Hooks
What agent-starter runs automatically, and when. A hook is a command Claude Code fires at a fixed moment, without you asking for it.
$ npx -y skills add sneg55/agent-starter --agent claude-codeShips with agent-starter. Installing the plugin gets these hooks.
What fires, and when
PostToolUse
- Runs check-file-size.sh.
PreToolUse
- Runs block-dangerous-commands.sh.
SessionStart
Fires once when a session begins, and again after a context compaction. It is where a plugin sets up its environment, or restores state the compaction dropped.
- Runs ..
UserPromptSubmit
Fires before Claude sees each prompt you send. A plugin can use it to inject context, so the same instruction reaches the model every turn instead of only at session start.
- Runs suggest-loop-improvements.sh.
Where it lives
- hooks/block-dangerous-commands.shGitHub
- hooks/check-codebase-health.shGitHub
- hooks/check-file-size.shGitHub
- hooks/check-silent-errors.shGitHub
- hooks/harness-ledger-stats.shGitHub
- hooks/lint-on-edit.shGitHub
- hooks/require-read-before-edit.shGitHub
- hooks/suggest-loop-improvements.shGitHub
- hooks/track-reads.shGitHub
Showing the source of 6 of 9 scripts. Every one is linked above.
Read the script before you install anything that runs on your machine. This is the one part of a plugin that acts without being asked.
Skills, hooks, templates, and engineering guides for bootstrapping AI-agent-friendly projects, with a per-project self-improvement loop.
Repo: sneg55/agent-starter