JordanCoinJordanCoin/codingskills/AGENTS.md

codingskills

AGENTS.md10 starsChanged 9 months agoMITView on GitHub

Guidelines for AI agents working in this repository. This repository contains Agent Skills for AI agents following the Agent Skills specification. Skills install to .agents/skills/ (the cross-agent standard). This repo also serves as a Claude Code plugin marketplace via .claude-plugin/marketplace.json. Skills are content-only (no build step). Verify manually: - YAML frontmatter is valid - name field matches directory name exactly - name is 1-64 chars, lowercase alphanumeric and hyphens only - description is 1-1024 characters Skills follow the Agent Skills…

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,843 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- boy-scout-ruleSkill
- convention-over-configurationSkill
- detect-stackSkill
- drySkill
- kissSkill
- law-of-demeterSkill
- separation-of-concernsSkill
- solidSkill
- yagniSkill

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
No consecutive hyphens (--)
line 65
Distinctive:
Must match parent directory name exactly
line 66
Very specific:
On first use: Run detect-stack to scan the codebase.
line 70
Very specific:
For framework-specific details: Use context7 MCP (resolve-library-id then query-docs) or web search to pull live docs.
line 72
Distinctive:
No static reference files per language: Instead:
line 89

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

Guidelines for AI agents working in this repository.

Repository Overview

This repository contains Agent Skills for AI agents following the Agent Skills specification. Skills install to .agents/skills/ (the cross-agent standard). This repo also serves as a Claude Code plugin marketplace via .claude-plugin/marketplace.json.

Name: Coding Skills
GitHub: JordanCoin/codingskills
Creator: Jordan Coin Jackson
License: MIT

Repository Structure

codingskills/
├── .claude-plugin/
│   └── marketplace.json   # Claude Code plugin marketplace manifest
├── skills/                # Agent Skills
│   └── skill-name/
│       └── SKILL.md       # Required skill file
├── AGENTS.md              # This file
├── CLAUDE.md → AGENTS.md  # Symlink for Claude Code
├── CONTRIBUTING.md
├── LICENSE
├── README.md
└── install.sh             # Cross-project installer

Build / Lint / Test Commands

Skills are content-only (no build step). Verify manually:

YAML frontmatter is valid
name field matches directory name exactly
name is 1-64 chars, lowercase alphanumeric and hyphens only
description is 1-1024 characters

Agent Skills Specification

Skills follow the Agent Skills spec.

Required Frontmatter

---
name: skill-name
description: What this skill does and when to use it. Include trigger phrases.
---

Frontmatter Field Constraints

Field	Required	Constraints
`name`	Yes	1-64 chars, lowercase `a-z`, numbers, hyphens. Must match dir.
`description`	Yes	1-1024 chars. Describe what it does and when to use it.
`license`	No	License name (default: MIT)
`metadata`	No	Key-value pairs (author, version, etc.)

Name Field Rules

Lowercase letters, numbers, and hyphens only
Cannot start or end with hyphen
No consecutive hyphens (--)
Must match parent directory name exactly

How Agents Should Use These Skills

On first use: Run detect-stack to scan the codebase. It writes .agents/stack-context.md with detected language, framework, and conventions.
Apply principles using your built-in knowledge of the detected stack. These files teach principles and decision frameworks — you already know how the language works.
For framework-specific details: Use context7 MCP (resolve-library-id then query-docs) or web search to pull live docs. Don't guess at API specifics.

When to Apply Each Principle

Situation	Primary	Supporting
Adding a new feature	yagni	kiss, separation-of-concerns
Refactoring	separation-of-concerns, solid	dry, boy-scout-rule
Reviewing a PR	kiss, dry	law-of-demeter, convention-over-configuration
Fixing a bug	boy-scout-rule, kiss	separation-of-concerns
Designing module boundaries	separation-of-concerns, solid	law-of-demeter
Choosing between approaches	kiss, yagni	convention-over-configuration
Organizing project structure	convention-over-configuration, separation-of-concerns	solid
Reducing coupling	law-of-demeter, solid	separation-of-concerns

Stack-Specific Knowledge Strategy

No static reference files per language. Instead:

Agent detects the stack (via detect-stack)
Agent applies principles using built-in language knowledge
For specific framework APIs, agent uses context7 MCP or web search on demand

This keeps the skill collection lightweight and always current.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free