Git safety rules and mandatory gates for all git operations
/plugin marketplace add p4ndroid/ai-dev-pipeline-architecture/plugin install ai-dev-pipeline@ai-dev-pipeline-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
CRITICAL: All git operations MUST go through the git-operator worker agent.
-d not -D for branch deletion| Operation | Description |
|---|---|
preflight | Check for uncommitted changes, offer stash |
branch-create | Create and checkout new branch |
branch-checkout | Switch to existing branch |
commit | Stage, commit, verify not on main |
push | Push to origin with tracking |
merge | Squash merge, delete source branch |
restore-workflow | Return to original branch, pop stash |
health-check | Diagnose repository state |
| Operation | Purpose |
|---|---|
workspace-create | Create isolated git worktree |
workspace-status | Poll all workspace states |
workspace-commit | Commit in workspace context |
workspace-push | Push workspace branch |
workspace-merge | Merge with AI conflict resolution |
workspace-cleanup | Remove completed workspaces |
{type}/{short-description}
| Type | Use Case |
|---|---|
feat/ | New features |
fix/ | Bug fixes |
refactor/ | Code refactoring |
docs/ | Documentation only |
test/ | Test additions/changes |
chore/ | Maintenance tasks |
<type>(<scope>): <short description>
<longer description if needed>
- Bullet points for specific changes
- Include test summary if applicable
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Example prompt for spawning:
subagent_type: git-operator
prompt: |
[DEPTH: 2/5]
operation: commit
files:
- src/feature.py
- tests/test_feature.py
message: |
feat(feature): Add new feature implementation
- Core logic implementation
- Unit tests added (5 tests, all passing)
Before any destructive operation, git-operator will:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.