StackMap
Subscribe
Explore / loop-engineering
cobusgreyling

loop-engineering

Reference repo plus npm CLIs (loop-init/audit/cost) for loop engineering: designing scheduled, gated control loops that prompt and orchestrate AI coding agents — Grok, Claude Code, Codex — over time.

8,044 1,051 JavaScript MITupdated today
codingorchestration
View on GitHubDispute this mapping →
Curator's take

The methodology layer for autonomous coding agents — read it once you've stopped hand-prompting and want to design the loop that prompts the agent instead: scheduled triage, worktree isolation, maker/checker sub-agents, MCP connectors, human gates, and a phased L1-report → L3-unattended rollout. Ships 7 clone-and-run patterns, tool-agnostic starters (Grok/Claude Code/Codex/OpenCode), and CLIs that score loop-readiness (loop-audit), estimate token spend (loop-cost) and scaffold state/budget (loop-init). It's a patterns + tooling reference, NOT a runtime — it won't execute or host your agents, so bring your own harness (an alook-style AI-company layer or a squid-style pipeline). Overkill if you just want one-shot interactive help; heed its own caveat that unattended loops make unattended mistakes, so verification stays on you.

Mapped by ShipWithAI editors · links verified
README.md

Loop Engineering

Explore the Showcase

GitHub stars loop-audit dogfood loop-audit npm loop-init npm loop-cost npm loop-sync npm loop-context npm loop-mcp-server npm loop-worktree npm MIT Pages

Loop Engineering logo

Stop prompting. Design the loop. Get a score.

Loop Engineering — design the system that prompts your agents 

npx @cobusgreyling/loop-init .

loop-init scaffolds skills, state, and budget files, then prints your Loop Ready score and first loop command. Swap --tool for claude, codex, or opencode.

Loop Ready score climbs from 10 to 100 in 15 seconds

Loop engineering replaces you as the person who prompts the agent — you design the system that does it instead.

New here? Quickstart (5 min) · Interactive picker

For developers using Grok, Claude Code, Codex, Cursor, and other AI coding agents.

→ Interactive showcase + pattern picker · Essay · Addy Osmani

Contents

Continue your stack

What teams reach for next — and why each earns a place beside loop-engineering. Ranked by curator confidence.

Pairs well with
squid

Claude Code plugin that turns a feature spec into a reviewed PR through a 5-agent pipeline — PA → SWE → Tester → PR-Reviewer → On-Call — with exactly two human gates.

Why it fitssquid is a concrete, productized maker/checker agent pipeline (PA→SWE→Tester→PR-Reviewer→On-Call) with human gates; loop-engineering is the cross-tool methodology and CLI tooling (PR-babysitter/CI-sweeper patterns, loop-audit, loop-worktree, design checklist) behind such pipelines. Use loop-engineering to design the loop, squid as one ready-made implementation.
govctl

Governance-as-code CLI for AI-assisted development: prompts and patches become RFCs, ADRs and work items with executable verification gates — reviewable, traceable, phase-gated delivery.

Why it fitsTwo halves of disciplined AI delivery: loop-engineering designs the gated control loops that drive coding agents; govctl supplies the governance artifacts and executable completion gates those loops should answer to.
alook

Self-hosted collaboration layer that turns local coding agents (Claude Code, Codex, OpenCode) into an always-on "AI company" — per-agent email, org chart, kanban, shared memory.

Why it fitsalook is an always-on multi-agent 'AI company' runtime (per-agent email, org chart, kanban, shared memory) for local coding agents; loop-engineering supplies the loop-design methodology plus scheduling, state and budget tooling to drive agents autonomously. Design the loops with one, run them on the other.