loop-worker
Run Ruflo background workers using Claude Code native /loop scheduling
Best for long-running sessionsWorks with GitHubLow risk
⌘source
- author
@ruvnet- repo
- ruvnet/ruflo
- language
- TypeScript
★46kstars
5.1kforks
May 5, 2026
✦overview.md
Key Features
- ·In-session periodic workers via /loop
- ·Cache-aware delay formula (min(270s, cachettl0.9))
- ·MCP dispatch for workers
- ·ScheduleWakeup for next iteration
- ·Pre-built workers: audit, optimize, consolidate, etc.
Use Cases
- →Running a security audit every 270 seconds
- →Periodic performance optimization during a long session
- →Background memory consolidation every 600 seconds
- →Automated test coverage analysis at intervals
Best for
- ✓long-running sessions
- ✓background tasks
- ✓recurring analysis
Not ideal for
- !single-shot scripts
- !latency-sensitive tasks
FAQs
name
loop-worker
description
Run Ruflo background workers using Claude Code native /loop scheduling
argument-hint:<worker-name>
allowed-tools:Bash(npx *) mcp__claude-flow__hooks_worker-dispatch mcp__claude-flow__hooks_worker-status ScheduleWakeup
Use /loop for in-session periodic workers. Cache-aware delays keep prompt cache warm:
- Delay formula:
min(270, cache_ttl * 0.9)-- default 270s
Dispatch a worker via MCP: mcp__claude-flow__hooks_worker-dispatch({ trigger: "WORKER_NAME" })
Then schedule the next iteration: ScheduleWakeup({ delaySeconds: 270, reason: "next WORKER_NAME iteration" })
Available Workers
| Worker | Interval | Description |
|---|---|---|
| audit | 270s | Security analysis |
| optimize | 270s | Performance optimization |
| consolidate | 600s | Memory consolidation |
| predict | 270s | Predictive preloading |
| map | 600s | Codebase mapping |
| testgaps | 270s | Test coverage analysis |
| document | 600s | Auto-documentation |
| benchmark | 600s | Performance benchmarking |
MCP tool responses include [LOOP_SUGGESTION] and [CRON_SUGGESTION] hints -- follow them.
$install
1-click copynpx skills add ruvnet/ruflo --skill loop-workerSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.