Skip to main content
SubTurtles support four loop types:
  • slow
  • yolo
  • yolo-codex
  • yolo-codex-spark
Choose loop type based on complexity, iteration speed, and quota pressure.

​
At a Glance

TypeCalls per iterationRuntimeBest for
slow4 calls (Plan -> Groom -> Execute -> Review)Claude + CodexComplex, high-risk multi-file work
yolo1 callClaudeDefault for most tasks
yolo-codex1 callCodexCost-efficient coding tasks
yolo-codex-spark1 callCodex Spark (gpt-5.3-codex-spark)Fastest Codex iterations
ctl spawn and ctl start default to --type yolo.

​
How Each Loop Executes

The loop dispatcher maps type to runtime function: 
LOOP_TYPES = {
    "slow": run_slow_loop,
    "yolo": run_yolo_loop,
    "yolo-codex": run_yolo_codex_loop,
    "yolo-codex-spark": run_yolo_codex_spark_loop,
}

​
slow (Most Thorough)

slow runs a 4-phase loop each iteration:
  1. Planner (Claude) creates one-commit plan.
  2. Groomer (Claude) updates CLAUDE.md backlog/current marker.
  3. Executor (Codex) implements the plan.
  4. Reviewer (Claude) validates and adds follow-ups if needed.
Use slow when:
  • The task is ambiguous or architecture-heavy.
  • Multiple files/systems must stay consistent.
  • You want explicit planning and review every cycle.
Tradeoff:
  • Highest quality guardrails.
  • Slowest and most expensive per iteration.
./super_turtle/subturtle/ctl spawn api-hardening --type slow --timeout 2h --state-file /tmp/api-hardening.md

​
yolo (Fast Claude Loop)

yolo runs a single Claude call per iteration using the state-file protocol. Use yolo when:
  • Scope is clear.
  • You still want Claude-centric reasoning.
  • Codex quota is constrained.
Tradeoff:
  • Faster than slow.
  • Less structured guardrail than Plan/Groom/Review.
./super_turtle/subturtle/ctl spawn auth-fix --type yolo --timeout 1h --state-file /tmp/auth-fix.md

​
yolo-codex

yolo-codex is the same single-call loop model as yolo, but uses Codex. Use yolo-codex when:
  • Work is implementation-heavy and well-scoped.
  • You want best cost-efficiency for autonomous backlog progress.
  • You are spawning many SubTurtles in parallel.
Tradeoff:
  • Best default cost/speed balance.
  • May require tighter state-file specificity than slow.
./super_turtle/subturtle/ctl spawn docs-agent --type yolo-codex --timeout 1h --state-file /tmp/docs-agent.md

​
yolo-codex-spark (Fastest Iterations)

yolo-codex-spark uses the Codex runtime with model gpt-5.3-codex-spark. Use yolo-codex-spark when:
  • Latency matters more than deep reasoning.
  • You want very rapid short iterations.
  • Tasks are concrete and low-ambiguity.
Tradeoff:
  • Fastest loop turnaround.
  • Least conservative option for complex design decisions.
./super_turtle/subturtle/ctl spawn ui-polish --type yolo-codex-spark --timeout 45m --state-file /tmp/ui-polish.md

​
Selection Guide

1

Default to yolo

Start with yolo for most tasks. It is the project default and uses Claude Code.
2

Escalate to slow for complex work

If a task needs explicit planning/review or crosses many boundaries, switch to slow.
3

Use yolo-codex for cost efficiency

Pick yolo-codex when you want lower cost or Claude quota is constrained.
4

Use yolo-codex-spark for shortest feedback loops

Pick Spark for highly concrete work where rapid iterations matter most.

​
Cost and Speed Tradeoffs

PriorityRecommended typeWhy
Maximum quality checksslowIncludes planning and review each iteration
Balanced defaultyoloSingle-call loop + Claude reasoning
Cost-efficientyolo-codexSingle-call loop + low-cost Codex runtime
Maximum iteration speedyolo-codex-sparkSpark model tuned for fast cycles

​
Operational Notes

  • All loop types read .subturtles/<name>/CLAUDE.md as the source of truth.
  • All loop types check for self-stop directive:
## Loop Control
STOP
  • Timeout/watchdog behavior is independent of loop type.
  • Cron supervision behavior is independent of loop type.