{"slug": "loop-engineering-score-the-system-that-prompts-your-agents", "title": "Loop Engineering: Score the System That Prompts Your Agents", "summary": "Loop Engineering introduces a framework and CLI toolkit for designing systems that prompt coding agents, shifting the bottleneck from individual prompts to orchestration loops. The project, published as npm packages, provides tools to scaffold, audit, and cost-estimate agent loops, with a phased rollout from read-only to unattended execution. It targets developers using agents like Grok, Claude Code, and Cursor, emphasizing safety through human gates and cost transparency.", "body_md": "Loop Engineering makes a blunt argument: the person who writes prompts to a coding agent is now the bottleneck, so the job is to design the system that prompts the agent instead. The repo, cobusgreyling/loop-engineering, turns that claim into something you can measure. Run `npx @cobusgreyling/loop-init .`\n\nand it scaffolds skills, state, and budget files, then prints a \"Loop Ready\" score and your first loop command. The pitch on the tin is equally direct: stop prompting, design the loop, get a score.\n\nThe README does not lean on its own authority. It quotes Peter Steinberger (\"You shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents\") and Boris Cherny, Head of Claude Code at Anthropic (\"I don't prompt Claude anymore. I have loops running that prompt Claude... My job is to write loops\"). The framing that follows is the useful part: the leverage point has moved from crafting individual prompts to designing the control systems that orchestrate agents over time.\n\nLoop Engineering breaks that control system into five building blocks plus memory. Automations and scheduling handle discovery and triage on a cadence. Worktrees give safe parallel execution. Skills hold persistent project knowledge. Plugins and connectors reach into real tools through MCP. Sub-agents split the work into a maker and a checker. Memory and state sit outside any single conversation as the durable spine. That list is opinionated, and it reads like the parts list for the animated loop the README diagrams: schedule, triage skill, read and write state, isolated worktree, implementer sub-agent, verifier sub-agent, then a human gate that either commits or escalates with full context.\n\nWhat separates this from a manifesto is the CLI surface. The repo ships a cluster of npm packages, each doing one small job. `loop-audit`\n\ncomputes a Loop Readiness Score and can suggest fixes or emit a badge for your README. `loop-init`\n\nscaffolds a starter with a budget and run log. `loop-cost`\n\nestimates token spend for a given pattern and cadence before you commit to it. `loop-sync`\n\ndetects drift between `STATE.md`\n\nand `LOOP.md`\n\n. `loop-context`\n\nmanages stateful memory and adds a circuit breaker for long runs. `loop-mcp-server`\n\nexposes patterns, skills, and state over MCP. `loop-worktree`\n\nmanages isolated git worktrees per fix attempt. The tools publish to npm from tagged releases, so no clone is required to try them.\n\nThe patterns section is where the token-cost honesty shows. Seven production patterns come with a cadence and a cost rating. Daily Triage runs on a one-day-to-two-hour cadence and is cheap. PR Babysitter runs every five to fifteen minutes and is flagged High. CI Sweeper, at the same cadence, is Very High. Dependency Sweeper, Changelog Drafter, Post-Merge Cleanup, and Issue Triage round out the set, mostly at Low cost. Putting \"Very high\" next to a pattern in the same table that sells you on it is a small act of restraint worth noting.\n\nThe rollout advice matches. The README pushes a phased path: L1 report only, then L2 assisted fixes, then L3 unattended. The Grok example even spells it out (\"Run loop-triage. Update STATE.md. No auto-fix in week one\"). This is a project telling you to start by watching before you let anything write.\n\nLoop Engineering aims at developers using Grok, Claude Code, Codex, Cursor, and Opencode, with a cross-tool primitives matrix meant to map loop concepts across those agents. The repo also dogfoods: it runs its own `validate-patterns`\n\nand `audit`\n\nworkflows on every push and pull request, and ships a `LOOP.md`\n\ndescribing the loops that maintain it.\n\nThe README is heavy on links out to docs, starters, and a live interactive picker, so some of the depth lives outside the page itself. The concepts here are also young, and the core idea of handing scheduled, semi-autonomous loops write access to your repo carries real risk, which is exactly why the L1-first, human-gate framing matters. If you have been wiring up cron jobs and sub-agents by hand, this repo is a structured vocabulary and a scorecard for work you may already be improvising.\n\n**GitHub:** [https://github.com/cobusgreyling/loop-engineering](https://github.com/cobusgreyling/loop-engineering)\n\n*Curated by Agent Palisade — practical AI for small and mid-sized businesses.*", "url": "https://wpnews.pro/news/loop-engineering-score-the-system-that-prompts-your-agents", "canonical_source": "https://dev.to/renolu/loop-engineering-score-the-system-that-prompts-your-agents-emd", "published_at": "2026-07-11 14:18:35+00:00", "updated_at": "2026-07-11 14:45:27.661400+00:00", "lang": "en", "topics": ["developer-tools", "ai-agents", "ai-tools", "ai-infrastructure"], "entities": ["Loop Engineering", "Peter Steinberger", "Boris Cherny", "Anthropic", "Claude Code", "Grok", "Codex", "Cursor"], "alternates": {"html": "https://wpnews.pro/news/loop-engineering-score-the-system-that-prompts-your-agents", "markdown": "https://wpnews.pro/news/loop-engineering-score-the-system-that-prompts-your-agents.md", "text": "https://wpnews.pro/news/loop-engineering-score-the-system-that-prompts-your-agents.txt", "jsonld": "https://wpnews.pro/news/loop-engineering-score-the-system-that-prompts-your-agents.jsonld"}}