other agent session on the left and a live preview of the project, branch, tool calls and conversation on the right, with replies rendered as Markdown, with Resume, bypass permissions and an editable command one click away.
Combine Sessions
Merge several past AI sessions into one opening prompt, or hand a single session to a different agent. Tick sessions in Resume AI Sessions, see a token estimate of the context they add, and send the result to a new chat with any agent or preset or to a terminal that is already open.
AI Diff Review Panel
Track every file modification any AI agent makes — Claude Code, Codex, Gemini, Amp, custom — and review, accept, or revert their work per file from a dedicated panel with inline diff overlays in the editor.
Ready to boost your workflow?
Download 1DevTool for free and experience Mention Chips That Show What They Do along with 340 other features — all in one app.