Looper — design-review your loop before running it
A plan-the-loop-first skill: it interviews you about the automation idea, previews the flow as ASCII art, and only writes final loop artifacts after you confirm — a safe on-ramp for loop beginners.
Implementation note
When to use: you are new to loops, or about to run one complex enough that a design mistake is expensive — this is the plan-first on-ramp that front-loads the thinking before any runner touches files. How it works: the skill interviews you about the automation idea, asking the questions a loop design needs answered, then writes the loop artifacts to looper-output/ and shows you an ASCII flow preview of what the loop will actually do. Nothing is finalized until you explicitly confirm — design the loop, inspect it, then run it, as separate steps. Safety: confirmation-before-finalize is the structural rail: the skill produces no final artifacts and runs nothing until you approve the previewed design, so the worst case of a bad interview is a discarded draft in looper-output/. The preview step catches the wrong loop shape before it costs tokens. The eventual run still needs its own caps.
More planning loops
loop-init, loop-audit, loop-cost CLI patterns
Three starter CLI tools that turn loop design into a repeatable workflow: scaffold a loop with a goal, budget, and verify step; audit an existing loop design; and estimate cost before you run.
Ralph the PRD backlog
The canonical Ralph loop: each iteration starts fresh, reads the PRD and guardrails, ships exactly one backlog item end-to-end, and records what it learned.
Set agent continuation budget
Configure max turns before agent stops, preventing runaway loops and controlling execution cost.