ad-bootstrap

Scan codebases to generate or audit AGENTS.md at the repository root.

728|16|Updated Mar 9, 2026

Search Tags:#automation #codebase #audit #agents.md #bootstrap #placeholders

Ready to run

npx skills add https://github.com/alexandremendoncaalvaro/CorridorKey-Runtime --skill ad-bootstrap

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ad-bootstrap
Source: https://github.com/alexandremendoncaalvaro/CorridorKey-Runtime/tree/main/.agents/skills/ad-bootstrap
Command: npx skills add https://github.com/alexandremendoncaalvaro/CorridorKey-Runtime --skill ad-bootstrap

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps. Use whenever the user wants to bootstrap, scaffold, generate, create, set up, or audit AGENTS.md / CLAUDE.md / agents.md (the operational guide for agents working on this project).

Core Features & Use Cases

Scan a repo to determine missing AGENTS.md sections and propose realistic placeholders based on observed signals.
Pre-fill AGENTS.md with governance, workflow, and role information to accelerate onboarding and audits.
Apply in brownfield, greenfield, or audit workflows to produce or validate the agents guide at repo root.

Quick Start

Run the ad-bootstrap workflow to generate or audit AGENTS.md at the repository root.

Frequently Asked Questions about ad-bootstrap

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

FAQPage Schema

How do I generate an AGENTS.md file for an existing repository?▼

To generate an AGENTS.md file for an existing repository, this Skill scans your codebase, reads manifests and documentation, and pre-fills placeholders with observed signals to bootstrap the guide at the repo root.

What is the best way to bootstrap an agents guide for a greenfield project?▼

Bootstrapping an agents guide for a greenfield project involves scanning available signals and scaffolding a deterministic AGENTS.md with governance and workflow placeholders at the repository root.

Can I audit an existing AGENTS.md file against my current codebase?▼

Yes, you can audit an existing AGENTS.md by running the workflow in audit mode, which validates the file against your repository structure and pre-fills any missing governance or role information.

Do I need to manually write placeholders when scaffolding AGENTS.md?▼

No, you do not need to manually write placeholders when scaffolding AGENTS.md because the scan detects manifests, ADRs, and agent configurations to automatically pre-fill realistic values.

How does codebase scanning determine the content for AGENTS.md?▼

Codebase scanning determines AGENTS.md content by reading manifests, documentation, and agent configurations, then generating deterministic governance and workflow sections aligned to the repository structure.

Are there limitations when generating an agents guide in brownfield scenarios?▼

In brownfield scenarios with meaningful code, the generated agents guide relies on observed signals from existing manifests and ADRs, asking only for genuine gaps that the scan cannot determine deterministically.