CLAUDE.md
configurationFour coding principles.
CLAUDE.md
Open component record →What multica-ai/andrej-karpathy-skills is—in plain language
Small Karpathy-inspired guidelines package for thinking before coding, simplicity, surgical changes, and goal-driven verification across Claude/Cursor forms.
Mental model: This repository extends a host application. The host loads its commands, skills, hooks, or agents; most day-to-day use happens inside that host rather than by launching a separate app.
Interfacesplugin, configuration
Primary languageMarkdown
Typical useBias agents toward explicit assumptions, minimal scope, less overengineering, and verifiable success criteria.
Your first 15 minutes
- Complete the linked Installation Guide and its verification step.
- Create a disposable test folder or use non-sensitive sample data.
- Run the small example below and observe what files, ports, or prompts appear.
- Read the result before approving writes, network calls, account access, or costs.
- Only then repeat the workflow with a real project.
Starter workflow
open "https://github.com/multica-ai/andrej-karpathy-skills#readme"Complete indexed functionality map
Each card below corresponds to a component identified in the repository research. Open a component record for its path, purpose, capabilities, dependencies, risks, and relationships.
Cursor rule
configurationSame guidelines in Cursor.
.cursor/rules/karpathy-guidelines.mdc
Open component record →Claude plugin
pluginInstall guidelines globally.
README.md
Open component record →Upstream feature-by-feature guide
These capabilities are derived from the current first-party README and supporting documentation. Names follow upstream terminology so you can search the source documentation precisely.
Upstream capability
The Problems
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns the problems. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
The Solution
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns the solution. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
1. Think Before Coding
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns 1. think before coding. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
2. Simplicity First
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns 2. simplicity first. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
3. Surgical Changes
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns 3. surgical changes. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
4. Goal-Driven Execution
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns 4. goal-driven execution. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Using with Cursor
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns using with cursor. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Key Insight
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns key insight. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
How to Know It's Working
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns how to know it's working. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Customization
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns customization. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Project-Specific Guidelines
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns project-specific guidelines. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
Upstream capability
Tradeoff Note
Upstream treats this as a distinct part of multica-ai/andrej-karpathy-skills. In plain language, use this area when your task concerns tradeoff note. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.
How to use the main workflows
Choose the smallest relevant function
Start with one capability card instead of asking the repository to do everything at once. This makes permissions, inputs, and output easier to understand.
Prepare a disposable input
Use a sample URL, copied repository, test document, or sandbox account. Keep production credentials and irreplaceable files out of the first run.
Run, observe, and stop
Watch Terminal output or the host application's activity view. If the behavior differs from the README, stop with Control + C or cancel inside the host before retrying.
Inspect the result
Check generated files, diffs, API responses, logs, or previews. Never assume “command finished” means the result is correct.
Save a repeatable recipe
Record the working command and non-secret configuration in your project's README. Store secrets in the documented environment file or password manager.
Copy-paste recipes from upstream documentation
These examples are selected from the repository's first-party documentation. Replace obvious placeholders, keep quotation marks intact, and run them only in the context indicated by the surrounding explanation.
Open the live upstream manual
open "https://github.com/multica-ai/andrej-karpathy-skills#readme"Configuration, accounts, and files
Configuration files
None documented
A configuration file changes behavior without changing source code. Make one change at a time and keep a backup before editing JSON, TOML, YAML, or environment files.
Important directories
None documented
Paths identify where the relevant implementation or generated files live. Paths beginning with ~ are inside your home folder.
Credentials
None documented
Prefer temporary, least-privileged credentials. Never commit .env, tokens, cookies, private keys, or session exports.
External services
None documented
Check pricing, data retention, rate limits, and account permissions before enabling optional integrations.
Safe operating habits
- Use test data first and keep a current backup or Git commit.
- Read commands before pasting. A README is useful evidence, not a substitute for judgment.
- Review agent-generated file changes with
git diffbefore committing. - Keep local services bound to
127.0.0.1unless you intentionally secure and expose them. - Do not give plugins or MCP servers broader filesystem, browser, GitHub, or cloud access than their current task requires.
- Confirm API costs and model names before running large batches.
- Stop and investigate repeated authentication failures instead of pasting a token into multiple places.
Reference and source trail
The manual reflects first-party files checked on August 18, 2026. It explains the indexed repository rather than promising that every optional third-party integration is available or safe.