skill-telemetry

skill-telemetry is a cursor rule for Cursor from dewtech-technologies/dare-method. It costs 0 tokens per session (1,553 once invoked), scanned A, original, MIT.

Rastreamento de Tokens e Modelos do Cursor utilizados em cada etapa do DARE.

Cursor rule for Cursor

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 rules/dewtech-technologies/dare-method/skill-telemetry
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: Cursor.

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 skill-telemetry

README.md
[![agentmods](https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-telemetry.svg)](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-telemetry)
Your own site
<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-telemetry"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-telemetry.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.01553
Opus 5 $0.00000 $0.00776
Sonnet 5 $0.00000 $0.00311
Haiku 4.5 $0.00000 $0.00155

Measured today against content hash ee092f885a20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-telemetry 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 today.

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.

implementations/cursor/.cursor/rules/skill-telemetry.mdc · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rastreamento de Telemetria (Cursor - Tokens e Modelos)

Você é um especialista em monitoramento e observabilidade. Seu objetivo é rastrear e registrar o consumo de tokens e modelos de IA em cada etapa do Método DARE para fins de auditoria, monitoramento de performance e análise de uso. O Cursor é a IA utilizada (por compliance), então registre qual modelo do Cursor foi usado (GPT-4, Claude, Gemini, etc).

Modelos Disponíveis no Cursor

O Cursor suporta múltiplos modelos de IA. Registre qual foi utilizado em cada etapa:

Modelo Provedor Características Melhor Para
GPT-4 Turbo OpenAI Rápido e versátil Tarefas gerais, código
Claude 3.5 Sonnet Anthropic Análise profunda Análise complexa, segurança
Gemini 2.0 Flash Google Ultra rápido Tarefas simples, processamento rápido
Modelos Locais Customizados Privacidade total Dados sensíveis

Estrutura de Rastreamento

Cada etapa do DARE deve registrar as seguintes informações em um arquivo de telemetria:

Arquivo de Telemetria: DARE/TELEMETRY.md

Este arquivo centraliza todas as métricas de consumo. Ele deve ser atualizado ao final de cada comando executado.

# Telemetria do Projeto: [Nome do Projeto]

## Resumo Executivo
- **Projeto:** [Nome]
- **Data de Início:** [Data]
- **Tokens Totais Processados:** [Número] (monitoramento de uso)
- **IA Utilizada:** Cursor (por compliance)
- **Modelos do Cursor Utilizados:** [Lista de modelos]
- **Tempo Total de Execução:** [Tempo]

## Detalhamento por Etapa

### 1. Design (`/generate-design`)
- **Data/Hora:** [Timestamp]
- **Modelo do Cursor:** GPT-4 Turbo (ou Claude, Gemini)
- **Tokens Estimados:** 7,390
- **Tempo de Execução:** 45 segundos
- **Comando Executado:** `/generate-design "Criar API de autenticação"`
- **Observações:** [Qualidade da resposta, ajustes necessários, etc]

### 2. Blueprint (`/generate-blueprint`)
- **Data/Hora:** [Timestamp]
- **Modelo do Cursor:** GPT-4 Turbo (ou Claude, Gemini)
- **Tokens Estimados:** 21,373
- **Tempo de Execução:** 2 minutos
- **Arquivo Processado:** DARE/DESIGN.md
- **Observações:** [Qualidade da arquitetura, ajustes necessários, etc]

### 3. Tasks (`/generate-tasks`)
- **Data/Hora:** [Timestamp]
- **Modelo do Cursor:** GPT-4 Turbo (ou Claude, Gemini)
- **Tokens Estimados:** 33,912
- **Tempo de Execução:** 3 minutos 20 segundos
- **Arquivo Processado:** DARE/BLUEPRINT.md
- **Tasks Geradas:** 12
- **Observações:** [Qualidade das tasks, clareza das especificações, etc]

### 4. Execute Tasks (`/execute-task`)
- **Task 001: Migration de Users**
  - Data/Hora: [Timestamp]
  - Modelo do Cursor: GPT-4 Turbo (ou Claude, Gemini)
  - Tokens Estimados: 7,801
  - Tempo: 1 minuto 30 segundos
  - Tentativas (Ralph Loop): 1
  - Status: ✓ Sucesso

- **Task 002: AuthController**
  - Data/Hora: [Timestamp]
  - Modelo do Cursor: GPT-4 Turbo (ou Claude, Gemini)
  - Tokens Estimados: 11,357
  - Tempo: 2 minutos
  - Tentativas (Ralph Loop): 2
  - Status: ✓ Sucesso

[... mais tasks ...]

## Análise de Tokens Processados

| Etapa | Tokens Estimados | % do Total | Tempo Total |
|-------|------------------|-----------|-------------|
| Design | 7,390 | 5% | 45 seg |
| Blueprint | 21,373 | 15% | 2 min |
| Tasks | 33,912 | 24% | 3 min 20 seg |
| Execute (12 tasks) | 85,234 | 56% | 25 min |
| **TOTAL** | **147,909** | **100%** | **~31 min** |

## Modelos do Cursor Utilizados

- **GPT-4 Turbo:** 147,909 tokens (100%)
- **Claude 3.5 Sonnet:** 0 tokens (0%)
- **Gemini 2.0 Flash:** 0 tokens (0%)

Read the full file on GitHub · 157 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. today First seen · 157 lines · 0 tokens per session scan A ee092f885a20

Subscribe to this mod's changes

skill-telemetry is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,553 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 2026-09-03.