An inline chat tool for terminalhire connections, where developers can exchange end-to-end encrypted messages. It reads the inbox or a conversation and can send replies without leaving the current terminal session.

Viewing invitations and messages, reading conversations, and replying to developers you have connected with.

It removes the need to switch windows or take over the terminal with a separate chat interface when checking connection messages.

chat — Skill for Claude Code by staqsIO

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add staqsIO/terminalhire-plugin

Claude Code

/plugin install terminalhire

Made for: Claude Code.

Or install terminalhire, the plugin that ships this one along with the rest of its 7 skills, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/staqsio/terminalhire-plugin/chat.svg)](https://agentmods.dev/skills/staqsio/terminalhire-plugin/chat)

Your own site

<a href="https://agentmods.dev/skills/staqsio/terminalhire-plugin/chat"><img src="https://agentmods.dev/badge/skills/staqsio/terminalhire-plugin/chat.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,220 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00064	$0.01220
Opus 5	$0.00032	$0.00610
Sonnet 5	$0.00013	$0.00244
Haiku 4.5	$0.00006	$0.00122

Measured 7d ago against content hash 93641ed2a153, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

chat 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 7d 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.

plugins/terminalhire/skills/chat/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

terminalhire:chat

Read and reply to your end-to-end-encrypted connection chats inline in this session — no terminal takeover, no window switch. Messages are E2E encrypted with keys that stay on the device; only ciphertext crosses the wire, and the connection check uses the existing web-session cookie (the GitHub token never leaves the machine).

These are the on-demand reader modes — each prints into the conversation and exits. (The live both-typing pane, node "${CLAUDE_PLUGIN_ROOT}/dist/bin/jpi-dispatch.js" chat <login> with no flag, is a separate raw-mode TUI and is not used here.)

Selectable actions — the inline picker (PREFERRED entry point)

Make the chat surface feel native to Claude Code: rather than only printing text + a copy-paste command, turn the actionable items into a selectable prompt the user arrow-keys through — the same selection widget behind the harness's own pickers. This is the assistant-driven AskUserQuestion tool, NOT a raw-mode TUI; never take over the terminal.

When the user opens chat or asks about messages/connections/invitations:

Run chat --inbox (below) to get current state: PENDING INVITATIONS (incoming, awaiting accept), and accepted connections with their unread (✉ N) + last preview.
If there is anything actionable, present it with AskUserQuestion as one selectable list — most-actionable first, one option per item:
- Accept @<login> — an incoming invitation → on pick, run … intro --accept @<login> and confirm the new connection.
- Open @<login> · 💬 N unread — a connection with unread → on pick, run chat <login> --read.
- Open @<login> — a read connection → chat <login> --read.
- Include a plain escape option (e.g. "Just print the inbox" / "Nothing now").
After the pick, run the matching command and report the result. For a reply, ask for the line, then chat <login> --send "…". You may chain (e.g. accept → then offer "say hi").
If the user wants to browse/manage everything themselves, mention node "${CLAUDE_PLUGIN_ROOT}/dist/bin/jpi-dispatch.js" inbox — the interactive full-screen inbox (navigate conversations, open threads, accept/decline invitations, mark read). It's for THEM to run in their own terminal; never launch it from a skill (it's a raw-mode TUI).

Read the full file on GitHub · 70 lines

Changes

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.

7d ago First seen · 70 lines · 64 tokens per session scan A 93641ed2a153

Subscribe to this mod's changes

chat is a skill published in the GitHub repository staqsIO/terminalhire-plugin (2 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,220 once invoked, about $0.0003 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 2026-08-31.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens