Guides
Practical, safety-first guides to writing and running agent loops — 19 published.
Code Review Loops: Five Claude Code Patterns That Keep PRs Moving
Code review is the stage of the pipeline that most reliably goes idle. You open a PR, reviewers respond on their own schedule, CI fails twenty minutes after you've moved on, and a change that took an hour to write
How to Create Loops with Claude: From One-Shot Prompts to Designed Loops
Most people use Claude the way they'd use a search box: type a request, get an answer, move on. That works until the work doesn't
Why Your Loop Got an F: How Agent-Loop Grading Actually Works
In August 2026 we ran fifteen published Ralph-style loops — real ones, read at the source, graded on their upstream descriptions
Loop Engineering: The Roadmap From Prompter to Loop Designer
Based on a roadmap shared by @0xCodez on X, content credited to Lev Deviatkin. Prompting is a conversation. Loop engineering is a
Observability Is Part of the Harness, Not an Afterthought
The usual order of operations is: build the loop, run it overnight, and add logging the morning you find it did something wrong
The Init Phase Your Loop Is Skipping
Most loops start work on iteration one. That is the bug. The agent reads its standing instructions, picks up the goal, and
Feature Lists Are a Harness Primitive, Not a To-Do List
Most people hand an agent a paragraph. "Build the checkout flow: cart, payment, receipt email, and an admin refund view." Then
One CLAUDE.md to Rule Them All (and Why That's the Bug)
Every agent project starts the same way. One CLAUDE.md, or one AGENTS.md, holding everything the agent needs to know: the stack
How to Keep an Agent Loop From Running Away
You hand an agent a goal and walk away. That is the entire point — you stop watching. The danger is that the agent doesn't stop
The Claude Code Harness: Plan → Work → Review → Release
Raw agent sessions drift. The plan lives in chat scrollback, so by turn forty nobody — including the agent — can say what was
The Anatomy of an Agent Loop: Five Parts and One Gate
This month, at least seven people published long "how to build agent loops" write-ups within a few weeks of each other. Different
Loop Engineering: What the 8-Million-View Threads Get Right, Wrong, and Made Up
Between June 7 and July 8, 2026, "loop engineering" went from a two-line post to a content wave: multi-part roadmaps, hour-long
CI Loops for Claude Code: Watch PR Checks Without Babysitting the Terminal
A CI loop moves PR-check polling from you to the agent. You open the pull request, hand the watching to Claude Code, and get
Loops Gone Wrong: Documented Agent Failures and the Guardrail Each One Teaches
This is an incident file: documented agent-loop failures, each with its primary source, and the specific control that would have
/goal vs /loop vs /schedule vs Ralph: Which Loop Do You Actually Need?
Claude Code has four ways to run without you: /goal, /loop, /schedule, and Ralph. From the outside they all look like "the agent
Claude Code /schedule Examples: A Cookbook
A schedule loop runs when the clock says so, not when a condition is met. It fits work that recurs and never stays done: issue
Agent Loop Safety: Hooks, Budgets, and Evaluators
A loop running claude -p with --dangerously-skip-permissions has no human between the agent and your filesystem. Something
15 /goal Examples You Can Copy-Paste (With Exit Conditions)
A goal loop has three parts: an outcome, a command that proves the outcome, and a cap on iterations. The exit condition does the
The Ralph Wiggum Loop: One Prompt, Fresh Context, Repeat
The Ralph Wiggum loop runs one prompt against your repo in a bash while true, with fresh context every iteration. No