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...

View on GitHub ↗Jump to charts ↓

ciembor/agent-rules-books has 3k+ stars and 500+ forks on GitHub and was last pushed on Sep 10, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 35 minutes ago
Type:Curated List / Learning ResourceCategory(s):MCP Servers, Agent Skills & PromptsAI Coding AgentsAI Agents & LLM Apps
Added to GitGenius on October 12th, 2026
Created on April 16th, 2026
Open Issues & Pull Requests: 7 (+0)
GitHub issues: Enabled
Number of forks: 531
Total Stargazers: 3,056 (+1)
Total Subscribers: 25 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 6.5 hours
Mean response time: 15.3 days
90th percentile: 45.5 days
Tracked items: 3

Maintainer activity

1 person did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 5
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 121 days
Stale 30+ days: 4
Stale 90+ days: 4

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Agent Rules Books is a collection of AGENTS.md rule sets for AI coding agents including Codex, Cursor, and Claude Code.

The project addresses the challenge of guiding AI coding agents toward better software practices by distilling principles from established programming books on refactoring, architecture, domain-driven design, code quality, and data-intensive systems. It provides ready-to-use rule sets in Markdown format that agents can reference during code generation and review. Each rule set is released in three versions—mini for typical use, nano for tight context budgets, and full as a complete reference—allowing developers to choose the appropriate level of detail for their workflow.

Developers should adopt this tool if they use AI coding agents and want to steer them toward established software engineering practices without manually crafting custom rules. The project suits teams working with Codex, Cursor, or Claude Code who value clean code principles and architectural best practices. The tool can be installed as skills through an Agent Skills CLI or configured manually for always-on, on-demand, or scoped usage depending on editor and workflow preferences. The README provides editor-specific setup guidance and usage patterns for each supported tool.

The project maintains multiple rule set variants to accommodate different context constraints and use cases. Development includes detailed documentation covering installation, usage patterns, compatibility notes, and release history, with constructive feedback incorporated into the design.