This file is byte-identical to the first copy the registry indexed, one of 5 indexed copies. Same content hash, so the same checks give both the same grade.
karpathy-guidelines from jdanigo/hydraia is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
## 1. Think Before Coding
**Don't assume. Don't hide confusion. Surface tradeoffs.**
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
## 2. Simplicity First
**Minimum code that solves the problem. Nothing speculative.**
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
## 3. Surgical Changes
**Touch only what you must. Clean up only your own mess.**
When editing existing code:
…
The line at the top of this page pins the label git:20260702.9dc0119, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2518 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
jdanigo/hydraia · 8 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bc5coy3uyuhgf2gl
GET https://markdownregistry.com/api/v1/resolve?ref=jdanigo/hydraia/karpathy-guidelines
GET https://markdownregistry.com/api/v1/blob/6e22cc54cb02a5e98ae42d06d9d7292db0c1b43894831b32879beb0166b2aea7
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
jdanigo/hydraia · codex/skills/hydraia/SKILL.md · Codex-native hydraia pipeline. Use when the user asks to build, add, implement, or change a feature, brings a…
jdanigo/hydraia · skills/adr/SKILL.md · Use when a design decision is made that is expensive to reverse, affects multiple components, or rejects a plausible…
jdanigo/hydraia · skills/agency-tier-ui/SKILL.md · Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and…
jdanigo/hydraia · skills/api-design/SKILL.md · Use when designing or reviewing an API surface — REST, GraphQL, or gRPC. Contract-first methodology: the contract…
jdanigo/hydraia · skills/banner-design/SKILL.md · Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with…
jdanigo/hydraia · skills/brainstorming/SKILL.md · You MUST use this before any creative work - creating features, building components, adding functionality, or modifying…
jdanigo/hydraia · skills/caveman/SKILL.md · Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical…
jdanigo/hydraia · skills/db-optimization/SKILL.md · Use when the bottleneck is database-shaped — slow queries, lock timeouts, connection exhaustion, N+1 patterns, index…
jdanigo/hydraia · skills/design-to-code/SKILL.md · Elite render-to-code skill. The user brings a finished website design render (jpg/png); this skill distills it into…
coco-research/coco · skills/karpathy-guidelines/SKILL.md · Pointer to the upstream skill for behavioural guidelines that reduce common LLM coding mistakes, installed from…
mxyhi/ok-skills · karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
openyida/openyida · .agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
youdotcom-oss/agent-skills · .agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
rudycity/superagent · .agents/skills/karpathy-guidelines/SKILL.md · Behavioral rules to minimize common LLM coding pitfalls. Applies to all code creation, modification, review, and…
