# 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.

Repository: https://github.com/ciembor/agent-rules-books
Canonical: https://ross.abutalabs.com/products/agent-rules-books
Homepage: https://ciembor.github.io/agent-rules-books/
License: MIT
License Family: permissive
Topics: agents-md, agent-rules, agent-skills, code-quality, refactoring, domain-driven-design, programming-books, ai-agent, ai-skills, claude-code, claude-code-skills, codex, codex-skills, cursor-rules, cursor-skills
Last push: 2026-05-22T11:00:37+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 82, longevity 9
- inputs: {"age_days": 139, "days_push": 103, "days_rel": 121, "gap_med": 0.0, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2623, forks 467 (observed 2026-08-28T04:07:05.009245+00:00)

## What it is
A collection of MIT-licensed Markdown rule sets and skills for AI coding agents (Codex, Cursor, Claude Code), distilled from classic software engineering books like Clean Code, Refactoring, DDD, Clean Architecture, and DDIA. Each rule set ships in three sizes (full, mini, nano) to fit different context budgets and usage patterns.

## Use cases
- add clean code rules to my AI coding agent
- AGENTS.md rules for Claude Code
- cursor rules based on Clean Architecture
- make my AI agent refactor code like a senior engineer
- skills for Codex from programming books
- domain-driven design guidelines for AI agents
- compact always-on coding rules for tight context windows

## When to choose
- you use Codex, Cursor, or Claude Code and want book-quality coding standards enforced by your agent
- you want tool-agnostic plain Markdown rules in multiple sizes
- you need focused decision pressure for reviews, refactors, or architecture passes

## When to avoid
- you need executable linters or automated enforcement rather than prompt-level guidance
- you don't use AI coding agents
- you want rules for a specific framework or language rather than general software design

## Facets
- artifact type: learning-resource
- maturity: active
- function: developer-tools, documentation, markdown
- domain: developer-tools, artificial-intelligence, programming-languages, tutorials
- platform: cross-platform
- tags: agents-md, ai-coding-agents, cursor-rules, claude-code, codex-skills, clean-code, domain-driven-design, refactoring, prompt-rules

## Member repositories
- ciembor/agent-rules-books (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:05.009245+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:19:54.912223+00:00, confidence not recorded.
  - readme: https://github.com/ciembor/agent-rules-books (fetched 2026-08-28T04:07:05.009245+00:00, sha 240cd8f20cc0)
  - homepage: https://ciembor.github.io/agent-rules-books/ (fetched 2026-08-29T10:03:18.304351+00:00, sha d2c7a15f64ea)
- Data as of 2026-08-30T08:39:29.467469+00:00.