tui

A live terminal dashboard for viewing subscription usage, spending, and recent coding-agent sessions. It refreshes its data in the background and offers conventional and expressive screen layouts.

In plain words
What is it for?
Use it to monitor the current week, spending trends, forecasts, and recent sessions from the terminal, with optional refresh and synchronization settings.
Why use it?
It puts current usage, cost trends, forecasts, and recent activity in one place instead of requiring separate commands or files. The displayed cost totals are transcript-based lower bounds, not exact billing totals.

Command

Install

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.

agentmods
npx agentmods add commands/omrikais/cctally/tui
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,889 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01889
Opus 5 $0.00000 $0.00945
Sonnet 5 $0.00000 $0.00378
Haiku 4.5 $0.00000 $0.00189

Measured 2d ago against content hash 131068bb7764, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tui 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 2d 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.

docs/commands/tui.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cctally tui

Live refreshing dashboard for subscription usage, spend, and recent-session activity. Renders with rich; background daemon thread keeps the data fresh while the main thread handles keys and redraws.

Cost coverage: Claude dollar and token totals are transcript-derived lower bounds, not exact /usage billing totals.

Maintenance status: the TUI is in bugfix-only maintenance mode as of the 2026-07-12 disposition decision. Both layout variants below keep working and remain fully supported, but the TUI no longer tracks new dashboard features. For the actively-developed rich UI, use cctally dashboard.

Two layout variants:

  • Conventional (default): a 2×2 grid — Current Week / Forecast on top, $/1% Trend / Recent Sessions on the bottom.
  • Expressive (--expressive or --variant expressive): a hero Current-Week meter beside a big trend sparkline, then a forecast strip, then full-width Recent Sessions.

Synopsis

cctally tui [--variant {conventional,expressive}]
                               [--expressive] [--refresh SECONDS]
                               [--sync-interval SECONDS] [--no-sync]
                               [--no-color] [--tz TZ]

Quick examples

# Default: conventional grid, 1 Hz UI tick, 10 s sync
cctally tui

# Hero / expressive layout
cctally tui --expressive

# Faster UI tick, slower sync
cctally tui --refresh 0.5 --sync-interval 20

# Frozen view: no background sync, render once with current data
cctally tui --no-sync

# Via the wrapper
cctally-tui --expressive

Flags

Flag Default Description
--variant {conventional,expressive} conventional Choose layout.
--expressive off Alias for --variant expressive.
--refresh SECONDS 1.0 UI tick cadence. Redraws when a key is pressed or this interval elapses.
--sync-interval SECONDS 10.0 How often the background daemon thread rebuilds DataSnapshot from the JSONL cache + SQLite.
--no-sync off Skip the background sync thread. The initial snapshot is still built; the UI stays frozen on it. Useful for screenshots and flaky-filesystem debugging.
--no-color off Disable ANSI color. Also honored: NO_COLOR env var.
--tz TZ config Display timezone for this call (local, utc, or IANA, e.g. America/New_York). Overrides config display.tz. See Display timezone for the full contract (parsing scope, JSON UTC invariant). Reset boundaries are always rendered in UTC for consistency with other subcommands.

Read the full file on GitHub · 154 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.

  1. 2d ago First seen · 154 lines · 0 tokens per session scan A 131068bb7764

Subscribe to this mod's changes

tui is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,889 tokens. 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.