AI Research Reproduction
lllllllama/RigorPilot-Skills
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.
Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation.
Install Karpathy
$ npx skills add tmdgusya/engineering-discipline --skill karpathy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tmdgusya/engineering-discipline karpathy --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tmdgusya/engineering-discipline.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/karpathy .claude/skills/karpathy && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "karpathy" agent skill from https://github.com/tmdgusya/engineering-discipline/tree/main/skills/karpathy into .claude/skills/karpathy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tmdgusya/engineering-discipline/tree/main/skills/karpathyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tmdgusya/engineering-discipline --skill karpathy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tmdgusya/engineering-discipline karpathy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmdgusya/engineering-discipline.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/karpathy .agents/skills/karpathy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "karpathy" agent skill from https://github.com/tmdgusya/engineering-discipline/tree/main/skills/karpathy into .agents/skills/karpathy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tmdgusya/engineering-discipline --skill karpathy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tmdgusya/engineering-discipline karpathy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmdgusya/engineering-discipline.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/karpathy .cursor/skills/karpathy && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "karpathy" agent skill from https://github.com/tmdgusya/engineering-discipline/tree/main/skills/karpathy into .cursor/skills/karpathy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tmdgusya/engineering-discipline.git --path skills/karpathy--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tmdgusya/engineering-discipline --skill karpathy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tmdgusya/engineering-discipline karpathy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmdgusya/engineering-discipline.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/karpathy .gemini/skills/karpathy && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "karpathy" agent skill from https://github.com/tmdgusya/engineering-discipline/tree/main/skills/karpathy into .gemini/skills/karpathy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tmdgusya/engineering-discipline karpathyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tmdgusya/engineering-discipline --skill karpathy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tmdgusya/engineering-discipline.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/karpathy .github/skills/karpathy && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "karpathy" agent skill from https://github.com/tmdgusya/engineering-discipline/tree/main/skills/karpathy into .github/skills/karpathy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tmdgusya/engineering-discipline --skill karpathy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tmdgusya/engineering-discipline karpathy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmdgusya/engineering-discipline.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/karpathy .opencode/skills/karpathy && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "karpathy" agent skill from https://github.com/tmdgusya/engineering-discipline/tree/main/skills/karpathy into .opencode/skills/karpathy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
karpathy- GitHub stars
- 125
- Token cost
- ~2k tokens
- SKILL.md length
- 1,134 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- None found
At a glance
Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation.
- Works in 4 steps: Read before you write. Do not modify a… → Scope to the request. Change what was… → Verify, don't assume. If you think a… → …
- Implementing features
- SKILL.md covers Hard Gates, When To Use, When NOT To Use and The Five Rules, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Karpathy is an agent skill from tmdgusya/engineering-discipline. Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation. Use when implementing features, modifying code, or when you notice yourself about to make changes without reading the existing code first.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. The repository describes itself as: SKILL for engineering-discipline.
When your agent uses it
- Implementing features
- You notice yourself about to make changes without reading the existing code first
Example prompts
- “/karpathy”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Read before you write. Do not modify a file you haven't read. Do not modify a function without understanding the callers. Do not modify a…
- Scope to the request. Change what was asked. Nothing more. No "while I'm here" improvements, no opportunistic refactoring, no adding…
- Verify, don't assume. If you think a function does X, read it. If you think a type has field Y, check it. If you think a test covers…
- Define success before starting. Before writing any code, state what "done" looks like in concrete, verifiable terms. If you can't define…
What it can do on your machine
Read from SKILL.md and the folder at commit 137dead. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Karpathy loads about 2k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 1,134 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,134 words (~1,988 tokens).
“A preventive thinking discipline for code implementation. Activates before and during code writing to block the most common mistakes LLMs make when generating code.”
- name
- karpathy
Files
Just SKILL.md in skills/karpathy of tmdgusya/engineering-discipline.
Open the folder on GitHubat commit 137dead
Compare with similar skills
Karpathy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Karpathy this skilltmdgusya/engineering-discipline | 125 | — | ~2k | Automated safety check: Pass | None | |
| AI Research Reproductionlllllllama/RigorPilot-Skills | 497 | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Onnxtxtonnx/onnx | 22k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Add Publication DocsRLinf/RLinf | 5.5k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Create Simple Promptpnp/copilot-prompts | 893 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Google Agents CLI Adk Codepifferologo/cloud-agents-cli | 129 | 1 repos | ~768 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Onnxtxt
onnx/onnx
Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.
Add Publication Docs
RLinf/RLinf
Adds a new publication page to the RLinf Sphinx docs (EN + ZH) and wires it into the Publications index/toctree.
Create Simple Prompt
pnp/copilot-prompts
This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…
Google Agents CLI Adk Code
pifferologo/cloud-agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…
- Official
Llmobs Testing
DataDog/dd-trace-js
A skill your agent uses when writing, modifying, or debugging tests for an LLMObs plugin in dd-trace-js.
More from tmdgusya/engineering-discipline
All 11 skills in this repoClarification
tmdgusya/engineering-discipline
A skill your agent uses when a user's request is vague, ambiguous, or underspecified.
Clean AI Slop
tmdgusya/engineering-discipline
Corrective cleanup of AI-generated code — removes LLM-specific patterns while preserving behavior.
Plan Crafting
tmdgusya/engineering-discipline
A skill your agent uses when a task's scope is clear and multi-step implementation is needed, before touching code.
Review Work
tmdgusya/engineering-discipline
Use after run-plan completes to independently verify the implementation.
Run Plan
tmdgusya/engineering-discipline
A skill your agent uses when you have a written implementation plan to execute.
Systematic Debugging
tmdgusya/engineering-discipline
A skill your agent uses when encountering any bug, test failure, or unexpected behavior.
Related
Categories
Questions about Karpathy
What does Karpathy do?
Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation. Karpathy is an agent skill from tmdgusya/engineering-discipline. Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation.
When should I use Karpathy?
Karpathy fits situations like: implementing features; you notice yourself about to make changes without reading the existing code first.
How do I install Karpathy in Claude Code?
Run `npx skills add tmdgusya/engineering-discipline --skill karpathy -a claude-code`. Or copy the skill folder (skills/karpathy in tmdgusya/engineering-discipline) into .claude/skills/karpathy in your project. Claude Code loads it when a task matches its description.
How do I install Karpathy in Codex?
Run `npx skills add tmdgusya/engineering-discipline --skill karpathy -a codex`. Or copy the skill folder (skills/karpathy in tmdgusya/engineering-discipline) into .agents/skills/karpathy in your project. Codex loads it when a task matches its description.
Can I use Karpathy in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tmdgusya/engineering-discipline --skill karpathy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/karpathy, .gemini/skills/karpathy, .github/skills/karpathy and .opencode/skills/karpathy in your project.
What does Karpathy need to run?
SKILL.md names no scripts, command-line tools or credentials: Karpathy is instructions for the agent only.
Does Karpathy access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Karpathy safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Karpathy use?
No licence was found for Karpathy or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Karpathy use?
About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Karpathy?
Skills that share tags, products or a category with Karpathy: AI Research Reproduction (lllllllama/RigorPilot-Skills, 497 stars), Onnxtxt (onnx/onnx, 22k stars), Add Publication Docs (RLinf/RLinf, 5.5k stars) and Create Simple Prompt (pnp/copilot-prompts, 893 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Karpathy?
tmdgusya (a GitHub user) maintains it in tmdgusya/engineering-discipline, which has 125 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 3, 2026.
Source: tmdgusya/engineering-discipline on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.