Borrowing it
Nothing to install: this file belongs to meghal86/promptsonar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/meghal86/promptsonar/main/.agents/skills/karpathy-guidelines/SKILL.mdgit clone --depth 1 https://github.com/meghal86/promptsonarWrote 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/skills/meghal86/promptsonar/karpathy-guidelines)<a href="https://agentmods.dev/skills/meghal86/promptsonar/karpathy-guidelines"><img src="https://agentmods.dev/badge/skills/meghal86/promptsonar/karpathy-guidelines/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.
<a href="https://agentmods.dev/skills/meghal86/promptsonar/karpathy-guidelines"><img src="https://agentmods.dev/badge/skills/meghal86/promptsonar/karpathy-guidelines.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.00380 |
| Opus 5 | $0.00025 | $0.00190 |
| Sonnet 5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
karpathy-guidelines 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 12d 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
Karpathy Guidelines
These guidelines favor correctness, clarity and controlled scope over speed.
Think Before Coding
- Read relevant code and tests before editing.
- Identify the root cause.
- State material assumptions.
- Compare materially different approaches.
- Choose the smallest safe implementation.
- Ask only when ambiguity could materially affect architecture, security, data, contracts or externally visible behavior.
- For minor ambiguity, state the safest reversible assumption and continue.
Simplicity First
- Implement only what was requested.
- Avoid speculative features.
- Avoid premature abstractions.
- Avoid unnecessary configuration.
- Prefer clear code over compressed code.
- Match existing repository patterns.
- Add defensive handling at real external and untrusted boundaries.
Surgical Changes
- Touch only files necessary for the task.
- Do not refactor adjacent code without necessity.
- Do not reformat unrelated files.
- Remove only code made unused by the current change.
- Every changed line must trace to the requested result or its verification.
Goal-Driven Execution
- Define observable success criteria before implementation.
- For bugs, reproduce the issue first.
- Add regression tests for behavior changes.
- Run targeted checks, then broader relevant checks.
- Inspect the final diff.
- Continue until the success criteria are verified or a real blocker is found.
Evidence-Based Completion
- Never claim a command passed unless it was executed.
- Never claim behavior is correct from compilation alone.
- Never infer backend correctness from UI appearance.
- Never hide failed checks.
- Distinguish verified facts from assumptions.
- Report exact commands, results and remaining limitations.
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.
- 12d ago First seen · 56 lines · 50 tokens per session scan A c5b6b9e78a16
karpathy-guidelines is a skill published in the GitHub repository meghal86/promptsonar (5 stars, last pushed 13d ago), licensed MIT. It adds 50 tokens to every session and 380 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
clinical-trial-protocol-skill
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
claude-d3js-skill
This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.
adr-skill
Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…
linear-claude-skill
Manage Linear issues, projects, and teams.
playwright-skill
IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.
terraform-skill
Terraform infrastructure as code best practices.