Boris Cherny loop methodology + agent-loop skill

A fact-checked knowledge base of Claude Code creator Boris Cherny's loop methodology, packaged as a runnable agent-loop skill you can drop straight into Claude Code.

prompt
→ Claude
Fact-checked knowledge base of Cherny's loop methodology for running Claude Code, shipped as a runnable `agent-loop` skill in `skill/agent-loop/`.
claude-code

Implementation note

When to use: you want to learn or standardize on loop practice from the source — Boris Cherny created Claude Code, and this packages his loop methodology in runnable form rather than as scattered posts. How it works: a fact-checked knowledge base of Cherny's methodology for running Claude Code in loops, shipped with a runnable agent-loop skill in skill/agent-loop/ that you can drop straight into Claude Code and invoke. The knowledge-base half explains the reasoning; the skill half executes the pattern, so the methodology and its implementation stay in sync. Safety: fact-checked is the notable attribute — loop advice attributed to Cherny circulates widely with varying accuracy, and this repo's stated purpose is verifying claims before packaging them. Still treat the skill like any third-party skill: read what it does before running it, and apply your own turn caps and branch discipline around it.

Source: cocodedk/loop-engineering

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