10x-agents-md

Generates and updates AGENTS.md onboarding documents for AI coding agents in a repository.

Updated May 20, 2026
One-click install
npx skills add https://github.com/ZawilecxD/trAInR --skill 10x-agents-md-zawilecxd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: 10x-agents-md
Source: https://github.com/ZawilecxD/trAInR/tree/main/.cursor/skills/10x-agents-md
Command: npx skills add https://github.com/ZawilecxD/trAInR --skill 10x-agents-md-zawilecxd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Repositories often lack a concise, agent-focused onboarding document, so AI coding agents waste context rediscovering build commands, conventions, and hard rules on every session. This Skill inspects the repo and writes a tight, reference-heavy AGENTS.md that keeps future agents unblocked. ## Core Features & Use Cases - Create and update flows: Generates a new AGENTS.md from repo discovery, or surgically updates an existing one by diffing repo state against the file's last-touched commit. - Repo-level and directory-level scope: Detects whether the target is the repo root or a subdirectory and adjusts the document's altitude, sections, and word budget accordingly. - Quality-guarded output: Enforces a 200–400 word budget, checkable rules only, @-references instead of inlined snippets, and critical-rules-first ordering. - Use Case: After adding new npm scripts and a CI gate to a project, run the update flow to refresh AGENTS.md so it reflects renamed scripts and new "never do X" rules without rewriting still-valid sections. ## Quick Start Ask the agent to create an AGENTS.md onboarding document for this repository using the 10x-agents-md skill.

Frequently Asked Questions about 10x-agents-md

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an AGENTS.md file for my repository?

Invoke the skill with no arguments to write AGENTS.md at the repo root. It reads your README, package manifest, lint and test configs, CI workflows, and git history, then drafts a 200–400 word guide ordered with critical rules first.

How do I update an existing AGENTS.md without losing my edits?

The update path classifies each existing line as KEEP, UPDATE, REMOVE, or MISSING by diffing repo state since the file's last-touched commit. It then applies small targeted edits after you confirm the change list, preserving still-valid content.

Can I generate AGENTS.md for a subdirectory instead of the repo root?

Yes, pass a directory path as the argument and the skill switches to directory-level scope. It infers local conventions from sibling files and produces a shorter 120–250 word guide focused on that directory's patterns.

What makes a good AGENTS.md for AI coding agents?

A good AGENTS.md is 200–400 words, leads with hard rules and the most-used commands, and cites canonical files via @-references instead of inlining snippets. Every rule must be checkable against a diff, with no generic advice like "write clean code".

When should I not use subagents for AGENTS.md generation?

Skip subagent fan-out when the repo has under roughly 20 top-level files, when the host lacks a subagent tool, or when relevant files are already loaded in context. Synthesis and drafting always stay in the main agent.