custo-hoje

custo-hoje is a command for Claude Code from luanpdd/kit-mcp. It costs 26 tokens per session (1,166 once invoked), scanned A, original, MIT.

A cost-reporting command for Claude Code that shows the current day’s spending in US dollars and token usage, broken down by model.

In plain words
What is it for?
Use it to inspect today’s model costs, optionally save a cost snapshot, or refresh pricing for models not in the built-in pricing data.
Why use it?
It gives developers a way to see what their Claude Code work is costing and distinguish real usage costs from other project metrics.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

Good fit Use it to inspect today’s model costs, optionally save a cost snapshot, or refresh pricing for models not in the built-in pricing data.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/luanpdd/kit-mcp/custo-hoje
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.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code.

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.

agentmods badge for custo-hoje

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/custo-hoje.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/custo-hoje)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/custo-hoje"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/custo-hoje.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,166 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.01166
Opus 5 $0.00013 $0.00583
Sonnet 5 $0.00005 $0.00233
Haiku 4.5 $0.00003 $0.00117

Measured 5d ago against content hash df22fd1de6d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

custo-hoje 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 5d 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.

kit/commands/custo-hoje.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lê: JSONLs descobertos via CLAUDE_CONFIG_DIR (multi-account) → XDG_CONFIG_HOME/claude~/.claude (POSIX) / %APPDATA%/claude (Windows), filtrando projects/<slug>/*.jsonl.

Cria/Atualiza: nada por default. Com --persist, grava snapshot em .planning/costs/<ts>-cost-today.json (gitignored).

Após: o user vê tabela compacta total_usd + breakdown by_model + flags de qualidade (unknown_models, pricing_staleness_days).

Disambiguation: este comando é sobre USD/tokens reais gastos — NÃO sobre error budget de SLO (use /burn-rate-status para isso). Ver skill cost-tracking para detalhes.

Flags:

  • --tz <IANA> — timezone do "dia". Default: UTC (paridade ccusage). Exemplo: --tz America/Sao_Paulo.
  • --refresh-pricing — opt-in fallback models.dev para modelos não cobertos pelo snapshot embedded. Side-effect: HTTP fetch + cache em ~/.kit-mcp/pricing-cache.json (TTL 24h). NÃO use por padrão.
  • --persist — grava snapshot do output em .planning/costs/.

Cross-reference: comando ↔ MCP tool. A SSOT do shape de output e do pipeline parser→dedup→price é a skill cost-tracking + os módulos em src/core/cost/. Este comando é apenas o wrapper PT-BR de invocação no Claude Code.

1. Parsear argumentos

TZ=$(echo "$ARGUMENTS" | grep -oE -- '--tz [^ ]+' | awk '{print $2}')
REFRESH=$(echo "$ARGUMENTS" | grep -oE -- '--refresh-pricing' | head -1)
PERSIST=$(echo "$ARGUMENTS" | grep -oE -- '--persist' | head -1)

2. Invocar MCP tool cost-today

Chame o tool cost-today com:

{
  "tz": "<TZ ou omitir para UTC>",
  "refresh_pricing": <true se --refresh-pricing, senão omitir>,
  "persist": <true se --persist, senão omitir>
}

Read the full file on GitHub · 97 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. 5d ago First seen · 97 lines · 26 tokens per session scan A df22fd1de6d1

Subscribe to this mod's changes

custo-hoje is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,166 once invoked, about $0.0001 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 2026-09-03.