agent/scripts/auto-approve.sh
Snider ecefb8a952 refactor: restructure as Claude Code marketplace plugin
- Add .claude-plugin/plugin.json manifest for auto-updates
- Move claude/ contents to root level (commands/, hooks/, scripts/, skills/)
- Update hooks.json to use ${CLAUDE_PLUGIN_ROOT} for portability
- Add .gitignore for IDE files
- Update CLAUDE.md with new structure and installation instructions

Plugin can now be installed via:
  claude plugin add host-uk/core-agent

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-01 19:35:06 +00:00

23 lines
534 B
Bash
Executable file

#!/bin/bash
# Auto-approve all permission requests during /core:yes mode
#
# PermissionRequest hook that returns allow decision for all tools.
# Used by the /core:yes skill for autonomous task completion.
read -r input
TOOL=$(echo "$input" | jq -r '.tool_name // empty')
# Log what we're approving (visible in terminal)
echo "[yes-mode] Auto-approving: $TOOL" >&2
# Return allow decision
cat << 'EOF'
{
"hookSpecificOutput": {
"hookEventName": "PermissionRequest",
"decision": {
"behavior": "allow"
}
}
}
EOF