Hooks
What alfred-dev 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 686f6c61/alfred-dev --agent claude-codeShips with alfred-dev. Installing the plugin gets these hooks.
What fires, and when
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 bash.
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 python3.
UserPromptExpansion
- Runs python3.
Stop
- Runs python3.
PreToolUse
- Runs python3.
PreCompact
- Runs python3.
PostToolUse
- Runs python3.
Where it lives
- hooks/activity-capture.pyGitHub
- hooks/dangerous-command-guard.pyGitHub
- hooks/dependency-watch.pyGitHub
- hooks/evidence-guard.pyGitHub
- hooks/evidence_guard_lib.pyGitHub
- hooks/memory-compact.pyGitHub
- hooks/prefetch-finish-guard.pyGitHub
- hooks/quality-gate.pyGitHub
- hooks/secret-guard.shGitHub
- hooks/sensitive-read-guard.pyGitHub
- hooks/session-bootstrap.shGitHub
- hooks/session-start.shGitHub
- hooks/spelling-guard.pyGitHub
- hooks/stop-hook.pyGitHub
Showing the source of 6 of 14 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.
Plugin de Claude Code: 18 agentes especializados, 60 skills, 25 comandos, 13 hooks, memoria persistente, Memory UI local, quality gates, evidence guard, continuidad operativa y modo autopilot.
Repo: 686f6c61/alfred-dev