AGENTS.md is the operational entrypoint documenting governance, precedence, session controls, and drift-management for a repository.

Can AGENTS.md be used across multiple repos?

No. This skill generates repo-specific AGENTS.md files that reference repository paths and governance terms.

What if there are conflicting governance rules?

Resolve by updating the AGENTS.md with the canonical precedence and drift-control policy, then re-run the skill to regenerate a consistent file.

create-agents-md

Scanned

npx machina-cli add skill MSiccDev/ai-context-kit/create-agents-md --openclaw

Files (1)

SKILL.md

2.0 KB

Create AGENTS.md

Purpose

Generate a complete root AGENTS.md file that acts as an operational entrypoint while preserving source-of-truth and repository governance rules.

When To Use

Use this skill when adding or refreshing repository AGENTS.md.
Use this skill when repository map, precedence, and session controls must be documented concisely.
Do not use this skill for project/user instruction file generation.

Required Inputs

Repository purpose and canonical paths.
Source precedence and key references.
Session-state defaults and command namespace rules.
Drift-control requirements.

Workflow

Run seven-phase discovery using references/discovery-phases.md.
Apply required element contract from references/required-elements.md.
Generate artifact using references/output-format.md.
Validate result against references/quality-checklist.md.
Ensure links/paths remain relative and repository-accurate.

Output Expectations

One complete root AGENTS.md file.
Includes purpose, precedence, repo map, command policy, and drift-control.
Uses provider-neutral wording and valid relative links.
Remains scannable and operationally actionable.
Output contract and summary format follow references/output-format.md.

Resources

Discovery workflow: references/discovery-phases.md
Required element contract: references/required-elements.md
Output contract: references/output-format.md
Quality checklist: references/quality-checklist.md
Canonical template: ../../templates/AGENTS_template.md
Repository example: ../../AGENTS.md

Constraints And Safety

Do not duplicate full normative specs in AGENTS.
Preserve canonical path stability.
Keep guidance deterministic and testable.
Use relative path references only.

Source

git clone https://github.com/MSiccDev/ai-context-kit/blob/development/skills/create-agents-md/SKILL.mdView on GitHub

Overview

Generates a complete root AGENTS.md for a repository, detailing operational contract, precedence rules, and drift-control guidance. The output serves as a governance entrypoint that preserves source truth and uses relative links, ensuring consistency across the project. Content is provider-neutral, scannable, and actionable.

How This Skill Works

The process follows seven-phase discovery, applies the required-element contract, and outputs an AGENTS.md formatted per the repository guidelines. It then validates the result against a quality checklist and ensures all links remain relative and repository-accurate.

When to Use It

Adding or refreshing the repository AGENTS.md to reflect its governance model.
Documenting repository map, precedence, and session controls concisely.
Capturing drift-control requirements and contract terms for compliance.
Generating a provider-neutral AGENTS.md with valid relative links.
Not suitable for generating project-wide or user instruction files.

Quick Start

Step 1: Gather repository purpose, canonical paths, precedence references, and drift-control needs.
Step 2: Run discovery (references/discovery-phases.md), apply required elements, and draft AGENTS.md.
Step 3: Validate with the quality checklist and commit the root AGENTS.md with relative links.

Best Practices

Run seven-phase discovery (references/discovery-phases.md) before drafting.
Apply the required element contract (references/required-elements.md) strictly.
Format output to match the output contract (references/output-format.md).
Validate against the quality checklist (references/quality-checklist.md).
Keep all links and paths relative and repository-accurate.

Example Use Cases

AGENTS.md for a monorepo with multiple services and a shared governance model.
AGENTS.md for a data science repo documenting drift-control and contracts.
AGENTS.md in a libraries repo with strict precedence rules.
AGENTS.md for internal tooling with session-state defaults.
AGENTS.md for an open-source project ensuring clear governance.

Frequently Asked Questions

Add this skill to your agents