A toolkit of skills, templates, and guides for bootstrapping AI-agent-friendly projects. Started from Anthropic's Claude Code engineering patterns, extended with a per-project self-improvement loop and more.
Hook
Runs after a tool call finishes for Write, Edit, Write, Edit, Write and Edit tool calls, executing check-file-size.sh, lint-on-edit.sh and check-silent-errors.sh (3 commands). From sneg55/agent-starter.
Hook
Runs before the agent uses a tool for Bash tool calls, executing block-dangerous-commands.sh. From sneg55/agent-starter.
Hook
Runs when a session starts, executing check-codebase-health.sh. From sneg55/agent-starter.
Hook
Runs when you submit a prompt, before the agent sees it, executing suggest-loop-improvements.sh. From sneg55/agent-starter.