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.

prompt
→ Claude
Skill interviews you about the automation idea, writes loop artifacts to `looper-output/`, shows an ASCII flow preview, and only finalizes after you confirm — design the loop before any runner touches files.
claude-code

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.

Source: ksimback/looper

More planning loops

loop-init, loop-audit, loop-cost CLI patterns

/ralphnew

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.

prompt
→ Claude
Starter CLI tools: `loop-init` scaffolds a loop (goal, budget, verify step), `loop-audit` reviews an existing loop design, `loop-cost` estimates spend before running.
planningmedium risk

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.

prompt
→ Claude
/loop start each iteration with fresh context: read PROMPT.md, prd.json, and .ralph/guardrails.md; pick the single highest-priority item in prd.json not marked done, implement it with tests, run the full check suite, commit and mark it done only if green; if blocked or a check fails twice the same way, append the lesson to .ralph/guardrails.md and move on; stop when every item is done or after 30 turns
planninghigh risk

Set agent continuation budget

/goalnew

Configure max turns before agent stops, preventing runaway loops and controlling execution cost.

prompt
→ Claude
/goal budget <n Set max continuation turns
planninglow risk