promptsonar: Skill for Claude Code

.agents/skills/karpathy-guidelines/SKILL.md

karpathy-guidelines is a skill for Claude Code, Codex from meghal86/promptsonar. It costs 50 tokens per session (380 once invoked), scanned A, original, MIT.

A set of coding guidelines for making small, deliberate changes while writing, reviewing, debugging, testing, or refactoring software. It emphasizes understanding the existing code, identifying the root cause, and defining how success will be checked.

In plain words
What is it for?
Planning code changes, fixing bugs, reviewing implementations, writing tests, refactoring carefully, and stating assumptions and verification criteria.
Why use it?
It reduces common agent mistakes such as unnecessary rewrites, speculative features, hidden assumptions, and changes outside the requested scope. The approach keeps edits easier to review and verify.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is meghal86/promptsonar's own configuration. It tells Claude Code and Codex how to work on promptsonar 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 promptsonar configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/meghal86/promptsonar/main/.agents/skills/karpathy-guidelines/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/meghal86/promptsonar

Made for: Claude Code, Codex.

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 karpathy-guidelines

README.md
[![agentmods](https://agentmods.dev/badge/skills/meghal86/promptsonar/karpathy-guidelines/github.svg)](https://agentmods.dev/skills/meghal86/promptsonar/karpathy-guidelines)
Your own site
<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.

agentmods 80×15 button for karpathy-guidelines

Your own site · 80×15
<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>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 380 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00050 $0.00380
Opus 5 $0.00025 $0.00190
Sonnet 5 $0.00010 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 12d ago against content hash c5b6b9e78a16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.agents/skills/karpathy-guidelines/SKILL.md · 56 lines

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.
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. 12d ago First seen · 56 lines · 50 tokens per session scan A c5b6b9e78a16

Subscribe to this mod's changes

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.

Related

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…

Agent-Threat-Rule/agent-threat-rules · 70 tokens

claude-d3js-skill

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.

Agent-Threat-Rule/agent-threat-rules · 25 tokens

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…

Agent-Threat-Rule/agent-threat-rules · 89 tokens

linear-claude-skill

Manage Linear issues, projects, and teams.

Agent-Threat-Rule/agent-threat-rules · 15 tokens

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.

Agent-Threat-Rule/agent-threat-rules · 60 tokens

terraform-skill

Terraform infrastructure as code best practices.

Agent-Threat-Rule/agent-threat-rules · 10 tokens