Manor Coding Guardrails
manor-os/manor-ai
A skill your agent uses when writing, reviewing, or refactoring Manor code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Behavioral guardrails for LLM-assisted coding. An agent skill from alirezarezvani/ClaudeForge.
Install Karpathy Guidelines
$ npx skills add alirezarezvani/ClaudeForge --skill karpathy-guidelines -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alirezarezvani/ClaudeForge karpathy-guidelines --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/alirezarezvani/ClaudeForge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/karpathy-guidelines .claude/skills/karpathy-guidelines && 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-guidelines" agent skill from https://github.com/alirezarezvani/ClaudeForge/tree/dev/skill/karpathy-guidelines into .claude/skills/karpathy-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-guidelines", 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/alirezarezvani/ClaudeForge/tree/dev/skill/karpathy-guidelinesType 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 alirezarezvani/ClaudeForge --skill karpathy-guidelines -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alirezarezvani/ClaudeForge karpathy-guidelines --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/ClaudeForge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill/karpathy-guidelines .agents/skills/karpathy-guidelines && 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-guidelines" agent skill from https://github.com/alirezarezvani/ClaudeForge/tree/dev/skill/karpathy-guidelines into .agents/skills/karpathy-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-guidelines", 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 alirezarezvani/ClaudeForge --skill karpathy-guidelines -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alirezarezvani/ClaudeForge karpathy-guidelines --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/ClaudeForge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill/karpathy-guidelines .cursor/skills/karpathy-guidelines && 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-guidelines" agent skill from https://github.com/alirezarezvani/ClaudeForge/tree/dev/skill/karpathy-guidelines into .cursor/skills/karpathy-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-guidelines", 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/alirezarezvani/ClaudeForge.git --path skill/karpathy-guidelines--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 alirezarezvani/ClaudeForge --skill karpathy-guidelines -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alirezarezvani/ClaudeForge karpathy-guidelines --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/ClaudeForge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill/karpathy-guidelines .gemini/skills/karpathy-guidelines && 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-guidelines" agent skill from https://github.com/alirezarezvani/ClaudeForge/tree/dev/skill/karpathy-guidelines into .gemini/skills/karpathy-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-guidelines", 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 alirezarezvani/ClaudeForge karpathy-guidelinesInstalls 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 alirezarezvani/ClaudeForge --skill karpathy-guidelines -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alirezarezvani/ClaudeForge.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill/karpathy-guidelines .github/skills/karpathy-guidelines && 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-guidelines" agent skill from https://github.com/alirezarezvani/ClaudeForge/tree/dev/skill/karpathy-guidelines into .github/skills/karpathy-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-guidelines", 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 alirezarezvani/ClaudeForge --skill karpathy-guidelines -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alirezarezvani/ClaudeForge karpathy-guidelines --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alirezarezvani/ClaudeForge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill/karpathy-guidelines .opencode/skills/karpathy-guidelines && 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-guidelines" agent skill from https://github.com/alirezarezvani/ClaudeForge/tree/dev/skill/karpathy-guidelines into .opencode/skills/karpathy-guidelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-guidelines", 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-guidelines- GitHub stars
- 429
- Token cost
- ~1.2k tokens
- SKILL.md length
- 569 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Behavioral guardrails for LLM-assisted coding. An agent skill from alirezarezvani/ClaudeForge.
- Works in 4 steps: Think Before Coding → Simplicity First → Surgical Changes → …
- Refactoring code in any project to avoid overcomplication
- SKILL.md covers When to Apply, 1. Think Before Coding, 2. Simplicity First and 3. Surgical Changes, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Karpathy Guidelines is an agent skill from alirezarezvani/ClaudeForge. Behavioral guardrails for LLM-assisted coding. Use when writing, reviewing, or refactoring code in any project to avoid overcomplication, keep changes surgical, surface assumptions early, and execute against verifiable success criteria.
Its SKILL.md is about 1.2k 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 Development, covering Refactoring and LLM guardrails. The repository describes itself as: A CLAUDE.md Generator and Maintenance tool for for Claude Code to create high-quality CLAUDE.md instruction files — aligned with Anthropic’s best practices for Claude Code. The licence is MIT.
When your agent uses it
- Refactoring code in any project to avoid overcomplication
- Keep changes surgical
- Surface assumptions early
- Execute against verifiable success criteria
Example prompts
- “/karpathy-guidelines”
Requirements
- Pre-approved tools (allowed-tools): Read, Glob, Grep
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 032c5e5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGlobGrep
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
Links to these hosts (documentation or services it may open):
github.com
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 Guidelines loads about 1.2k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 569 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
The full file from alirezarezvani/ClaudeForge at commit 032c5e5, republished under its MIT licence (© alirezarezvani). 569 words, ~1,225 tokens.
Download SKILL.mdSave it as
.claude/skills/karpathy-guidelines/SKILL.md (or your agent's skills folder).- name
- karpathy-guidelines
- description
- Behavioral guardrails for LLM-assisted coding. Use when writing, reviewing, or refactoring code in any project to avoid overcomplication, keep changes surgical, surface assumptions early, and execute against verifiable success criteria.
- allowed-tools
- Read, Glob, Grep
- license
- MIT
- paths
- **/*.py, **/*.ts, **/*.tsx, **/*.js, **/*.jsx, **/*.go, **/*.rs, **/*.java, **/*.kt, **/*.rb, **/*.php, **/*.swift, **/*.c, **/*.cc, **/*.cpp, **/*.h…
- permissions.allow
- Read, Glob, Grep
Karpathy Guidelines for LLM Coding
Behavioral guardrails for code generation in Claude Code projects, distilled from observations on common LLM coding failure modes. Apply these to every editing, reviewing, and refactoring task.
Attribution: adapted from the MIT-licensed
karpathy-guidelinesskill by Forrest Chang (https://github.com/forrestchang/andrej-karpathy-skills), inspired by Andrej Karpathy's commentary on where LLM-generated code typically goes wrong. ClaudeForge integrates these principles so every project initialised or enhanced through/enhance-claude-mdships with them in its CLAUDE.md.
When to Apply
Apply on every non-trivial task: writing new code, editing existing code, code review, refactoring, and bug fixing. They are intentionally conservative — bias toward caution over speed.
1. Think Before Coding
Surface what is uncertain. Do not paper over confusion with plausible-sounding code.
- State assumptions before implementing; if any are load-bearing and you are not sure, ask.
- If the request admits more than one reasonable interpretation, list them rather than silently picking one.
- If a simpler approach exists than the one the user proposed, say so and explain the tradeoff.
- When something is genuinely unclear, stop. Identify what is unclear in concrete terms, then ask.
2. Simplicity First
Write the minimum code that solves the stated problem. Nothing speculative.
- Do not add features that were not requested.
- Do not introduce abstractions when there is only one call site.
- Do not add configuration knobs or extension points on speculation.
- Do not add error handling for conditions that cannot occur in this code path.
- If the first draft is 200 lines and a 50-line version would do, rewrite it before shipping.
Self-check: a senior engineer skimming this diff — would they say it is overcomplicated for what was asked? If yes, simplify.
3. Surgical Changes
Touch only what the task requires. Do not opportunistically refactor.
- Do not "improve" adjacent code, comments, or formatting that the task did not require touching.
- Do not refactor code that is working, even when you would have written it differently.
- Match the surrounding code's style and conventions, even when they differ from your defaults.
- If you notice unrelated dead code or bugs, surface them in the response — do not silently delete or fix them.
When your own changes leave orphans:
- Remove imports, variables, and helpers that your edits made unreachable.
- Do not remove pre-existing dead code unless explicitly asked.
Diff test: every changed line should be traceable to the user's request. If a line is not, drop it.
Show full SKILL.md (174 more words)Show less
4. Goal-Driven Execution
Turn the task into a verifiable goal, then iterate until the verification passes.
- Convert vague requests into checkable success criteria before coding:
- "Add validation" → write the failing tests for invalid inputs first, then make them pass.
- "Fix the bug" → write a test that reproduces the bug, then make it pass.
- "Refactor X" → confirm the existing tests pass, refactor, confirm they still pass.
- For multi-step tasks, state the plan inline with verification per step:
1. <step> → verify: <how you will check>
2. <step> → verify: <how you will check>
3. <step> → verify: <how you will check>Strong success criteria let you loop without supervision. Vague ones ("make it work") force the user back into the loop.
Integration with ClaudeForge
- The slash command
/enhance-claude-mdinjects a## Behavioral Guidelinessection into every generated or enhancedCLAUDE.md, summarising these four principles with a link back to this skill. - The
claude-md-guardianagent preserves the section across automated maintenance updates. skill/generator.pyandskill/template_selector.pyinsert the section unconditionally — these principles are not opt-in.
Effectiveness Indicators
The guidelines are working when diffs trend smaller, rewrites caused by overcomplication drop, and clarifying questions arrive before implementation rather than after a failed attempt.
© alirezarezvani, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skill/karpathy-guidelines of alirezarezvani/ClaudeForge.
Open the folder on GitHubat commit 032c5e5
Compare with similar skills
Karpathy Guidelines 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 Guidelines this skillalirezarezvani/ClaudeForge | 429 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Manor Coding Guardrailsmanor-os/manor-ai | 162 | — | ~816 | Automated safety check: Pass | MIT | |
| Refactor React Effectslangfuse/langfuse | 36k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Concern Patternsdilolabs/nosia | 213 | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Elixirstreamband/hydra-srt | 146 | — | ~804 | Automated safety check: Pass | Apache-2.0 | |
| Change CleanupSimon-Initiative/oli-torus | 119 | — | ~3.7k | Automated safety check: Pass | MIT |
Similar skills
Refactor React Effects
langfuse/langfuse
Refactor avoidable React useEffect usage in Langfuse frontend code.
Concern Patterns
dilolabs/nosia
Creates and refactors model and controller concerns for shared behavior.
Elixir
streamband/hydra-srt
A skill your agent uses for Elixir/Phoenix development in this repo: implementing features, refactors, debugging, tests, Ecto changes, and production-safe fixes.
Change Cleanup
Simon-Initiative/oli-torus
Clean up and harden code introduced by the current branch without drifting into broad refactors.
Cpp String API Review
tetherto/qvac
Review C++ changes for string parameter and call-site efficiency conventions (std::stringview, std::string&&, const std::string&, const char, and TransparentStringMap lookup).
More from alirezarezvani/ClaudeForge
Claude Md Dependency Rescan
alirezarezvani/ClaudeForge
Re-detect this project's tech stack from package.json / requirements.txt / pyproject.toml / go.mod / Cargo.toml and diff it against the Tech Stack section of every CLAUDE.md.
Claude Md Drift Audit
alirezarezvani/ClaudeForge
Audit every CLAUDE.md in this project for drift against the last week of git history.
Claude Md Link Check
alirezarezvani/ClaudeForge
Verify every @path chain import and every markdown link inside every CLAUDE.md in this project resolves to an existing file.
Related
Categories
Questions about Karpathy Guidelines
What does Karpathy Guidelines do?
Behavioral guardrails for LLM-assisted coding. An agent skill from alirezarezvani/ClaudeForge. Karpathy Guidelines is an agent skill from alirezarezvani/ClaudeForge. Behavioral guardrails for LLM-assisted coding.
When should I use Karpathy Guidelines?
Karpathy Guidelines fits situations like: refactoring code in any project to avoid overcomplication; keep changes surgical; surface assumptions early; execute against verifiable success criteria.
How do I install Karpathy Guidelines in Claude Code?
Run `npx skills add alirezarezvani/ClaudeForge --skill karpathy-guidelines -a claude-code`. Or copy the skill folder (skill/karpathy-guidelines in alirezarezvani/ClaudeForge) into .claude/skills/karpathy-guidelines in your project. Claude Code loads it when a task matches its description.
How do I install Karpathy Guidelines in Codex?
Run `npx skills add alirezarezvani/ClaudeForge --skill karpathy-guidelines -a codex`. Or copy the skill folder (skill/karpathy-guidelines in alirezarezvani/ClaudeForge) into .agents/skills/karpathy-guidelines in your project. Codex loads it when a task matches its description.
Can I use Karpathy Guidelines 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 alirezarezvani/ClaudeForge --skill karpathy-guidelines -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-guidelines, .gemini/skills/karpathy-guidelines, .github/skills/karpathy-guidelines and .opencode/skills/karpathy-guidelines in your project.
What does Karpathy Guidelines need to run?
SKILL.md names no scripts, command-line tools or credentials: Karpathy Guidelines is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep.
Does Karpathy Guidelines access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Karpathy Guidelines 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 Guidelines use?
Karpathy Guidelines is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Karpathy Guidelines use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Guidelines?
Skills that share tags, products or a category with Karpathy Guidelines: Manor Coding Guardrails (manor-os/manor-ai, 162 stars), Refactor React Effects (langfuse/langfuse, 36k stars), Concern Patterns (dilolabs/nosia, 213 stars) and Elixir (streamband/hydra-srt, 146 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Karpathy Guidelines?
alirezarezvani (a GitHub user) maintains it in alirezarezvani/ClaudeForge, which has 429 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on May 19, 2026.
Source: alirezarezvani/ClaudeForge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.