loop-engineering
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
Runssource: GitHubhomepageTypeScriptMITcommit 7422449e2297
TypeScript, MIT licensed. The project labels itself: agentic ai, ai agents, ai coding, anthropic, automation, claude, claude code and codex.
loop-engineering runs. An Argusic agent installed it in 27 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 15 TypeScript tools in tools/ build and pass their test suites (298 passed), unified loop CLI (tools/loop) runs doctor/status/audit with real audit output scoring 100/100 L3, before-after-demo.sh exercises the full empty→L2 scaffold pipeline end to end
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- loop-sandbox uses '^1.3.0' registry semver instead of local file: dependency on loop-worktree, breaking loop-swarm transitive resolution4 minutes
- loop-audit failing 2 tests — ERR_MODULE_NOT_FOUND for readiness-core2 minutes
- loop-metrics test had hardcoded date 2026-07-30 that fell outside 30-day window1 minute
- Install time
- 27 minutes
- Cold machine to finish
- 28 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm test on each of 15 tools: 298 tests passing across all packages, loop doctor returns 100/100 L3 with real data, loop status returns recent runs, before-after-demo.sh completes successfully
- Model tokens used
- 527,277
- Exact commit tested
- 7422449e2297
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
M tools/loop-worktree/dist/cli.js M tools/mcp-server/package-lock.json M tools/mcp-server/package.json Now let me compile the final summary. Let me check the timing exec /bin/sh -lc 'date -u +%s' in /work/repo succeeded in 0ms: 1789136036 Here is my full report. tokens used 527,277 Here is my full report.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 27 minutes to install, slower than the median of the 7 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 8 agentic-ai projects Argusic has installed and timed, loop-engineering was the 7th fastest to reach a running state, and 5 of 8 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agentic-aiai-agentsai-codinganthropicautomationclaudeclaude-codecodexcoding-agentsdevops-automationdevtoolsgithub-actionsgrokllmloop-engineeringmcpprompt-engineering
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/loop-engineering)Questions
- Does loop-engineering run?
- Yes. loop-engineering runs. Argusic installed and launched it on a clean machine in 27 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test loop-engineering?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7422449e2297. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test loop-engineering?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does loop-engineering take to install?
- 27 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does loop-engineering need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing loop-engineering?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does loop-engineering compare with the alternatives?
- Of the 8 agentic-ai projects Argusic has installed and timed, loop-engineering was the 7th fastest to reach a running state, and 5 of 8 reached one at all.
- Where is the evidence for loop-engineering?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.