npx claudepluginhub tobyhede/turboshovel --plugin turboshovelExecute an implementation plan with workflow orchestration
If you're reading this, the plugin is working. This command triggered the `SessionStart` hook.
Verify with independent agents and consensus-based collation
Run the turboshovel feature walkthrough
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
Algorithmic decision tree for when to follow plan exactly vs when to report STOPPED - prevents scope creep and unauthorized deviations
Dispatch N independent review agents, collate by consensus ratio, cross-check exclusive findings
Use when executing multi-step processes requiring state persistence and agent coordination - defines two-tier protocol where subagents report PASS/FAIL status and main agent handles dispatch, advancement, and failure troubleshooting
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
Persistent Workflows for Claude Code
Turboshovel is a Claude Code plugin that brings persistent, enforceable workflows to your agents. Define multi-step processes in Markdown runbooks, and Turboshovel ensures agents follow them—even across context clears.
Workflow progress survives context clears. Resume interrupted tasks instantly. Never lose track of where you are.
Enforce multi-step workflows with Rundown runbooks. Prevent agents from skipping steps or jumping around.
Run lint, test, build at workflow boundaries. Block agents when checks fail. Chain gates for complex pipelines.
Auto-inject context at runbook steps. Agents get focused, step-specific instructions exactly when needed.
claude plugin add tobyhede/turboshovel
Turboshovel includes Rundown for workflow orchestration.
Define your workflow in .claude/rundown/runbooks/feature.runbook.md:
## 1. Create Plan
Design the implementation approach.
- PASS: CONTINUE
- FAIL: STOP
## 2. Implement Feature
Write the code following the plan.
- PASS: CONTINUE
- FAIL: RETRY 2
## 3. Run Tests
Verify everything works.
- PASS: COMPLETE
- FAIL: GOTO 2
Create .claude/turboshovel.json:
{
"gates": {
"test": {
"command": "npm test",
"on_fail": "BLOCK"
}
},
"hooks": {
"SubagentStop": {
"gates": ["test"]
}
}
}
rundown run .claude/rundown/runbooks/feature.runbook.md
How it works:
.claude/rundown/session.jsonrundown status shows where you arerundown run <file> # Start a workflow
rundown pass # Mark current step as passed
rundown fail # Mark current step as failed
rundown goto <n> # Jump to step number
rundown status # Show current state
rundown stop # Abort workflow
rundown complete # Mark complete
rundown stash # Pause enforcement
rundown pop # Resume enforcement
MIT
Battle-tested Claude Code plugin for engineering teams — 48 agents, 182 skills, 68 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete collection of battle-tested Claude Code configs agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use