SaltoInicial: Instructions file for Claude Code

CLAUDE.md

SaltoInicial CLAUDE.md is an instructions file for Claude Code from dgfigueroa29/SaltoInicial. It costs 3,340 tokens per session, scanned A, original, MIT.

A project guide for an Android app that displays a website inside a native Jetpack Compose app. It lists the app structure, build commands, tests, code checks, and local handling of secret keys.

In plain words
What is it for?
Building debug or release versions, running unit and device tests, checking code quality with Detekt, cleaning builds, and installing the app on a connected device.
Why use it?
It gives coding agents the project context and commands they need, while warning them not to commit passwords, tokens, or signing files.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is dgfigueroa29/SaltoInicial's own configuration. It tells Claude Code how to work on SaltoInicial itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SaltoInicial configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dgfigueroa29/SaltoInicial. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dgfigueroa29/SaltoInicial/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dgfigueroa29/SaltoInicial

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 SaltoInicial CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dgfigueroa29/saltoinicial/claude-md/github.svg)](https://agentmods.dev/instructions/dgfigueroa29/saltoinicial/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dgfigueroa29/saltoinicial/claude-md"><img src="https://agentmods.dev/badge/instructions/dgfigueroa29/saltoinicial/claude-md/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.

agentmods 80×15 button for SaltoInicial CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dgfigueroa29/saltoinicial/claude-md"><img src="https://agentmods.dev/badge/instructions/dgfigueroa29/saltoinicial/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,340 This file is loaded in full into every session.
When invoked 3,340 The same file — it is already loaded in full.
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 $0.03340 $0.03340
Opus 5.5 $0.01336 $0.01336
Sonnet 5.5 $0.00668 $0.00668
Haiku 4.5 $0.00334 $0.00334

Measured 2mo ago against content hash 050fbbe9cd30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SaltoInicial CLAUDE.md 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 2mo 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.

CLAUDE.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Descripción

SaltoInicial es una app Android que envuelve el sitio web https://www.saltoinicial.com.ar/ en un WebView nativo con Jetpack Compose. Es un proyecto de módulo único (:app).

Repositorio público: nunca commitear claves, tokens, DSNs ni keystores. Ver Configuración local.

Comandos

# Compilar debug
./gradlew assembleDebug

# Compilar release (con R8 + shrinkResources)
./gradlew assembleRelease

# Ejecutar tests unitarios
./gradlew test

# Ejecutar tests instrumentados (requiere dispositivo/emulador)
./gradlew connectedAndroidTest

# Ejecutar un test específico
./gradlew testDebugUnitTest --tests "com.boa.saltoinicial.presentation.viewmodel.MainViewModelTest"

# Análisis estático (config en config/detekt/detekt.yml, autoCorrect activado)
./gradlew detekt

# Limpiar build
./gradlew clean

# Instalar en dispositivo conectado
./gradlew installDebug

Configuración local

Los SDKs de terceros se configuran con claves inyectadas en BuildConfig en tiempo de compilación. Van en local.properties (ignorado por git) o como propiedades de Gradle (-PclaveX=valor):

appsFlyerDevKey=
amplitudeApiKey=
sentryDsn=
newRelicAppToken=
mixpanelProjectToken=
facebookAppId=
facebookClientToken=

Cada clave ausente degrada con gracia: el SDK correspondiente no se inicializa y se loguea una advertencia con Timber. La app compila y corre sin ninguna de ellas.

facebookAppId y facebookClientToken además se inyectan como manifestPlaceholders.

local.properties nunca debe commitearse. app/google-services.json sí está versionado: la API key de Firebase que contiene no es un secreto (es extraíble de cualquier APK), pero la seguridad real depende de las Firebase Security Rules y de App Check, no de ocultar ese archivo.

Arquitectura

Clean Architecture en tres capas dentro del módulo :app, con patrón MVI en presentación y DI manual vía ViewModelProvider.Factory (sin Hilt).

Read the full file on GitHub · 247 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. 2mo ago First seen · 247 lines · 3,340 tokens per session scan A 050fbbe9cd30

Subscribe to this mod's changes

SaltoInicial CLAUDE.md is an instructions file published in the GitHub repository dgfigueroa29/SaltoInicial (6 stars, last pushed 1mo ago), licensed MIT. It adds 3,340 tokens to every session, about $0.0134 per session on Opus 5.5. 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.

Related

SaltoInicial CLAUDE.md compared with instructions from other repositories

SaltoInicial CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
SaltoInicial CLAUDE.mddgfigueroa29/SaltoInicialInstructions file61mo agoMITA3,340Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode