Loop Engineering Playbooks.
The agent stops the second you stop typing. Build the loop that does not: a contract it reads every iteration, an exit condition a computer evaluates, a separate verifier it cannot talk past, and a receipt in tokens, minutes, and dollars.
2 titles · 10 free guides
Are Your Overnight Claude Agents Making You Money?
Work out in dollars whether an overnight Claude Code run made you money, using its own result files and your hourly rate. In a worked example the tokens cost $6.40 either way, but checking the work line by line takes the cost per usable change from $13.63 to $43.71.
from: Claude Code Loops
What to Do When Claude Code Gets Stuck in a Loop
When Claude Code gets stuck in a loop overnight, make it try something different each time and stop with a note after 4 tries. Wrong API keys, blocked files and an empty budget are never retried, and each try gets its own slice of the budget.
from: Claude Code Loops
Why Claude Code Fails Overnight
Find out in one command why last night's Claude Code loop failed and what to do about it. There are 6 ways a loop fails, each leaves a trace in the loop's own result files, and the most common fake success comes from a check that exits 1.
from: Claude Code Loops
How to Build a Multi-Step Loop With Claude
Run two Claude Code loops back to back every night, where the second only starts if the first one's work passed its check. It takes four checks in shell, and the schedule has to live somewhere other than /loop, whose recurring tasks expire 7 days after creation.
from: Claude Code Loops
Are You a Loop Engineer or Still Babysitting Claude Code?
Find out whether you are doing loop engineering or still babysitting Claude Code, with two numbers from your own sessions. The rung audit scores turns per finished task and how often you repeat yourself, and it never parses a transcript file.
from: Claude Code Loops
How to Give an Agentic Loop an Exit Condition
An agentic loop exit condition has two halves: a measurable pass criterion and a hard cap. Wire both in Claude Code so a runaway loop stops in 1-4 turns.
from: Claude Code Loop Engineering
How to Cap a Claude Code Loop's Spend
Set a Claude Code budget limit per run so an unattended loop can't burn $200 overnight: a hard --max-budget-usd cap, a model router, and context trimming.
from: Claude Code Loop Engineering
/loop vs /goal in Claude Code: The Real Difference
Claude Code /loop vs /goal confuses everyone. /goal is the self-correcting loop that fixes code; /loop is a scheduler that polls. Here's each in its place.
from: Claude Code Loop Engineering
Agent Loop vs Single Prompt vs Fan-Out: When to Use Each
When to use an agent loop vs a single prompt vs fan-out comes down to task shape. A 3-question test routes any coding task to the cheapest tool that fits.
from: Claude Code Loop Engineering
Read them in this order. Each one assumes the one before it.
Claude Code Loops
A fleet of loops that runs overnight, verifies its own work before it reaches your branch, and prints the bill
Claude Code Loop Engineering
A bounded, self-correcting Claude Code loop that ships trusted code overnight without burning $200
These titles sit on a path that tells you which three to buy first.