Agent skill

System Design

A skill your agent uses when making technology or structural decisions - selecting databases, APIs, auth strategies, caching layers, file organization, or weighing monolith against services

MITAuto-check passedBackend & APIs

Install System Design

skills CLI

$ npx skills add NoobyGains/godmode --skill system-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode system-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/system-design .claude/skills/system-design && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "system-design" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/system-design into .claude/skills/system-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-design", 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

$skill-installer install https://github.com/NoobyGains/godmode/tree/master/skills/system-design

Type 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.

skills CLI

$ npx skills add NoobyGains/godmode --skill system-design -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode system-design --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/system-design .agents/skills/system-design && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "system-design" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/system-design into .agents/skills/system-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-design", 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.

skills CLI

$ npx skills add NoobyGains/godmode --skill system-design -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode system-design --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/system-design .cursor/skills/system-design && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "system-design" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/system-design into .cursor/skills/system-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-design", 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

$ gemini skills install https://github.com/NoobyGains/godmode.git --path skills/system-design

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add NoobyGains/godmode --skill system-design -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode system-design --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/system-design .gemini/skills/system-design && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "system-design" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/system-design into .gemini/skills/system-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-design", 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.

GitHub CLI

$ gh skill install NoobyGains/godmode system-design

Installs 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).

skills CLI

$ npx skills add NoobyGains/godmode --skill system-design -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/system-design .github/skills/system-design && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "system-design" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/system-design into .github/skills/system-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-design", 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.

skills CLI

$ npx skills add NoobyGains/godmode --skill system-design -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install NoobyGains/godmode system-design --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/system-design .opencode/skills/system-design && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "system-design" agent skill from https://github.com/NoobyGains/godmode/tree/master/skills/system-design into .opencode/skills/system-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "system-design", 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: system-design
GitHub stars: 107
Token cost: ~2.2k tokens
SKILL.md length: 727 words
Files: 1
Skills in repo: 34
Repo updated: Mar 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when making technology or structural decisions - selecting databases, APIs, auth strategies, caching layers, file organization, or weighing monolith against services

Making technology
SKILL.md covers Overview, The Prime Directive, When to Use and The Entry Protocol, plus 6 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
Structural decisions - selecting databases

What it does

System Design is an agent skill from NoobyGains/godmode. Use when making technology or structural decisions - selecting databases, APIs, auth strategies, caching layers, file organization, or weighing monolith against services

Its SKILL.md is about 2.2k 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 Backend & APIs, covering Caching and File organization. It works with PostgreSQL. The repository describes itself as: The AI development framework that thinks before it builds. 36 composable skills for Claude Code, Cursor, Codex, and OpenCode. The licence is MIT.

When your agent uses it

Making technology
Structural decisions - selecting databases
Auth strategies
File organization

Example prompts

“/system-design”

What it can do on your machine

Read from SKILL.md and the folder at commit 441103a. 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 (its code samples are dot).
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

System Design loads about 2.2k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 727 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~46
When it runs · the whole SKILL.md, loaded when a task matches: ~2.2k

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 NoobyGains/godmode at commit 441103a, republished under its MIT licence (© NoobyGains). 727 words, ~2,201 tokens.

Download SKILL.mdSave it as .claude/skills/system-design/SKILL.md (or your agent's skills folder).

name: system-design
description: Use when making technology or structural decisions - selecting databases, APIs, auth strategies, caching layers, file organization, or weighing monolith against services

System Design

Overview

Select the simplest architecture that satisfies requirements. Introduce complexity only when evidence demands it.

Core principle: Every structural decision must be driven by a current requirement, not a speculative future one.

No exceptions. No workarounds. No shortcuts.

The Prime Directive

NO STRUCTURAL COMPLEXITY WITHOUT AN ESTABLISHED REQUIREMENT

If you cannot point to a concrete, current requirement that demands the complexity, choose the simpler option.

When to Use

Always before:

Selecting a database
Designing an API
Organizing a new project
Introducing a caching layer
Adding message queues or event systems
Choosing authentication strategy
Deciding on monolith vs services

Especially when:

"We might need to scale" (might = do not add complexity)
"What if we need X later?" (later = not now)
Multiple valid approaches exist

The Entry Protocol

BEFORE making ANY structural decision:

1. IDENTIFY: What concrete requirement drives this choice?
2. COMPARE: What is the simplest option that satisfies it?
3. JUSTIFY: Why is anything more complex necessary?
   - If no justification: Use the simple option
   - If justified: Record the requirement driving complexity
4. DECIDE: Choose. Document. Move on.

Skip any step = over-engineering

Decision Frameworks

Monolith vs Services

dot

digraph structure_decision {
    start [label="New project?", shape=diamond];
    team [label="Multiple teams\nown separate\ndomains?", shape=diamond];
    scale [label="Components need\nindependent\nscaling NOW?", shape=diamond];
    deploy [label="Components need\nindependent\ndeploy cycles?", shape=diamond];
    mono [label="MONOLITH\nSimplest path", shape=box, style=filled, fillcolor="#ccffcc"];
    services [label="SERVICES\nEstablished need", shape=box, style=filled, fillcolor="#ffcccc"];

    start -> mono [label="yes"];
    start -> team [label="existing"];
    team -> services [label="yes"];
    team -> scale [label="no"];
    scale -> services [label="yes"];
    scale -> deploy [label="no"];
    deploy -> services [label="yes"];
    deploy -> mono [label="no"];
}

Default: Monolith. Extract services only when a specific component demonstrates it requires independent scaling or deployment.

Database Selection

Requirement	Select	Rationale
Structured data, relationships, transactions	PostgreSQL	ACID guarantees, mature, covers 90% of use cases
Document-oriented, genuinely variable schema per record	MongoDB	Only when schema truly differs per document
Key-value, caching, session storage	Redis	In-memory speed, built-in TTL
Full-text search at volume	Elasticsearch	Purpose-built for search workloads
Time-series data (metrics, logs)	TimescaleDB / InfluxDB	Optimized for time-indexed writes
Graph traversal is the primary query model	Neo4j	Only when traversal IS the product
Embedded, zero-config, single-user	SQLite	Simplest possible, no server needed

Default: PostgreSQL. It handles JSON, full-text search, and most workloads adequately. Switch only when PostgreSQL demonstrably cannot meet a requirement.

API Design

Context	Select	Rationale
CRUD operations, public-facing API	REST	Universal, cacheable, well-understood
Complex nested data, client-controlled shape	GraphQL	Eliminates over/under-fetching
Internal service-to-service, high throughput	gRPC	Binary protocol, generated stubs, streaming
Real-time bidirectional communication	WebSockets	Persistent connection, low latency
Simple webhooks, event notification	REST callbacks	Stateless, easy to troubleshoot

Default: REST. Adopt GraphQL only when clients genuinely need flexible queries. Adopt gRPC only for internal services where throughput is measured and proven insufficient with REST.

Authentication Strategy

Context	Select	Rationale
Standard web application	Session-based (cookies)	Simple, secure, server-controlled revocation
SPA + API on different origins	JWT (short-lived) + refresh tokens	Stateless API auth across domains
Third-party login	OAuth 2.0 / OIDC	Delegated authentication standard
Machine-to-machine	API keys + HMAC	Simple, auditable
Multi-tenant SaaS	OIDC + tenant-scoped tokens	Isolation per tenant

Default: Session-based auth with httpOnly cookies. JWTs are not inherently more secure. Use them only when stateless authentication across domains is a concrete requirement.

Caching Strategy

BEFORE introducing a cache:

1. Is there actually a measured performance problem?
2. Can the database query be optimized instead?
3. Is the data read-heavy with infrequent writes?

Only if YES to 1, NO to 2, YES to 3: Introduce cache.

Layer	Mechanism	Use When
Application	In-memory (LRU)	Single instance, small dataset
Distributed	Redis / Memcached	Multi-instance, shared state
HTTP	CDN / reverse proxy	Static assets, public pages
Database	Query cache / materialized views	Expensive aggregations

Default: No cache. Optimize queries first. Introduce caching only after measuring a bottleneck.

Show full SKILL.md (286 more words)Show less

Event-Driven Architecture

BEFORE introducing a message queue:

1. Do you need asynchronous processing? (Email delivery, image processing)
2. Do producers and consumers need to scale independently?
3. Do you need guaranteed delivery across service boundaries?

If NO to all: Direct function calls are sufficient.

Need	Mechanism	Rationale
Simple task queue	Redis + BullMQ / Celery	Lightweight, familiar
Event streaming, replay	Kafka	High throughput, log-based
Cloud-native messaging	SQS / Cloud Pub/Sub	Managed, serverless
Complex routing	RabbitMQ	Flexible routing, mature

Default: Direct function calls. Queues add operational complexity. Introduce them only when async processing or decoupling is an established requirement.

File Organization Conventions

Organize by capability, not by layer:

# AVOID: organized by layer
src/
  controllers/
  models/
  services/
  validators/

# PREFER: organized by capability
src/
  users/
    user.controller.ts
    user.service.ts
    user.model.ts
    user.test.ts
  orders/
    order.controller.ts
    order.service.ts
    order.model.ts
    order.test.ts
  shared/
    database.ts
    auth.middleware.ts

Capability-based organization keeps related code together. Changing one capability touches one directory.

Cognitive Traps

Rationalization	Truth
"We might need microservices later"	Extract when needed. Monolith-first is faster to build and debug.
"NoSQL is more flexible"	PostgreSQL handles JSON. Schema flexibility usually means schema confusion.
"GraphQL is the modern choice"	REST is simpler for CRUD. Modern does not mean appropriate.
"JWTs are more secure"	JWTs are harder to revoke. Sessions are simpler and server-controlled.
"We need a cache for performance"	Have you optimized your queries? Measure first.
"Event-driven is more scalable"	Direct calls are simpler. Scaling concerns are future concerns.
"This architecture handles future growth"	The future is unpredictable. Solve current problems.

Guardrails - HALT and Simplify

Adding infrastructure for "future scale"
Selecting technology because it is "modern" or "industry standard"
Architecture diagram has more than 5 components for an MVP
Multiple databases without distinct access patterns
Message queues for synchronous workflows
Microservices with a single team
"Flexible" schemas without concrete varying fields
Caching before measuring

All of these mean: Simplify. Use the boring, proven option.

Integration

Complements:

godmode:performance-tuning — When structural choices affect performance
godmode:security-protocol — Auth patterns and data flow security
godmode:project-bootstrap — File organization and initial setup
godmode:task-planning — Structural decisions during planning phase

The Bottom Line

Simplest architecture that works > "best" architecture that might be needed

PostgreSQL. REST. Monolith. Sessions. No cache. Direct calls. Start there. Introduce complexity only when you have evidence it is necessary.

Files

Just SKILL.md in skills/system-design of NoobyGains/godmode.

Open the folder on GitHubat commit 441103a

Compare with similar skills

System Design 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.

System Design compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
System Design this skillNoobyGains/godmode	107	—	~2.2k	Automated safety check: Pass	MIT	7 mo ago
Stripe Projectsfossasia/eventyay	1.7k	5 repos	~2k	Automated safety check: Notes	Apache-2.0	today
Veloxdb Scalable Performanceveloxbase/veloxdb	646	—	~1.7k	Automated safety check: Pass	MIT	8 days ago
Database Domain Specialistmodu-ai/moai-adk	1.2k	—	~2.8k	Automated safety check: Pass	Apache-2.0	today
Database Patternsmajiayu000/spellbook	286	—	~2.8k	Automated safety check: Pass	MIT	today
Database Optimizationaiskillstore/marketplace	430	1 repos	~787	Automated safety check: Pass	None	yesterday

Similar skills

Stripe Projects
fossasia/eventyay
A skill your agent uses when the user wants to provision infrastructure or third-party services using Stripe Projects.
1.7k GitHub starsUsed in 5 repos~2k tokens
Backend & APIsAuto-check: notes
Veloxdb Scalable Performance
veloxbase/veloxdb
Guides scalability and performance work for VeloxDB's Tauri + Rust PostgreSQL backend and React + TanStack frontend.
646 GitHub stars~1.7k tokensUpdated 8 days ago
DatabasesAuto-check passed
Database Domain Specialist
modu-ai/moai-adk
Database guidance for PostgreSQL, MongoDB, Redis and Oracle plus Neon, Supabase and Firestore: schema design, indexing, query tuning and cloud database choice.
1.2k GitHub stars~2.8k tokensUpdated today
DatabasesAuto-check passed
Database Patterns
majiayu000/spellbook
A skill your agent uses when designing PostgreSQL + Redis data models, indexes, caching strategies, JSONB usage, tiered storage, or cache consistency contracts.
286 GitHub stars~2.8k tokensUpdated today
DatabasesAuto-check passed
Database Optimization
aiskillstore/marketplace
SQL query optimization and database performance specialist. An agent skill from aiskillstore/marketplace.
430 GitHub starsUsed in 1 repo~787 tokens
DatabasesAuto-check passed
Cloudflare Hyperdrive
secondsky/claude-skills
Cloudflare Hyperdrive for Workers-to-database connections with pooling and caching.
227 GitHub stars~1.8k tokensUpdated 10 days ago
DatabasesAuto-check passed

Questions about System Design

What does System Design do?

A skill your agent uses when making technology or structural decisions - selecting databases, APIs, auth strategies, caching layers, file organization, or weighing monolith against services. System Design is an agent skill from NoobyGains/godmode.

When should I use System Design?

System Design fits situations like: making technology; structural decisions - selecting databases; auth strategies; file organization.

How do I install System Design in Claude Code?

Run `npx skills add NoobyGains/godmode --skill system-design -a claude-code`. Or copy the skill folder (skills/system-design in NoobyGains/godmode) into .claude/skills/system-design in your project. Claude Code loads it when a task matches its description.

How do I install System Design in Codex?

Run `npx skills add NoobyGains/godmode --skill system-design -a codex`. Or copy the skill folder (skills/system-design in NoobyGains/godmode) into .agents/skills/system-design in your project. Codex loads it when a task matches its description.

Can I use System Design 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 NoobyGains/godmode --skill system-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/system-design, .gemini/skills/system-design, .github/skills/system-design and .opencode/skills/system-design in your project.

What does System Design need to run?

SKILL.md names no scripts, command-line tools or credentials: System Design is instructions for the agent only.

Does System Design 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 System Design 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 System Design use?

System Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does System Design use?

About 2.2k tokens (SKILL.md is roughly 8.8k 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 System Design?

Skills that share tags, products or a category with System Design: Stripe Projects (fossasia/eventyay, 1.7k stars), Veloxdb Scalable Performance (veloxbase/veloxdb, 646 stars), Database Domain Specialist (modu-ai/moai-adk, 1.2k stars) and Database Patterns (majiayu000/spellbook, 286 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains System Design?

NoobyGains (a GitHub user) maintains it in NoobyGains/godmode, which has 107 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on March 9, 2026.

Source: NoobyGains/godmode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install System Design

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

System Design

Overview

The Prime Directive

When to Use

The Entry Protocol

Decision Frameworks

Monolith vs Services

Database Selection

API Design

Authentication Strategy

Caching Strategy

Event-Driven Architecture

File Organization Conventions

Cognitive Traps

Guardrails - HALT and Simplify

Integration

The Bottom Line

Files

Compare with similar skills

Similar skills

More from NoobyGains/godmode

Related

Questions about System Design