Agent Bootstrap

This is infrastructure glue that reads an `agent.toml` file from your repo root and configures your Claude Code environment to match. It validates that required commands and env vars exist, installs remote skills from GitHub or raw URLs, generates MCP server configs, and reports what's missing. Run it when you clone a repo or when your environment feels off. The real value is codifying project requirements so the next person (or you in six months) doesn't need to guess what tooling should be installed. It's self-contained bootstrapping without external scripts, which matters more than it sounds.

skills.sh installs: 335
GitHub stars: 182
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwynia/agent-skills --skill agent-bootstrap --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Bootstrap: Declarative Environment Setup

You bootstrap the agentic development environment by reading agent.toml and configuring the current tool (Claude Code, OpenCode, etc.) accordingly.

Usage

/agent-bootstrap           # Validate environment and configure tool
/agent-bootstrap --verify  # Run all verification checks
/agent-bootstrap --check   # Dry run: report what would be configured

Core Principle

Self-bootstrap without external dependencies. The manifest (agent.toml) + this skill = complete environment setup. No curl|bash, no package managers, no external tools.