learn-harness-engineering
Harness engineering beginner tutorial, from 0 to 1
Runs with mockssource: GitHubTypeScriptMITcommit 77e7a3e21469
TypeScript, MIT licensed. The project labels itself: agent, agentic, agentic ai, ai, ai agent, ai agents, dsh and dsh plugin.
learn-harness-engineering runs, with stand-ins for the services it depends on. An Argusic agent installed it in 30 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Root npm install succeeded, VitePress docs dev server serves all pages with 200, all 15 project Electron apps build successfully, and project-01 starter Electron app launches and stays running in the container.
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 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- VitePress static build (npm run docs:build) exhausts heap on 512MB machine with 15 locales; OOM on node v18.19.1 even with --max-old-space-size=4008 minutes
- Electron startup errors: dbus connection failures, GPU process exit — expected in headless container3 minutes
- Install time
- 30 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- curl http://localhost:5174/learn-harness-engineering/en/ returned 200; curl http://localhost:5174/learn-harness-engineering/en/lectures/lecture-01-why-capable-agents-still-fail/ returned 200; npx electron . --no-sandbox --disable-gpu ran for 10s timeout then exited 124 (killed, not crash); npm run build exited 0 in all 15 project directories
- Model tokens used
- 603,618
- Exact commit tested
- 77e7a3e21469
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Minutes elapsed:** ~30 minutes **Install summary:** - Root `npm install` succeeded (272 packages) - All 15 project directories installed and built successfully (project-01 through project-06, each … **Errors encountered:** 1. **VitePress static build OOM** — `npm run docs:build` exhausts heap on 512MB machine even with `… 2. **Electron sandbox / dbus / GPU errors** — Expected in a container environment. `--no-sandbox --… 3. **Type-check errors in project-01 starter/solution** — Pre-existing issues in the course code (u… **Verification:** - VitePress dev server: `curl http://localhost:5174/learn-harness-engineering/en/` returns 200; lec… - Project-01 starter: `npm run build` succeeds, `npx electron . --no-sandbox --disable-gpu` stays u… - Project builds across all 15 project directories succeed with no errors
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
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 30 minutes to install, slower than the median of the 39 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 40 agent projects Argusic has installed and timed, learn-harness-engineering was the 35th fastest to reach a running state, and 30 of 40 reached one at all.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
agentagenticagentic-aiaiai-agentai-agentsdshdsh-pluginharnessharness-engineeringharness-frameworkllm
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/learn-harness-engineering)Questions
- Does learn-harness-engineering run?
- learn-harness-engineering runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 30 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test learn-harness-engineering?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 77e7a3e21469. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test learn-harness-engineering?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does learn-harness-engineering take to install?
- 30 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 learn-harness-engineering need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing learn-harness-engineering?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does learn-harness-engineering compare with the alternatives?
- Of the 40 agent projects Argusic has installed and timed, learn-harness-engineering was the 35th fastest to reach a running state, and 30 of 40 reached one at all.
- Where is the evidence for learn-harness-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.