Karpathy Guidelines
alirezarezvani/ClaudeForge
Behavioral guardrails for LLM-assisted coding. An agent skill from alirezarezvani/ClaudeForge.
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.
Install Manor Coding Guardrails
$ npx skills add manor-os/manor-ai --skill manor-coding-guardrails -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install manor-os/manor-ai manor-coding-guardrails --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/manor-os/manor-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/manor-coding-guardrails .claude/skills/manor-coding-guardrails && 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 "manor-coding-guardrails" agent skill from https://github.com/manor-os/manor-ai/tree/main/.agents/skills/manor-coding-guardrails into .claude/skills/manor-coding-guardrails/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manor-coding-guardrails", 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/manor-os/manor-ai/tree/main/.agents/skills/manor-coding-guardrailsType 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 manor-os/manor-ai --skill manor-coding-guardrails -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install manor-os/manor-ai manor-coding-guardrails --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manor-os/manor-ai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/manor-coding-guardrails .agents/skills/manor-coding-guardrails && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "manor-coding-guardrails" agent skill from https://github.com/manor-os/manor-ai/tree/main/.agents/skills/manor-coding-guardrails into .agents/skills/manor-coding-guardrails/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manor-coding-guardrails", 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 manor-os/manor-ai --skill manor-coding-guardrails -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install manor-os/manor-ai manor-coding-guardrails --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manor-os/manor-ai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/manor-coding-guardrails .cursor/skills/manor-coding-guardrails && 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 "manor-coding-guardrails" agent skill from https://github.com/manor-os/manor-ai/tree/main/.agents/skills/manor-coding-guardrails into .cursor/skills/manor-coding-guardrails/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manor-coding-guardrails", 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/manor-os/manor-ai.git --path .agents/skills/manor-coding-guardrails--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 manor-os/manor-ai --skill manor-coding-guardrails -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install manor-os/manor-ai manor-coding-guardrails --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manor-os/manor-ai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/manor-coding-guardrails .gemini/skills/manor-coding-guardrails && 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 "manor-coding-guardrails" agent skill from https://github.com/manor-os/manor-ai/tree/main/.agents/skills/manor-coding-guardrails into .gemini/skills/manor-coding-guardrails/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manor-coding-guardrails", 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 manor-os/manor-ai manor-coding-guardrailsInstalls 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 manor-os/manor-ai --skill manor-coding-guardrails -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/manor-os/manor-ai.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/manor-coding-guardrails .github/skills/manor-coding-guardrails && 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 "manor-coding-guardrails" agent skill from https://github.com/manor-os/manor-ai/tree/main/.agents/skills/manor-coding-guardrails into .github/skills/manor-coding-guardrails/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manor-coding-guardrails", 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 manor-os/manor-ai --skill manor-coding-guardrails -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install manor-os/manor-ai manor-coding-guardrails --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manor-os/manor-ai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/manor-coding-guardrails .opencode/skills/manor-coding-guardrails && 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 "manor-coding-guardrails" agent skill from https://github.com/manor-os/manor-ai/tree/main/.agents/skills/manor-coding-guardrails into .opencode/skills/manor-coding-guardrails/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "manor-coding-guardrails", 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
manor-coding-guardrails- GitHub stars
- 162
- Token cost
- ~816 tokens
- SKILL.md length
- 392 words
- Files
- 2
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
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.
- Works in 4 steps: Think Before Coding → Simplicity First → Surgical Changes → …
- Refactoring Manor code to avoid overcomplication
- SKILL.md covers 1. Think Before Coding, 2. Simplicity First, 3. Surgical Changes and 4. Goal-Driven Execution, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Manor Coding Guardrails is an agent skill from manor-os/manor-ai. Use when writing, reviewing, or refactoring Manor code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in AI & LLM Engineering, covering LLM guardrails and Refactoring. The repository describes itself as: Source-available, self-hosted AI agent workspace for small businesses and lean teams — with BYOK, workflows, tools, and human approvals. The licence is MIT.
When your agent uses it
- Refactoring Manor code to avoid overcomplication
- Make surgical changes
- Surface assumptions
- Define verifiable success criteria
Example prompts
- “/manor-coding-guardrails”
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 140c09a. 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
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
Manor Coding Guardrails loads about 816 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 392 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 manor-os/manor-ai at commit 140c09a, republished under its MIT licence (© manor-os). 392 words, ~816 tokens.
Download SKILL.mdSave it as
.claude/skills/manor-coding-guardrails/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- manor-coding-guardrails
- description
- Use when writing, reviewing, or refactoring Manor code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
- license
- MIT
Manor Coding Guardrails
Adapted from Karpathy Guidelines (MIT). Preserve these core directives when working in Manor.
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.
- Do not select a "safe", "simple", or reversible default when interpretations change persisted state, user-visible behavior, lifecycle, or external effects. Stop and request a decision.
- 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:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.
When your changes create orphans:
- Remove imports, variables, and functions that your changes made unused.
- Don't remove pre-existing dead code unless asked.
The test: Every changed line should trace directly to the user's request.
Show full SKILL.md (144 more words)Show less
4. Goal-Driven Execution
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
- "Add validation" -> "Write tests for invalid inputs, then make them pass."
- "Fix the bug" -> "Write a test that reproduces it, then make it pass."
- "Refactor X" -> "Ensure tests pass before and after."
For multi-step tasks, state a brief plan:
1. [Step] -> verify: [check]
2. [Step] -> verify: [check]
3. [Step] -> verify: [check]Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
Manor Boundary Rule
These rules do not permit a Manor shortcut around a shared contract. When a
change crosses Workspace, Task, Plan, Workflow, approval, credits, Knowledge,
artifact, lifecycle, or Blueprint boundaries, REQUIRED SUB-SKILL: use
$manor-workspace-architecture before editing. Keep all entry surfaces on the
same authorization, approval, credit, lifecycle, and durable-artifact path.
Use another specialized Manor skill only when its trigger directly matches the request. It adds domain-specific context; it never replaces the four core guardrails above.
© manor-os, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/manor-coding-guardrails of manor-os/manor-ai.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 140c09a
Compare with similar skills
Manor Coding Guardrails 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 |
|---|---|---|---|---|---|---|
| Manor Coding Guardrails this skillmanor-os/manor-ai | 162 | — | ~816 | Automated safety check: Pass | MIT | |
| Karpathy Guidelinesalirezarezvani/ClaudeForge | 429 | — | ~1.2k | Automated safety check: Pass | MIT | |
| HoneyGreen-PT/honey-for-devs | 313 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Implementation Kickoffopenai/openai-guardrails-js | 105 | — | ~1k | Automated safety check: Pass | MIT | |
| Spec Kitty Bulk Edit Classificationspec-kitty/spec-kitty | 1.7k | — | ~3.8k | Automated safety check: Pass | MIT | |
| AI Coding Agent Guardrailssickn33/agentic-awesome-skills | 47k | 2 repos | ~3.3k | Automated safety check: Notes | MIT |
Similar skills
Honey
Green-PT/honey-for-devs
Write less code and say less about it. An agent skill from Green-PT/honey-for-devs.
- Official
Implementation Kickoff
openai/openai-guardrails-js
Start or resume a requested Guardrails implementation or PR takeover in the selected linked worktree with bounded scope and verification.
Spec Kitty Bulk Edit Classification
spec-kitty/spec-kitty
Recognize when a mission is a bulk edit and drive the occurrence-classification guardrail on the user's behalf.
AI Coding Agent Guardrails
sickn33/agentic-awesome-skills
Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.
Git Guardrails Claude Code
fossasia/eventyay-interpretation
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
More from manor-os/manor-ai
All 21 skills in this repoPDF
manor-os/manor-ai
A skill your agent uses whenever the user wants to do anything with PDF files.
Manor Workspace Blueprint
manor-os/manor-ai
A skill your agent uses when creating, exporting, hand-authoring, installing, upgrading, reverting, reviewing, or debugging any Manor Workspace Blueprint, especially when Workspace behavior differs…
PPTX
manor-os/manor-ai
A skill your agent uses to generate high-quality editable PowerPoint/PPTX decks from user requirements, topic prompts, or provided text/Markdown.
Video Edit
manor-os/manor-ai
Default workflow for editing, composing, or creating a finished video from screenshots, UI captures, uploaded clips, images, audio, or a written brief.
Intro
manor-os/manor-ai
Public English guide to the Manor AI OSS self-hosted product, its visible capabilities, and end-user workflows.
Skill Creator
manor-os/manor-ai
Create, update, review, and evaluate reusable Manor Skills. An agent skill from manor-os/manor-ai.
Related
Categories
Questions about Manor Coding Guardrails
What does Manor Coding Guardrails do?
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. Manor Coding Guardrails is an agent skill from manor-os/manor-ai. Use when writing, reviewing, or refactoring Manor code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
When should I use Manor Coding Guardrails?
Manor Coding Guardrails fits situations like: refactoring Manor code to avoid overcomplication; make surgical changes; surface assumptions; define verifiable success criteria.
How do I install Manor Coding Guardrails in Claude Code?
Run `npx skills add manor-os/manor-ai --skill manor-coding-guardrails -a claude-code`. Or copy the skill folder (.agents/skills/manor-coding-guardrails in manor-os/manor-ai) into .claude/skills/manor-coding-guardrails in your project. Claude Code loads it when a task matches its description.
How do I install Manor Coding Guardrails in Codex?
Run `npx skills add manor-os/manor-ai --skill manor-coding-guardrails -a codex`. Or copy the skill folder (.agents/skills/manor-coding-guardrails in manor-os/manor-ai) into .agents/skills/manor-coding-guardrails in your project. Codex loads it when a task matches its description.
Can I use Manor Coding Guardrails 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 manor-os/manor-ai --skill manor-coding-guardrails -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manor-coding-guardrails, .gemini/skills/manor-coding-guardrails, .github/skills/manor-coding-guardrails and .opencode/skills/manor-coding-guardrails in your project.
What does Manor Coding Guardrails need to run?
SKILL.md names no scripts, command-line tools or credentials: Manor Coding Guardrails is instructions for the agent only.
Does Manor Coding Guardrails 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 Manor Coding Guardrails 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 Manor Coding Guardrails use?
Manor Coding Guardrails 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 Manor Coding Guardrails use?
About 816 tokens (SKILL.md is roughly 3.3k 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 Manor Coding Guardrails?
Skills that share tags, products or a category with Manor Coding Guardrails: Karpathy Guidelines (alirezarezvani/ClaudeForge, 429 stars), Honey (Green-PT/honey-for-devs, 313 stars), Implementation Kickoff (openai/openai-guardrails-js, 105 stars) and Spec Kitty Bulk Edit Classification (spec-kitty/spec-kitty, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Manor Coding Guardrails?
manor-os (a GitHub organization) maintains it in manor-os/manor-ai, which has 162 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 7, 2026.
Source: manor-os/manor-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.