Flightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission check, subagent cards and swimlanes, a turn receipt and a session log, all from real session events
What this mod can do
- Reviewed at commit 207968c
- Connects to the internet
- Reads environment variables
- Sees each prompt you send and can change or drop it
- Sees each tool call before it runs and can block or change it
- Can approve or deny each tool call before Claude Code asks you
- Sees each subagent before it starts and can stop it or pick its model
8 more things it can do
- Remembers data between sessions
- Plays sounds
- Can change or hide the status entries other mods show
- Can change or hide the transcript lines other mods add
- Adds the /deck command
- Lists running subagents
- Runs on a timer
- Runs on Claude Code hooks, such as session start
Good to know (3)
- The pet needs a terminal that shows images (Ghostty, Kitty, WezTerm or iTerm2); elsewhere it hides.
- The VS Code chat panel runs /deck commands but doesn't draw the panel; run claude in a terminal.
- Spend tracking stays off until you run /deck cost on.
Preview
Terminal
⎿ deck: Sample plan running above the prompt, with sample routing until real ones arrive.
[-]
0: deck ▾ · 5 rows /home/user/app · 16:02:53
⇄ Model route opus = opus jev: haiku · not applied effort ▁▃·· medi = kept ✕
✓ Orders module Done · 12/12 · 2/2 agents 100% ✕
● Context 44k / 200k 22% ✕
◔ Session · 5h 5h · 26% used ↻ 2:04:25 ✕
◔ Weekly · 7d 7d · 7% used ↻ 2d 0h 57m ✕
[ Deck 1 ]Claude Desktop
What it does
In the author's words
A cockpit for Claude Code: plan bars and subagent strips, context, usage limits with reset countdowns and burn rates, spend, the model route and a pet. Six bar styles, three collapsed looks. CLI and Desktop.
- What you see
- A collapsible panel above the prompt, or one line
- Works in
- Terminal and Claude Desktop
- Slash commands
- /deck
- Uses your tokens
- No
- Changes files
- Nothing
- Network access
- Weather from Open-Meteo, only once you set a city
- Reviewed commit
- 207968c
- Preview recorded with
- Claude Code 2.1.309
How it works
- Builds a plan bar from Claude's todo list, task tools or a plan you approve
- Adds a strip for each subagent, with its current tool, model and elapsed time
- Reads context and your 5h and 7d rate limits, with a countdown to each reset
- When a permission prompt or question waits on you, the row turns amber and an alert plays
Common questions
How do I see when my Claude Code usage limits reset?
Claude Code shows plan usage when you run /usage. Deck keeps your 5-hour and 7-day usage on screen instead, with percent used, a live countdown to each reset and a burn rate such as +12%/h.
Can I see which model each subagent is using?
Yes. Deck's agent strips show each subagent's current tool, the model it got and its elapsed time, under the plan bar that started it.
How do I make Deck take less space?
Run /deck or press 0 in an empty prompt to collapse it to one line. /deck collapsed chips, text or rings picks how that line looks.
Does Deck send my prompts anywhere?
No. Its only network requests go to Open-Meteo for the weather, and only when you set a city. The optional jev-model-router is a separate mod, and with a TypeSafe key it sends prompt text to TypeSafe.
Badge for your README
Own this listing? Add it to your README. The badge shows the install count as it grows.
[](https://staging.statuslin.es/mods/deck?utm_source=readme-badge)
Or show the preview card:
[](https://staging.statuslin.es/mods/deck?utm_source=readme-badge)
More like this
An animated pixel-art companion above your prompt that reacts to your session and your typing, with a live context meter.
One line above the prompt: context tokens with their weather, a bar per recent prompt, your 5-hour and 7-day limits against the time elapsed, the prompt cache with its time left, the session cost with the last prompt's share in dollars and in points of the 5-hour limit, the subagents running, and a one-click pill for the GOs Claude proposes. Labels in English, French or Russian. After Token Weather (Anthropic, Apache-2.0) and the ideas of usage-meter (HolyGrail) and prompt-cache-control (Daniel San).
Live session cost odometer above the prompt: a burning fuse, real-world comparisons, threshold alerts
Opus 4.8 high ✦ │ ctx 22% │ app (main) │ PR #1287 ● │ $0.41 · 10m +128 -34
Session ● ● ● ● ● ● ● ● ○ ○ ○ 74% left Resets in 2h 6m
Weekly ● ● ● ● ● ● ● ● ● ● ○ 93% left Resets in 2d 0h
Feature-rich bash status line with model, context bar, session cost (read live from Claude Code, so it stays correct on any model), rate-limit bars, and live tool/agent activity that adapts to terminal width. Source: github.com/JungHoonGhae/claude-statusline
✧ ███████████▋ 73% 🗝 Ultima Weapon ✦ app ∙ main
♥ ████████████████████████ 100% 「SAVE POINT」 ✶ Limit Form ◉ 41
Claude Code plan-usage HP bar that reads the Claude auth token to show remaining usage.
🤖 Opus 4.8 [200K] │ 🎯 high │ 📁 app │ 🌿 main
📅 07/07/26 Tue │ ⏰ 22:59:15 │ ₿$63k │ ☀️ +90°F
Ctx: ● ▓▓░░░░ 33% [66K/200K] │ ⏱ 10m │ 🔧 2.1.155
A three-line bar that mixes coding metrics with ambient real-world data: model, context and git on top; date, time, live weather from wttr.in and the Bitcoin price from Coinbase in the middle; a context bar with real token counts, session cost and Claude Code version below.
Opus 4.8 │ ✍️ 78% │ app (main) │ +128/-34
Cost $0.4100
Tokens in 44.0k │ cache write 5000 │ cache read 2000 │ out 1.4k
Compact status line showing model, context remaining %, directory/git, session time and lines changed, with rate-limit bars or a cost/token breakdown. Source: github.com/susomejias/claude-statusline