
Turboshovel
- Updated January 14, 2026
- tobyhede/turboshovel
turboshovel is a Claude Code skill in the AI & Agent Building category. Generic hook framework for quality enforcement and context injection
Key points
- turboshovel
- AI & Agent Building
- AI-coding skill
Turboshovel by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add tobyhede/turboshovel/plugin install turboshovel@turboshovelAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Last updated | January 14, 2026 |
|---|---|
| Repository | tobyhede/turboshovel ↗ |
What it does
Generic hook framework for quality enforcement and context injection
README.md
Turboshovel
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.
Features
💾 Persistent State
Workflow progress survives context clears. Resume interrupted tasks instantly. Never lose track of where you are.
🛡️ Process Enforcement
Enforce multi-step workflows with Rundown runbooks. Prevent agents from skipping steps or jumping around.
⚙️ Quality Gates
Run lint, test, build at workflow boundaries. Block agents when checks fail. Chain gates for complex pipelines.
🧠 Context Injection
Auto-inject context at runbook steps. Agents get focused, step-specific instructions exactly when needed.
Installation
claude plugin add tobyhede/turboshovel
Turboshovel includes Rundown for workflow orchestration.
Quick Start
1. Create a Runbook
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
2. Add Quality Gates
Create .claude/turboshovel.json:
{
"gates": {
"test": {
"command": "npm test",
"on_fail": "BLOCK"
}
},
"hooks": {
"SubagentStop": {
"gates": ["test"]
}
}
}
3. Run the Workflow
rundown run .claude/rundown/runbooks/feature.runbook.md
How it works:
- Runbook defines the workflow steps and transitions
- State persists in
.claude/rundown/session.json - Context clears?
rundown statusshows where you are - Gates enforce quality at each step boundary
CLI Commands
rundown 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
Documentation
- SETUP.md - Full configuration guide
- CONVENTIONS.md - Context file naming conventions
- ARCHITECTURE.md - System design
- TYPESCRIPT.md - Custom TypeScript gates
License
MIT