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/dotdevdotdev/agentwire-dev/agentwire-desktop-uinpx skills add dotdevdotdev/agentwire-dev --skill agentwire-desktop-uigit clone --depth 1 https://github.com/dotdevdotdev/agentwire-devWhat 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 | $0.00152 | $0.02773 |
| Opus 5 | $0.00076 | $0.01386 |
| Sonnet 5 | $0.00030 | $0.00555 |
| Haiku 4.5 | $0.00015 | $0.00277 |
Grade A, and why
agentwire-desktop-ui 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portal Desktop UI Patterns
Left Sidebar (click-toggle tab handle)
The portal uses a left sidebar with a floating tab handle instead of hover hotzone. A small tab (›) peeks from the left edge — click to slide sidebar open, click again to close. Click outside or press Escape to dismiss. Pin to keep visible (reflows desktop area).
Structure:
- Tab handle: floating 20×40px button on left edge, rides sidebar when open, chevron flips direction
- Header: connection status dot, session count, clock, pin toggle
- Open Windows section: lists currently-open windows (drag to reorder, click to focus, × to close). Persisted in
localStorage['taskbar-state']— restores on refresh. - Accordion sections: Sessions, Services, Machines, Projects, Artifacts, Scheduler, Safety, Config. Click header to expand/collapse. Data fetched on first expand.
- Footer: global PTT button, voice indicator
Session grouping: Sessions are split into two accordion sections based on the name:
- Services: infrastructure sessions. The built-in allowlist in
service-classification.js(agentwire-portal,agentwire-tts,agentwire-stt,agentwire-scheduler,agentwire-notifications) is merged at load time with config-defined custom services fetched from/api/services/custom(driven byservices.custominconfig.yaml). When the fetch resolves,notifyListeners()re-renders so flagged sessions hop into this column. - Sessions: everything else (working sessions, worktrees, remote sessions)
Both share session data from sessions-section.js (single fetch, shared activity state, pub-sub via onSessionsChanged).
Keyboard: Alt+] cycles forward through open windows, Alt+[ cycles backward — works everywhere including inside terminals (captured on window in capture phase before xterm, detected via e.code bracket keys). Tab and Shift+Tab are NEVER intercepted by the desktop; they always pass through to the focused terminal (Claude Code uses Tab for completion and Shift+Tab for permission modes — #659/#696).
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.
- yesterday First seen · 100 lines · 152 tokens per session scan A 00550e4015bb
agentwire-desktop-ui is a skill published in the GitHub repository dotdevdotdev/agentwire-dev (21 stars, last pushed 17d ago), licensed Apache-2.0. It adds 152 tokens to every session and 2,773 once invoked, about $0.0008 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
luvus-module
Write a luvus module (an extension for luvus, mission control for your AI coding agents). Use when the user is building or debugging a luvus module: authoring luvus-module.toml, adding a sidebar dock, Luvus Bar widget, right-click action, event hook, module pane, module settings, or calling luvus back over its UHP.
luvus
Control Luvus through its local CLI and UHP. Use only for a line beginning with =target message, an explicit request naming Luvus, a request to delegate to a named live Luvus agent or pane, or an explicit Luvus operation involving sessions, workspaces, tabs, panes, agents, files, Git, DIFF, worktrees, tasks, leases…
tmux-via-mcp
Use the tmux MCP tools to create sessions, shape layouts, run tracked commands, and automate interactive terminals when a real TTY or parallel panes are required.
tmux-buffer-explorer
Explore large tmux buffers via search and bounded slices. Use when buffer data is too large to load at once or needs incremental inspection.
not-happy-jan
Adjust Not-Happy-Jan feedback settings by running the nhj CLI when the user wants to tune voices, dials, muting, censoring, tests, or hold music.
release
Use when the user asks to release unitmux, bump the version, publish a GitHub release, update the Homebrew cask, check release status, or says リリース/release/バージョン上げて.