/karpathy-guardrails
Behavioral guardrails for Forge agents based on Andrej Karpathy's principles — prevents over-engineering, silent assumptions, scope creep, and unfocused execution
$ npx -y skills add LucasDuys/forge --skill karpathy-guardrails --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/karpathy-guardrails
Context preview
The summary Claude sees to decide when to auto-load this skill.
Behavioral guardrails for Forge agents based on Andrej Karpathy's principles — prevents over-engineering, silent assumptions, scope creep, and unfocused execution
Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.
Repo: LucasDuys/forge
Other skills on forge.
- /backpropagation
Trace runtime bugs back to spec gaps — identify missing acceptance criteria, update specs, generate regression tests, and detect patterns
Open skill - /brainstorming
Interactive spec generation — turn ideas into concrete specs with R-numbered requirements and testable acceptance criteria
Open skill - /caveman-internal
Internal token optimization for Forge agent artifacts (handoff notes, artifact summaries, review notes). NOT exposed as a user-facing /caveman command.
Open skill - /collaborating
Hackathon-native multiplayer collaboration mode -- brain-dump together, claim tasks across machines, flag decisions async. Drives the subcommands of /forge:collaborate.
Open skill - /design-system
DESIGN.md integration for Forge — ensures visual consistency across all UI tasks through standardized design specifications
Open skill - /executing
Autonomous task implementation workflow — implement, test, review, commit for each task in the frontier
Open skill