ciembor/agent-rules-books

AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.

About the project

agent-rules-books is a collection of Markdown rules and skills that guide AI coding agents using principles from books on software design, refactoring, architecture, domain-driven design, reliability, and data systems. Developers use the rules with Codex, Cursor, Claude Code, and other compatible agents to shape how they perform coding tasks. The catalogue skills package these rule sets for installation and use by coding agents.

2.7kStars on the repository
14Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, or reviewing APIs and abstractions.

not rated 2.7k +45 today A 33 tokens original MIT

clean-architecture

02

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Robert C. Martin-inspired architecture rules when separating business policy from frameworks, databases, UI, or infrastructure details.

not rated 2.7k +45 today A 27 tokens original MIT

clean-code

03

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Robert C. Martin-inspired clean code rules when improving readability, naming, function design, responsibilities, or testable everyday code.

not rated 2.7k +45 today A 29 tokens original MIT

code-complete

04

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Steve McConnell-inspired construction rules when implementing routines, variables, classes, control flow, defensive code, or tests.

not rated 2.7k +45 today A 28 tokens original MIT

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Martin Kleppmann-inspired data-system rules when designing reliability, scalability, consistency, replication, transactions, streams, or schema evolution.

not rated 2.7k +45 today A 34 tokens original MIT

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Vaughn Vernon-inspired lightweight DDD rules when using bounded contexts, subdomains, context maps, and tactical modeling without excess ceremony.

not rated 2.7k +45 today A 33 tokens original MIT

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Eric Evans-inspired DDD rules when modeling a complex domain, defining bounded contexts, protecting ubiquitous language, or designing aggregates.

not rated 2.7k +45 today A 29 tokens original MIT

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Vaughn Vernon-inspired implementation DDD rules when building aggregates, domain events, repositories, application services, or context integrations.

not rated 2.7k +45 today A 31 tokens original MIT

refactoring-guru

10

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.

not rated 2.7k +45 today A 29 tokens original MIT

refactoring

11

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.

not rated 2.7k +45 today A 20 tokens original MIT

release-it

12

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Michael T. Nygard-inspired production reliability rules when designing failure handling, timeouts, retries, circuit breakers, observability, or deployment behavior.

not rated 2.7k +45 today A 34 tokens original MIT

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Hunt and Thomas-inspired pragmatic programming rules when improving engineering judgment, feedback loops, DRY knowledge, orthogonality, automation, or adaptability.

not rated 2.7k +45 today A 36 tokens original MIT

ciembor/agent-rules-books

Skill Claude CodeCodex

Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.

not rated 2.7k +45 today A 37 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: