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.
npx agentmods add instructions/eschnou/gepetto/claude-mdgit clone --depth 1 https://github.com/eschnou/gepettoWrote 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/instructions/eschnou/gepetto/claude-md)<a href="https://agentmods.dev/instructions/eschnou/gepetto/claude-md"><img src="https://agentmods.dev/badge/instructions/eschnou/gepetto/claude-md.svg" alt="Measured on agentmods" 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 | $0.00561 | $0.00561 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
gepetto 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 6d 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
Gepetto Development Guide
Build Commands
# Build the project
./mvnw clean install
# Quick build (skip tests)
./mvnw clean package -P dev
# Run all Java tests
./mvnw test
# Run a single Java test
./mvnw test -Dtest=TestClassName#testMethodName
# Run application with specific command
./mvnw spring-boot:run -Dspring-boot.run.arguments="help"
./mvnw spring-boot:run -Dspring-boot.run.arguments="run gepetto/tasks/login.gpt --debug"
# Run from JAR (after building)
java -jar target/gepetto-0.0.1-SNAPSHOT.jar help
CLI Commands
init: Initialize a new Gepetto project (--var, -vto define variables)run <taskfile>: Execute a task file (options:--var, -v,--debug, -d,--no-report)version: Show version informationhelp [command]: Display help for commands
Code Style Guidelines
- Package structure: Maintain
sh.gepetto.appwith functional areas (config,model,service,cli) - Imports: No wildcards, standard Java first, then framework-specific imports
- Naming: PascalCase for classes, camelCase for methods/variables, UPPER_SNAKE_CASE for constants
- Error handling: Use try-catch with specific exceptions, log with SLF4J, return appropriate status codes
- Dependency injection: Use Spring's constructor injection
- Documentation: Maintain Javadoc for classes and public methods
Project Structure
After initialization, a Gepetto project will have the following structure:
gepetto/
├── config.yaml # Configuration
├── tasks/ # Generic automation tasks
│ ├── login.gpt # Example task file
└── results/ # Execution results
Task File Format
# Task Name
description: "Brief description of task purpose"
tags: [tag1, tag2]
author: "Author Name"
created: "YYYY-MM-DD"
Task:
Step 1 in natural language.
Step 2 in natural language.
...
Verification step in natural language.
Product Overview
Gepetto enables natural language task automation without programming knowledge. The app parses plain English task instructions, executes them automatically, and generates user-friendly reports. Focus on maintaining the core components: task parsing, execution service, and CLI commands.
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.
- 6d ago First seen · 65 lines · 561 tokens per session scan A 47f3b49634ca
gepetto CLAUDE.md is an instructions file published in the GitHub repository eschnou/gepetto (12 stars, last pushed 10mo ago), licensed MIT. It adds 561 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
hoop CLAUDE.md
Claude Code instructions for hoophq/hoop, covering claude.md, project overview, toolchain & prerequisites, architecture and module breakdown.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
rome CLAUDE.md
Claude Code instructions for rome-os/rome, covering rome, playbook and traps.
zapcode CLAUDE.md
Instructions for TheUncharted/zapcode, covering claude.md, git, read agents.md first, codebase orientation and how to add a new language feature.
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.