/git-workflow
Orchestrate git workflow from code review through PR creation with quality gates
$ npx -y skills add wshobson/agents --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/git-workflow
Context preview
What this command does when you run it.
Orchestrate git workflow from code review through PR creation with quality gates
Command definition
git-workflow.mddescription: "Orchestrate git workflow from code review through PR creation with quality gates"
argument-hint: "<target branch> [--skip-tests] [--draft-pr] [--no-push] [--squash] [--conventional] [--trunk-based]"
Git Workflow Orchestrator
CRITICAL BEHAVIORAL RULES
You MUST follow these rules exactly. Violating any of them is a failure.
1. **Execute steps in order.** Do NOT skip ahead, reorder, or merge steps. 2. **Write output files.** Each step MUST produce its output file in `.git-workflow/` before the next step begins. Read from prior step files — do NOT rely on context window memory. 3. **Stop at checkpoints.** When you reach a `PHASE CHECKPOINT`, you MUST stop and wait for explicit user approval before continuing. Use the AskUserQuestion tool with clear options. 4. **Halt on failure.** If any step fails (agent error, test failure, missing dependency), STOP immediately. Present the error and ask the user how to proceed. Do NOT silently continue. 5. **Use only local agents.** All `subagent_type` references use agents bundled with this plugin or `general-purpose`. No cross-plugin dependencies. 6. **Never enter plan mode autonomously.** Do NOT use EnterPlanMode. This command IS the plan — execute it.
Pre-flight Checks
Before starting, perform these checks:
1. Check for existing session
Check if `.git-workflow/state.json` exists:
- If it exists and `status` is `"in_progress"`: Read it, display the current step, and ask the user:
Found an in-progress git workflow session:
Target branch: [branch from state]
Current step: [step from state]
1. Resume from where we left off
2. Start fresh (archives existing session)
- If it exists and `status` is `"complete"`: Ask whether to archive and start fresh.
2. Initialize state
Create `.git-workflow/` directory and `state.json`:
{
"target_branch": "$ARGUMENTS",
"status": "in_progress",
"flags": {
"skip_tests": false,
"draft_pr": false,
"no_push": false,
"squash": false,
"conventional": true,
"trunk_based": false
},
"current_step": 1,
"current_phase": 1,
"completed_steps": [],
"files_created": [],
"started_at": "ISO_TIMESTAMP",
"last_updated": "ISO_TIMESTAMP"
}Parse `$ARGUMENTS` for the target branch (defaults to 'main') and flags. Use defaults if not specified.
3. Gather git context
Run these commands and save output:
- `git status` — current working tree state
- `git diff --stat` — summary of changes
- `git diff` — full diff of changes
- `git log --oneline -10` — recent commit history
- `git branch --show-current` — current branch name
Save this context to `.git-workflow/00-git-context.md`.
---
Phase 1: Pre-Commit Review and Analysis (Steps 1–2)
Step 1: Code Quality Assessment
Read `.git-workflow/00-git-context.md`.
Use the Task tool to launch the code reviewer:
Task:
subagent_type: "git-pr-workflows-code-reviewer"
description: "Review uncommitted changes for code quality"
prompt: |
Review all uncommitted changes for code quality issues.
## Git Context
[Insert contents of .git-workflow/00-git-context.md]
Check for:
1. Code style violations
2. Security vulnerabilities
3. Performance concerns
4. Missing error handling
5. Incomplete implementations
Generate a detailed report with severity levels (critical/high/medium/low) and provide
specific line-by-line feedback.
## Deliverables
Output format: structured report with:
- Issues list with severity, file, line, description
- Summary counts: {critical: N, high: N, medium: N, low: N}
- Recommendations for fixes
Write your complete review as a single markdown document.Save the agent's output to `.git-workflow/01-code-review.md`.
Update `state.json`: set `current_step` to 2, add step 1 to `completed_steps`.
Step 2: Dependency and Breaking Change Analysis
Read `.git-workflow/00-git-context.md` and `.git-workflow/01-code-review.md`.
Use the Task tool:
Task:
subagent_type: "git-pr-workflows-code-reviewer"
description: "Analyze changes for dependencies and breaking changes"
prompt: |
Analyze the changes for dependency and breaking change issues.
## Git Context
[Insert contents of .git-workflow/00-git-context.md]
## Code Review
[Insert contents of .git-workflow/01-code-review.md]
Check for:
1. New dependencies or version changes
2. Breaking API changes
3. Database schema modifications
4. Configuration changes
5. Backward compatibility issues
Identify any changes that require migration scripts or documentation updates.
## Deliverables
1. Breaking change assessment
2. Dependency change analysis
3. Migration requirements
4. Documentation update needs
Write your complete analysis as a single markdown document.Save output to `.git-workflow/02-breaking-changes.md`.
Update `state.json`: set `current_step` to "checkpoint-1", add step 2 to `completed_steps`.
---
PHASE CHECKPOINT 1 — User Approval Required
Display a summary of code review and breaking change analysis and ask:
Pre-commit review complete. Please review:
- .git-workflow/01-code-review.md
- .git-workflow/02-breaking-changes.md
Issues found: [X critical, Y high, Z medium, W low]
Breaking changes: [summary]
1. Approve — proceed to testing (or skip if --skip-tests)
2. Fix issues first — I'll address the critical/high issues
3. Pause — save progress and stop here
If user selects option 2, address the critical/high issues, then re-run the review and re-checkpoint.
Do NOT proceed to Phase 2 until the user approves.
---
Phase 2: Testing and Validation (Steps 3–4)
If `--skip-tests` flag is set, skip to Phase 3. Write a note in `.git-workflow/03-test-results.md` explaining tests were skipped.
Step 3: Test Execution and Coverage
Read `.git-workflow/00-git-context.md` and `.git-workflow/01-code-review.md`.
Use the
Read more
description: "Orchestrate git workflow from code review through PR creation with quality gates" argument-hint: "<target branch> [--skip-tests] [--draft-pr] [--no-push] [--squash] [--conventional] [--trunk-based]"
Git Workflow Orchestrator
CRITICAL BEHAVIORAL RULES
You MUST follow these rules exactly. Violating any of them is a failure.
1. **Execute steps in order.** Do NOT skip ahead, reorder, or merge steps. 2. **Write output files.** Each step MUST produce its output file in `.git-workflow/` before the next step begins. Read from prior step files — do NOT rely on context window memory. 3. **Stop at checkpoints.** When you reach a `PHASE CHECKPOINT`, you MUST stop and wait for explicit user approval before continuing. Use the AskUserQuestion tool with clear options. 4. **Halt on failure.** If any step fails (agent error, test failure, missing dependency), STOP immediately. Present the error and ask the user how to proceed. Do NOT silently continue. 5. **Use only local agents.** All `subagent_type` references use agents bundled with this plugin or `general-purpose`. No cross-plugin dependencies. 6. **Never enter plan mode autonomously.** Do NOT use EnterPlanMode. This command IS the plan — execute it.
Pre-flight Checks
Before starting, perform these checks:
1. Check for existing session
Check if `.git-workflow/state.json` exists:
- If it exists and `status` is `"in_progress"`: Read it, display the current step, and ask the user:
Found an in-progress git workflow session: Target branch: [branch from state] Current step: [step from state] 1. Resume from where we left off 2. Start fresh (archives existing session)
- If it exists and `status` is `"complete"`: Ask whether to archive and start fresh.
2. Initialize state
Create `.git-workflow/` directory and `state.json`:
{
"target_branch": "$ARGUMENTS",
"status": "in_progress",
"flags": {
"skip_tests": false,
"draft_pr": false,
"no_push": false,
"squash": false,
"conventional": true,
"trunk_based": false
},
"current_step": 1,
"current_phase": 1,
"completed_steps": [],
"files_created": [],
"started_at": "ISO_TIMESTAMP",
"last_updated": "ISO_TIMESTAMP"
}Parse `$ARGUMENTS` for the target branch (defaults to 'main') and flags. Use defaults if not specified.
3. Gather git context
Run these commands and save output:
- `git status` — current working tree state
- `git diff --stat` — summary of changes
- `git diff` — full diff of changes
- `git log --oneline -10` — recent commit history
- `git branch --show-current` — current branch name
Save this context to `.git-workflow/00-git-context.md`.
---
Phase 1: Pre-Commit Review and Analysis (Steps 1–2)
Step 1: Code Quality Assessment
Read `.git-workflow/00-git-context.md`.
Use the Task tool to launch the code reviewer:
Task:
subagent_type: "git-pr-workflows-code-reviewer"
description: "Review uncommitted changes for code quality"
prompt: |
Review all uncommitted changes for code quality issues.
## Git Context
[Insert contents of .git-workflow/00-git-context.md]
Check for:
1. Code style violations
2. Security vulnerabilities
3. Performance concerns
4. Missing error handling
5. Incomplete implementations
Generate a detailed report with severity levels (critical/high/medium/low) and provide
specific line-by-line feedback.
## Deliverables
Output format: structured report with:
- Issues list with severity, file, line, description
- Summary counts: {critical: N, high: N, medium: N, low: N}
- Recommendations for fixes
Write your complete review as a single markdown document.Save the agent's output to `.git-workflow/01-code-review.md`.
Update `state.json`: set `current_step` to 2, add step 1 to `completed_steps`.
Step 2: Dependency and Breaking Change Analysis
Read `.git-workflow/00-git-context.md` and `.git-workflow/01-code-review.md`.
Use the Task tool:
Task:
subagent_type: "git-pr-workflows-code-reviewer"
description: "Analyze changes for dependencies and breaking changes"
prompt: |
Analyze the changes for dependency and breaking change issues.
## Git Context
[Insert contents of .git-workflow/00-git-context.md]
## Code Review
[Insert contents of .git-workflow/01-code-review.md]
Check for:
1. New dependencies or version changes
2. Breaking API changes
3. Database schema modifications
4. Configuration changes
5. Backward compatibility issues
Identify any changes that require migration scripts or documentation updates.
## Deliverables
1. Breaking change assessment
2. Dependency change analysis
3. Migration requirements
4. Documentation update needs
Write your complete analysis as a single markdown document.Save output to `.git-workflow/02-breaking-changes.md`.
Update `state.json`: set `current_step` to "checkpoint-1", add step 2 to `completed_steps`.
---
PHASE CHECKPOINT 1 — User Approval Required
Display a summary of code review and breaking change analysis and ask:
Pre-commit review complete. Please review: - .git-workflow/01-code-review.md - .git-workflow/02-breaking-changes.md Issues found: [X critical, Y high, Z medium, W low] Breaking changes: [summary] 1. Approve — proceed to testing (or skip if --skip-tests) 2. Fix issues first — I'll address the critical/high issues 3. Pause — save progress and stop here
If user selects option 2, address the critical/high issues, then re-run the review and re-checkpoint.
Do NOT proceed to Phase 2 until the user approves.
---
Phase 2: Testing and Validation (Steps 3–4)
If `--skip-tests` flag is set, skip to Phase 3. Write a note in `.git-workflow/03-test-results.md` explaining tests were skipped.
Step 3: Test Execution and Coverage
Read `.git-workflow/00-git-context.md` and `.git-workflow/01-code-review.md`.
Use the
Production-ready agentic workflow building blocks: 94 plugins, 203 agents, 175 skills, 109 commands — built for Claude Code and consumed natively by OpenAI Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot from a single Markdown source.
Repo: wshobson/agents
Other commands on wshobson-agents.
- /accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits, identify barriers, provide remediation guidance, and ensure digital products are accessible to all users.
Open command - /improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Open command - /multi-agent-optimize
The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to
Open command - /team-debug
Debug issues using competing hypotheses with parallel investigation by multiple agents
Open command - /team-delegate
Task delegation dashboard for managing team workload, assignments, and rebalancing
Open command - /team-feature
Develop features in parallel with multiple agents using file ownership boundaries and dependency management
Open command

