Which AI agents does this loop work with?

Guardrails that learn from failure is written for claude-code, codex.

Is this loop safe to run unattended?

This loop is graded B (85/100) by looprepo's automatic safety evaluator, which checks for exit conditions, iteration budgets, verification steps, and scoping before publishing.

Loop/ralph Automationmedium riskadvancedsafety B · 85 · open-ended Geoffrey Huntley

Guardrails that learn from failure

A Ralph-style loop that writes its own rules: when a check fails the same way twice, the failure pattern gets appended to a guardrails file that every later iteration reads first.

prompt

→ Claude

/loop read .ralph/guardrails.md before doing anything, then run the full check suite and fix the first failure; if a check fails twice with the same error, append the failure pattern and a one-line rule for avoiding it to .ralph/guardrails.md before retrying; stop when all checks pass or after 15 turns

claude-code · codex

Implementation note

Create an empty .ralph/guardrails.md first and commit it so learned rules survive across sessions. The file becomes a project-specific playbook of what not to do.

Source: Geoffrey Huntley (Ralph technique) ↗

More automation loops

Ship production-grade apps autonomously

Loop/ralphnew

Hand an idea to Claude Code; it authors specs, designs, builds, tests, secures, and ships until enterprise done or budget exhausted.

prompt

→ Claude

# dare-to-be-stupid — Design (v2, refined) > A Claude Code plugin. One command, /dare , hands an idea or PRD to an autonomous > loop that authors specs, designs, builds, tests, secures, ships, fixes, and iterates > until the app passes an enterprise-production definition of done — or the budget dies. > > Named for the Weird Al song. The joke is that it runs the Ralph Loop on purpose , > with --dangerously-skip-permissions , and narrates the whole thing in the voice of an > '80s Junkion. Pre-production only. Never points at anything with users. This is v2. It keeps the strong core of the original spec (external reviewer, ratchet, guard hook, Junkion style) and adds the three phases the original left thin relative to the actual goal: PRD authoring, a design phase, and a real enterprise DoD including security, CI, docs/observability, and design quality (with quality plugins auto-installed). --- ## 0. The premise, in one paragraph The User builds documentation-first: spec → system docs → API contracts → CLAUDE.md → code. dare-to-be-stupid is the deliberate inverse, packaged as comedy that also solves two real engineering problems. It is a real build , not a joke ar

automationhigh riskclaude-code

source ↗

claude-progress.txt harness pattern (Anthropic)

Loop/ralph★ Anthropic

Anthropic's first-party file-as-memory harness for long-running agents: every fresh-context session recovers state from a progress file and the git log, does one unit of work, updates the file, commits, and exits.

prompt

→ Claude

Long-running agent harness: each fresh-context session starts by reading `claude-progress.txt` + git log to recover state, does one unit of work, updates the progress file, commits, exits. Initializer session sets up the file; coder sessions loop. Guardrails: Stop when the goal is verifiably met, or stop after 15 iterations, whichever comes first. Verify each pass by running the relevant tests or checks — self-reported success does not count. Keep changes minimal and never touch files outside the task’s scope.

automationmedium riskclaude-code

Complete all tasks in tasks.md

Loop/ralphnew

Work through your tasks.md file, completing each task until none remain or max iterations is reached.

prompt

→ Claude

/ralph-loop "Complete all tasks in tasks.md" --max-iterations 50

automationmedium riskclaude-code