What makes Karpathy Guidelines notable?

2K downloads. Trust evidence available

How should Karpathy Guidelines be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Karpathy Guidelines

engineering execution guardrails for coding, implementing features, fixing bugs, debugging failures, reviewing diffs, refactoring code, simplifying overbuilt... Skill: Karpathy Guidelines Owner: gmvp3 Summary: engineering execution guardrails for coding, implementing features, fixing bugs, debugging failures, reviewing diffs, refactoring code, simplifying overbuilt... Tags: latest:1.0.3 Version history: v1.0.3 | 2026-05-19T02:39:40.401Z | user Add agent-era engineering discipline: deterministic logic in code, read-before-write, explicit conflicts, intent-focused tests, check

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.0k

Updated

Oct 9, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.3release · observed May 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s178cextnnpf4qperwwzm27py984wm6f:karpathy-engineering-guidelines

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-gmvp3-karpathy-engineering-guidelines/snapshot"

Documentation

CLAWHUB

28,372 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: karpathy-guidelines
description: engineering execution guardrails for coding, implementing features, fixing bugs, debugging failures, reviewing diffs, refactoring code, simplifying overbuilt solutions, and planning multi-step code changes. use for choosing implementation approaches, editing code safely, reviewing correctness and scope, reducing unnecessary complexity, surfacing hidden assumptions, deciding what belongs in deterministic code rather than model judgment, defining concrete verification steps, and keeping software tasks to the smallest effective change.
---

# Karpathy Guidelines

Apply this skill to non-trivial software engineering work. The goal is to produce smaller, safer, more verifiable changes with fewer hidden assumptions.

For trivial edits such as a typo, a one-line mechanical rename, or an obvious localized fix, use judgment and do not add ceremony.

## Default operating loop

For non-trivial tasks, follow this sequence:

1. Restate the task in concrete engineering terms.
2. Read the nearest relevant callers, utilities, tests, and conventions before editing.
3. Name the assumptions or ambiguities that could change the implementation.
4. Choose the smallest viable approach.
5. Make only the changes required for that approach.
6. Verify the result with concrete checks.
7. Report what changed, how it was verified, and any remaining uncertainty.

When useful, think in this compact frame before acting:

- **assumptions:** what must be true
- **read:** the nearby evidence that guides the change
- **plan:** the minimum set of steps
- **verify:** the checks that define success

## Core rules

### 1. Think before coding

Do not silently pick an interpretation when the request is ambiguous.

- State assumptions that materially affect design or code changes.
- Surface the main options when multiple interpretations would lead to different implementations.
- Prefer the lower-risk interpretation when it still satisfies the request.
- Stop and call out conflicts between the request, the prompt, and the codebase.
- Push back on complexity when a simpler path clearly achieves the goal.

### 2. Simplicity first

Implement the minimum change that solves the actual problem.

- Do not add features that were not requested.
- Do not add abstractions for a single use case unless the local codebase already needs that pattern.
- Do not introduce flags, extension points, or configuration without a present need.
- Prefer straightforward control flow over cleverness.
- Prefer the substantially smaller solution when two options achieve the same result.

Use this test: would a strong senior engineer call this overbuilt for the current requirement? If yes, simplify.

### 3. Surgical changes

Touch only what the request requires.

- Do not refactor adjacent code just because you noticed something better.
- Do not reformat, rename, or reorganize unrelated code.
- Match existing local style and patterns unless the task explicitly asks for a broader

_meta.json

{
  "ownerId": "kn7ca14yv5ext6a8r07mrwaws1821snr",
  "slug": "karpathy-engineering-guidelines",
  "version": "1.0.3",
  "publishedAt": 1779158380401
}

skill-card.md

## Description:

Karpathy Guidelines provides engineering execution guardrails for coding, bug fixing, debugging, review, refactoring, planning, and verification.

This skill is ready for commercial/non-commercial use.

## Publisher:

[gmvp3](https://clawhub.ai/user/gmvp3)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and coding agents use this skill to keep non-trivial software changes focused, evidence-driven, and verifiable while avoiding unnecessary abstractions and unrelated edits.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can influence how an agent approaches substantive coding tasks and may add process to larger tasks.

Mitigation: Apply it to non-trivial software engineering work and skip extra ceremony for trivial localized edits, as the skill directs.

Risk: Engineering guidance can still lead to incorrect changes if assumptions, skipped checks, or verification gaps are not made visible.

Mitigation: Require concrete local evidence before editing, keep changes scoped, and report verification results and remaining uncertainty.

## Reference(s):


## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown guidance with implementation plans, review notes, code snippets, shell commands, configuration suggestions, and verification steps.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [No executable code is included in the artifact; outputs are guidance for an agent's software engineering workflow.]

## Skill Version(s):

1.0.3 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

agents/openai.yaml

interface:
  display_name: "Karpathy Guidelines"
  short_description: "Engineering guardrails for smaller diffs, clearer reasoning, and stronger verification"

Github ReposUpdated 7h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.