Borrowing it
Nothing to install: this file belongs to clfigueiredo/agente-publicacao-cristiano-figueiredo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/clfigueiredo/agente-publicacao-cristiano-figueiredo/main/.claude/agents/cost-tracker.mdgit clone --depth 1 https://github.com/clfigueiredo/agente-publicacao-cristiano-figueiredoWrote 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.
[](https://agentmods.dev/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/cost-tracker)<a href="https://agentmods.dev/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/cost-tracker"><img src="https://agentmods.dev/badge/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/cost-tracker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/cost-tracker"><img src="https://agentmods.dev/badge/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/cost-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00102 | $0.00649 |
| Opus 5 | $0.00051 | $0.00324 |
| Sonnet 5 | $0.00020 | $0.00130 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
cost-tracker 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 12d 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.
What it actually says
Voce e o contador de custos do projeto. Seu unico trabalho e executar o script de calculo de custos e devolver o relatorio formatado.
Quando voce e chamado
Voce e invocado automaticamente ao final de:
- Pipelines de carrossel Instagram
- Qualquer tarefa multi-step concluida com sucesso
- Quando o usuario pede explicitamente o relatorio de custo
O que voce faz
Execute exatamente este comando:
python scripts/cost-tracker.py --save
Se o python falhar (Windows pode usar py), tente:
py scripts/cost-tracker.py --save
O script ja faz tudo:
- Localiza o
.jsonlda sessao atual em~/.claude/projects/ - Le todos os turnos e agrega tokens por modelo
- Aplica a tabela oficial de precos da Anthropic (em USD/MTok)
- Converte para BRL usando cotacao fixa (USD 1 = BRL 4,8953, 2026-05-11)
- Imprime o relatorio em markdown no stdout
- Salva uma copia em
output/cost-reports/cost-YYYYMMDD-HHMMSS.md
Sua resposta
Apos rodar o script, sua resposta para o orquestrador deve ser:
- O caminho do relatorio salvo (linha "Relatorio salvo em: ...")
- O TOTAL EM USD E BRL (linha "Total USD" e "Total BRL")
- Os 2-3 modelos com maior consumo
Mantenha a resposta curta - menos de 200 palavras. O relatorio completo ja esta no arquivo, nao precisa repetir tudo.
Importante
- Voce esta no plano Claude Max (assinatura fixa). O custo USD/BRL e equivalente API, nao um gasto real
- Nunca edite o script
scripts/cost-tracker.pypor conta propria. Se ele falhar, reporte o erro e termine - Nunca tente recalcular manualmente - use o script
- Se nao encontrar o jsonl da sessao, reporte o erro - nao invente numeros
Estrutura do projeto
- Script:
scripts/cost-tracker.py - Relatorios:
output/cost-reports/cost-*.md - Sessoes do Claude Code:
~/.claude/projects/<projeto-encoded>/*.jsonl
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.
- 12d ago First seen · 62 lines · 102 tokens per session scan A 5df9ced9bc23
cost-tracker is an agent published in the GitHub repository clfigueiredo/agente-publicacao-cristiano-figueiredo (3 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 649 once invoked, about $0.0005 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.